[INFO] fetching crate rusoto_sagemaker 0.48.0...
[INFO] documenting rusoto_sagemaker-0.48.0 against 1.69.0 for beta-1.70-rustdoc-1
[INFO] extracting crate rusoto_sagemaker 0.48.0 into /workspace/builds/worker-0-tc1/source
[INFO] validating manifest of crates.io crate rusoto_sagemaker 0.48.0 on toolchain 1.69.0
[INFO] running `Command { std: CARGO_HOME="/workspace/cargo-home" RUSTUP_HOME="/workspace/rustup-home" "/workspace/cargo-home/bin/cargo" "+1.69.0" "metadata" "--manifest-path" "Cargo.toml" "--no-deps", kill_on_drop: false }`
[INFO] started tweaking crates.io crate rusoto_sagemaker 0.48.0
[INFO] finished tweaking crates.io crate rusoto_sagemaker 0.48.0
[INFO] tweaked toml for crates.io crate rusoto_sagemaker 0.48.0 written to /workspace/builds/worker-0-tc1/source/Cargo.toml
[INFO] running `Command { std: CARGO_HOME="/workspace/cargo-home" RUSTUP_HOME="/workspace/rustup-home" __CARGO_TEST_CHANNEL_OVERRIDE_DO_NOT_USE_THIS="nightly" "/workspace/cargo-home/bin/cargo" "+1.69.0" "generate-lockfile" "--manifest-path" "Cargo.toml" "-Zno-index-update", kill_on_drop: false }`
[INFO] running `Command { std: CARGO_HOME="/workspace/cargo-home" RUSTUP_HOME="/workspace/rustup-home" "/workspace/cargo-home/bin/cargo" "+1.69.0" "fetch" "--manifest-path" "Cargo.toml", kill_on_drop: false }`
[INFO] running `Command { std: "docker" "create" "-v" "/var/lib/crater-agent-workspace/builds/worker-0-tc1/target:/opt/rustwide/target:rw,Z" "-v" "/var/lib/crater-agent-workspace/builds/worker-0-tc1/source:/opt/rustwide/workdir:ro,Z" "-v" "/var/lib/crater-agent-workspace/cargo-home:/opt/rustwide/cargo-home:ro,Z" "-v" "/var/lib/crater-agent-workspace/rustup-home:/opt/rustwide/rustup-home:ro,Z" "-e" "SOURCE_DIR=/opt/rustwide/workdir" "-e" "CARGO_TARGET_DIR=/opt/rustwide/target" "-e" "CARGO_HOME=/opt/rustwide/cargo-home" "-e" "RUSTUP_HOME=/opt/rustwide/rustup-home" "-w" "/opt/rustwide/workdir" "-m" "1610612736" "--user" "0:0" "--network" "none" "ghcr.io/rust-lang/crates-build-env/linux@sha256:5ff2268d62e97bff2cde7d5815dd6ed5b47097566f13b8d0ca110b04b60e07ed" "/opt/rustwide/cargo-home/bin/cargo" "+1.69.0" "metadata" "--no-deps" "--format-version=1", kill_on_drop: false }`
[INFO] [stdout] c4b0b57b9a3aa405aab95d95f5705492ae1a45ddd1b887c7c9e1c764a9087cf8
[INFO] running `Command { std: "docker" "start" "-a" "c4b0b57b9a3aa405aab95d95f5705492ae1a45ddd1b887c7c9e1c764a9087cf8", kill_on_drop: false }`
[INFO] running `Command { std: "docker" "inspect" "c4b0b57b9a3aa405aab95d95f5705492ae1a45ddd1b887c7c9e1c764a9087cf8", kill_on_drop: false }`
[INFO] running `Command { std: "docker" "rm" "-f" "c4b0b57b9a3aa405aab95d95f5705492ae1a45ddd1b887c7c9e1c764a9087cf8", kill_on_drop: false }`
[INFO] [stdout] c4b0b57b9a3aa405aab95d95f5705492ae1a45ddd1b887c7c9e1c764a9087cf8
[INFO] running `Command { std: "docker" "create" "-v" "/var/lib/crater-agent-workspace/builds/worker-0-tc1/target:/opt/rustwide/target:rw,Z" "-v" "/var/lib/crater-agent-workspace/builds/worker-0-tc1/source:/opt/rustwide/workdir:ro,Z" "-v" "/var/lib/crater-agent-workspace/cargo-home:/opt/rustwide/cargo-home:ro,Z" "-v" "/var/lib/crater-agent-workspace/rustup-home:/opt/rustwide/rustup-home:ro,Z" "-e" "SOURCE_DIR=/opt/rustwide/workdir" "-e" "CARGO_TARGET_DIR=/opt/rustwide/target" "-e" "CARGO_INCREMENTAL=0" "-e" "RUST_BACKTRACE=full" "-e" "RUSTFLAGS=--cap-lints=warn" "-e" "RUSTDOCFLAGS=--cap-lints=warn" "-e" "CARGO_HOME=/opt/rustwide/cargo-home" "-e" "RUSTUP_HOME=/opt/rustwide/rustup-home" "-w" "/opt/rustwide/workdir" "-m" "1610612736" "--user" "0:0" "--network" "none" "ghcr.io/rust-lang/crates-build-env/linux@sha256:5ff2268d62e97bff2cde7d5815dd6ed5b47097566f13b8d0ca110b04b60e07ed" "/opt/rustwide/cargo-home/bin/cargo" "+1.69.0" "doc" "--frozen" "--no-deps" "--document-private-items" "--message-format=json", kill_on_drop: false }`
[INFO] [stdout] df950d75c5c3df0b7fe84b45e7e8513b89a4940914b25bc87b249954c41a03fd
[INFO] running `Command { std: "docker" "start" "-a" "df950d75c5c3df0b7fe84b45e7e8513b89a4940914b25bc87b249954c41a03fd", kill_on_drop: false }`
[INFO] [stderr]    Compiling proc-macro2 v1.0.56
[INFO] [stderr]    Compiling tokio v1.28.0
[INFO] [stderr]     Checking mio v0.8.6
[INFO] [stderr]    Compiling semver v1.0.17
[INFO] [stderr]     Checking dirs-sys-next v0.1.2
[INFO] [stderr]     Checking time v0.1.45
[INFO] [stderr]     Checking crypto-mac v0.11.1
[INFO] [stderr]     Checking shlex v1.1.0
[INFO] [stderr]     Checking hmac v0.11.0
[INFO] [stderr]     Checking dirs-next v2.0.0
[INFO] [stderr]     Checking sha2 v0.9.9
[INFO] [stderr]     Checking md-5 v0.9.1
[INFO] [stderr]     Checking xml-rs v0.8.4
[INFO] [stderr]    Compiling rustc_version v0.4.0
[INFO] [stderr]    Compiling rusoto_core v0.48.0
[INFO] [stderr]    Compiling quote v1.0.26
[INFO] [stderr]    Compiling syn v2.0.15
[INFO] [stderr]    Compiling futures-macro v0.3.28
[INFO] [stderr]    Compiling tokio-macros v2.1.0
[INFO] [stderr]    Compiling serde_derive v1.0.160
[INFO] [stderr]    Compiling openssl-macros v0.1.1
[INFO] [stderr]    Compiling async-trait v0.1.68
[INFO] [stderr]     Checking openssl v0.10.52
[INFO] [stderr]     Checking futures-util v0.3.28
[INFO] [stderr]     Checking native-tls v0.2.11
[INFO] [stderr]     Checking serde v1.0.160
[INFO] [stderr]     Checking futures-executor v0.3.28
[INFO] [stderr]     Checking futures v0.3.28
[INFO] [stderr]     Checking tokio-util v0.7.8
[INFO] [stderr]     Checking tokio-native-tls v0.3.1
[INFO] [stderr]     Checking h2 v0.3.18
[INFO] [stderr]     Checking chrono v0.4.24
[INFO] [stderr]     Checking serde_json v1.0.96
[INFO] [stderr]     Checking hyper v0.14.26
[INFO] [stderr]     Checking rusoto_credential v0.48.0
[INFO] [stderr]     Checking hyper-tls v0.5.0
[INFO] [stderr]     Checking rusoto_signature v0.48.0
[INFO] [stderr]  Documenting rusoto_sagemaker v0.48.0 (/opt/rustwide/workdir)
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:167:12
[INFO] [stdout]     |
[INFO] [stdout] 167 |     /// <p><p/></p>
[INFO] [stdout]     |            ^^
[INFO] [stdout]     |
[INFO] [stdout]     = note: `#[warn(rustdoc::invalid_html_tags)]` on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:737:12
[INFO] [stdout]     |
[INFO] [stdout] 737 |     /// <p><p/></p>
[INFO] [stdout]     |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:755:12
[INFO] [stdout]     |
[INFO] [stdout] 755 |     /// <p><p/></p>
[INFO] [stdout]     |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:759:12
[INFO] [stdout]     |
[INFO] [stdout] 759 |     /// <p><p/></p>
[INFO] [stdout]     |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:763:12
[INFO] [stdout]     |
[INFO] [stdout] 763 |     /// <p><p/></p>
[INFO] [stdout]     |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:821:12
[INFO] [stdout]     |
[INFO] [stdout] 821 |     /// <p><p/></p>
[INFO] [stdout]     |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:826:8
[INFO] [stdout]     |
[INFO] [stdout] 826 | /// <p><p/></p>
[INFO] [stdout]     |        ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:829:12
[INFO] [stdout]     |
[INFO] [stdout] 829 |     /// <p><p/></p>
[INFO] [stdout]     |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:833:12
[INFO] [stdout]     |
[INFO] [stdout] 833 |     /// <p><p/></p>
[INFO] [stdout]     |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:839:8
[INFO] [stdout]     |
[INFO] [stdout] 839 | /// <p><p/></p>
[INFO] [stdout]     |        ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:842:12
[INFO] [stdout]     |
[INFO] [stdout] 842 |     /// <p><p/></p>
[INFO] [stdout]     |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:887:12
[INFO] [stdout]     |
[INFO] [stdout] 887 |     /// <p><p/> <p>Specify RecordIO as the value when input data is in raw format but the training algorithm requires the RecordIO format...
[INFO] [stdout]     |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:1913:1755
[INFO] [stdout]      |
[INFO] [stdout] 1913 | ...>) labeling jobs for this task type. </p> </li> </ul> </li> </ul> <p/> <important> <p>If you are creating an adjustment or verificatio...
[INFO] [stdout]      |                                                                      ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:1916:891
[INFO] [stdout]      |
[INFO] [stdout] 1916 | ...mat. Identify the labels you want to use by replacing <code>label<em>1</code>, <code>label</em>2</code>,<code>...</code>,<code>label<e...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 1916 |     /// <p><p>The S3 URI of the file, referred to as a <i>label category configuration file</i>, that defines the categories used to label the data objects.</p> <p>For 3D point cloud and video frame task types, you can add label category attributes and frame attributes to your label category configuration file. To learn how, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/sms-point-cloud-label-category-config.html">Create a Labeling Category Configuration File for 3D Point Cloud Labeling Jobs</a>. </p> <p>For all other <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/sms-task-types.html">built-in task types</a> and <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/sms-custom-templates.html">custom tasks</a>, your label category configuration file must be a JSON file in the following format. Identify the labels you want to use by replacing <code>`label<em>`1</code>, <code>label</em>2</code>,<code>...</code>,<code>label<em>n</code> with your label categories.</p> <p> <code>{ </code> </p> <p> <code>&quot;document-version&quot;: &quot;2018-11-28&quot;,</code> </p> <p> <code>&quot;labels&quot;: [{&quot;label&quot;: &quot;label</em>1&quot;},{&quot;label&quot;: &quot;label<em>2&quot;},...{&quot;label&quot;: &quot;label</em>n&quot;}]</code> </p> <p> <code>}</code> </p> <p>Note the following about the label category configuration file:</p> <ul> <li> <p>For image classification and text classification (single and multi-label) you must specify at least two label categories. For all other task types, the minimum number of label categories required is one. </p> </li> <li> <p>Each label category must be unique, you cannot specify duplicate label categories.</p> </li> <li> <p>If you create a 3D point cloud or video frame adjustment or verification labeling job, you must include <code>auditLabelAttributeName</code> in the label category configuration. Use this parameter to enter the <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateLabelingJob.html#sagemaker-CreateLabelingJob-request-LabelAttributeName"> <code>LabelAttributeName</code> </a> of the labeling job you want to adjust or verify annotations of.</p> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      +         +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:1916:916
[INFO] [stdout]      |
[INFO] [stdout] 1916 | ...ou want to use by replacing <code>label<em>1</code>, <code>label</em>2</code>,<code>...</code>,<code>label<em>n</code> with your label...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:1916:958
[INFO] [stdout]      |
[INFO] [stdout] 1916 | ...m>1</code>, <code>label</em>2</code>,<code>...</code>,<code>label<em>n</code> with your label categories.</p> <p> <code>{ </code> </p>...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 1916 |     /// <p><p>The S3 URI of the file, referred to as a <i>label category configuration file</i>, that defines the categories used to label the data objects.</p> <p>For 3D point cloud and video frame task types, you can add label category attributes and frame attributes to your label category configuration file. To learn how, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/sms-point-cloud-label-category-config.html">Create a Labeling Category Configuration File for 3D Point Cloud Labeling Jobs</a>. </p> <p>For all other <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/sms-task-types.html">built-in task types</a> and <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/sms-custom-templates.html">custom tasks</a>, your label category configuration file must be a JSON file in the following format. Identify the labels you want to use by replacing <code>label<em>1</code>, <code>label</em>2</code>,<code>...</code>,<code>`label<em>`n</code> with your label categories.</p> <p> <code>{ </code> </p> <p> <code>&quot;document-version&quot;: &quot;2018-11-28&quot;,</code> </p> <p> <code>&quot;labels&quot;: [{&quot;label&quot;: &quot;label</em>1&quot;},{&quot;label&quot;: &quot;label<em>2&quot;},...{&quot;label&quot;: &quot;label</em>n&quot;}]</code> </p> <p> <code>}</code> </p> <p>Note the following about the label category configuration file:</p> <ul> <li> <p>For image classification and text classification (single and multi-label) you must specify at least two label categories. For all other task types, the minimum number of label categories required is one. </p> </li> <li> <p>Each label category must be unique, you cannot specify duplicate label categories.</p> </li> <li> <p>If you create a 3D point cloud or video frame adjustment or verification labeling job, you must include <code>auditLabelAttributeName</code> in the label category configuration. Use this parameter to enter the <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateLabelingJob.html#sagemaker-CreateLabelingJob-request-LabelAttributeName"> <code>LabelAttributeName</code> </a> of the labeling job you want to adjust or verify annotations of.</p> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         +         +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:1916:1166
[INFO] [stdout]      |
[INFO] [stdout] 1916 | ...> <p> <code>&quot;labels&quot;: [{&quot;label&quot;: &quot;label</em>1&quot;},{&quot;label&quot;: &quot;label<em>2&quot;},...{&quot;la...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `i`
[INFO] [stdout]     --> src/generated.rs:2588:118
[INFO] [stdout]      |
[INFO] [stdout] 2588 |     /// <p>Specifies the number of records to include in a mini-batch for an HTTP inference request. A <i>record</i> <i/> is a single uni...
[INFO] [stdout]      |                                                                                                                      ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2844:8
[INFO] [stdout]      |
[INFO] [stdout] 2844 | /// <p><p/></p>
[INFO] [stdout]      |        ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2847:12
[INFO] [stdout]      |
[INFO] [stdout] 2847 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2851:12
[INFO] [stdout]      |
[INFO] [stdout] 2851 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2854:12
[INFO] [stdout]      |
[INFO] [stdout] 2854 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2857:12
[INFO] [stdout]      |
[INFO] [stdout] 2857 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2861:12
[INFO] [stdout]      |
[INFO] [stdout] 2861 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2864:12
[INFO] [stdout]      |
[INFO] [stdout] 2864 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2870:8
[INFO] [stdout]      |
[INFO] [stdout] 2870 | /// <p><p/></p>
[INFO] [stdout]      |        ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2874:12
[INFO] [stdout]      |
[INFO] [stdout] 2874 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2877:12
[INFO] [stdout]      |
[INFO] [stdout] 2877 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2880:12
[INFO] [stdout]      |
[INFO] [stdout] 2880 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2883:12
[INFO] [stdout]      |
[INFO] [stdout] 2883 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2886:12
[INFO] [stdout]      |
[INFO] [stdout] 2886 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:3543:12
[INFO] [stdout]      |
[INFO] [stdout] 3543 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:3547:12
[INFO] [stdout]      |
[INFO] [stdout] 3547 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:5189:136
[INFO] [stdout]      |
[INFO] [stdout] 5189 | ...This is one of the following values.</p> <ul> <li> <p> <code>DATA<em>QUALITY</code> - The schedule is for a data quality monitoring jo...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 5189 |     /// <p><p>The type of the monitoring job that this schedule runs. This is one of the following values.</p> <ul> <li> <p> <code>`DATA<em>`QUALITY</code> - The schedule is for a data quality monitoring job.</p> </li> <li> <p> <code>MODEL</em>QUALITY</code> - The schedule is for a model quality monitoring job.</p> </li> <li> <p> <code>MODEL<em>BIAS</code> - The schedule is for a bias monitoring job.</p> </li> <li> <p> <code>MODEL</em>EXPLAINABILITY</code> - The schedule is for an explainability monitoring job.</p> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                    +        +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:5189:238
[INFO] [stdout]      |
[INFO] [stdout] 5189 | ...or a data quality monitoring job.</p> </li> <li> <p> <code>MODEL</em>QUALITY</code> - The schedule is for a model quality monitoring j...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:5189:342
[INFO] [stdout]      |
[INFO] [stdout] 5189 | ...or a model quality monitoring job.</p> </li> <li> <p> <code>MODEL<em>BIAS</code> - The schedule is for a bias monitoring job.</p> </li...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 5189 |     /// <p><p>The type of the monitoring job that this schedule runs. This is one of the following values.</p> <ul> <li> <p> <code>DATA<em>QUALITY</code> - The schedule is for a data quality monitoring job.</p> </li> <li> <p> <code>MODEL</em>QUALITY</code> - The schedule is for a model quality monitoring job.</p> </li> <li> <p> <code>`MODEL<em>`BIAS</code> - The schedule is for a bias monitoring job.</p> </li> <li> <p> <code>MODEL</em>EXPLAINABILITY</code> - The schedule is for an explainability monitoring job.</p> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                 +         +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:5189:433
[INFO] [stdout]      |
[INFO] [stdout] 5189 | ...ule is for a bias monitoring job.</p> </li> <li> <p> <code>MODEL</em>EXPLAINABILITY</code> - The schedule is for an explainability mon...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `i`
[INFO] [stdout]     --> src/generated.rs:5783:118
[INFO] [stdout]      |
[INFO] [stdout] 5783 |     /// <p>Specifies the number of records to include in a mini-batch for an HTTP inference request. A <i>record</i> <i/> is a single uni...
[INFO] [stdout]      |                                                                                                                      ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:6742:1469
[INFO] [stdout]      |
[INFO] [stdout] 6742 | ... filter is satisfied by training jobs with a <code>&quot;learning<em>rate&quot;</code> hyperparameter that is less than <code>&quot;0....
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 6742 | /// <p><p>A conditional statement for a search expression that includes a resource property, a Boolean operator, and a value. Resources that match the statement are returned in the results from the <a>Search</a> API.</p> <p>If you specify a <code>Value</code>, but not an <code>Operator</code>, Amazon SageMaker uses the equals operator.</p> <p>In search, there are several property types:</p> <dl> <dt>Metrics</dt> <dd> <p>To define a metric filter, enter a value using the form <code>&quot;Metrics.&lt;name&gt;&quot;</code>, where <code>&lt;name&gt;</code> is a metric name. For example, the following filter searches for training jobs with an <code>&quot;accuracy&quot;</code> metric greater than <code>&quot;0.9&quot;</code>:</p> <p> <code>{</code> </p> <p> <code>&quot;Name&quot;: &quot;Metrics.accuracy&quot;,</code> </p> <p> <code>&quot;Operator&quot;: &quot;GreaterThan&quot;,</code> </p> <p> <code>&quot;Value&quot;: &quot;0.9&quot;</code> </p> <p> <code>}</code> </p> </dd> <dt>HyperParameters</dt> <dd> <p>To define a hyperparameter filter, enter a value with the form <code>&quot;HyperParameters.&lt;name&gt;&quot;</code>. Decimal hyperparameter values are treated as a decimal in a comparison if the specified <code>Value</code> is also a decimal value. If the specified <code>Value</code> is an integer, the decimal hyperparameter values are treated as integers. For example, the following filter is satisfied by training jobs with a <code>&quot;`learning<em>`rate&quot;</code> hyperparameter that is less than <code>&quot;0.5&quot;</code>:</p> <p> <code> {</code> </p> <p> <code> &quot;Name&quot;: &quot;HyperParameters.learning</em>rate&quot;,</code> </p> <p> <code> &quot;Operator&quot;: &quot;LessThan&quot;,</code> </p> <p> <code> &quot;Value&quot;: &quot;0.5&quot;</code> </p> <p> <code> }</code> </p> </dd> <dt>Tags</dt> <dd> <p>To define a tag filter, enter a value with the form <code>Tags.&lt;key&gt;</code>.</p> </dd> </dl></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     +            +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:6742:1642
[INFO] [stdout]      |
[INFO] [stdout] 6742 | ...</p> <p> <code> &quot;Name&quot;: &quot;HyperParameters.learning</em>rate&quot;,</code> </p> <p> <code> &quot;Operator&quot;: &quot;Le...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:7078:640
[INFO] [stdout]      |
[INFO] [stdout] 7078 | ...Amazon S3, the model artifacts, and intermediate information.</p> <p/> <p>For more information about input modes, see <a href="https:/...
[INFO] [stdout]      |                                                                      ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7308:85
[INFO] [stdout]      |
[INFO] [stdout] 7308 |     /// <p><p>Specifies one of the following:</p> <dl> <dt>IDENTICAL<em>DATA</em>AND<em>ALGORITHM</dt> <dd> <p>The new hyperparameter tun...
[INFO] [stdout]      |                                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 7308 |     /// <p><p>Specifies one of the following:</p> <dl> <dt>IDENTICAL<em>DATA</em>`AND<em>`ALGORITHM</dt> <dd> <p>The new hyperparameter tuning job uses the same input data and training image as the parent tuning jobs. You can change the hyperparameter ranges to search and the maximum number of training jobs that the hyperparameter tuning job launches. You cannot use a new version of the training algorithm, unless the changes in the new version do not affect the algorithm itself. For example, changes that improve logging or adding support for a different data format are allowed. You can also change hyperparameters from tunable to static, and from static to tunable, but the total number of static plus tunable hyperparameters must remain the same as it is in all parent jobs. The objective metric for the new tuning job must be the same as for all parent jobs.</p> </dd> <dt>TRANSFER</em>LEARNING</dt> <dd> <p>The new hyperparameter tuning job can include input data, hyperparameter ranges, maximum number of concurrent training jobs, and maximum number of training jobs that are different than those of its parent hyperparameter tuning jobs. The training image can also be a different version from the version used in the parent hyperparameter tuning job. You can also change hyperparameters from tunable to static, and from static to tunable, but the total number of static plus tunable hyperparameters must remain the same as it is in all parent jobs. The objective metric for the new tuning job must be the same as for all parent jobs.</p> </dd> </dl></p>
[INFO] [stdout]      |                                                                                  +       +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7308:889
[INFO] [stdout]      |
[INFO] [stdout] 7308 | ... must be the same as for all parent jobs.</p> </dd> <dt>TRANSFER</em>LEARNING</dt> <dd> <p>The new hyperparameter tuning job can inclu...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:1453
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ... input:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 7419 |     /// <p><p>Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are <a>InputConfig$Framework</a> specific. </p> <ul> <li> <p> <code>TensorFlow</code>: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>KERAS</code>: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, <code>DataInputConfig</code> should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;`input<em>`1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input</em>1&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>MXNET/ONNX/DARKNET</code>: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>PyTorch</code>: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.</p> <ul> <li> <p>Examples for one input in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Example for one input in list format: <code>[[1,3,224,224]]</code> </p> </li> <li> <p>Examples for two inputs in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]} </code> </p> </li> </ul> </li> <li> <p>Example for two inputs in list format: <code>[[1,3,224,224], [1,3,224,224]]</code> </p> </li> </ul> </li> <li> <p> <code>XGBOOST</code>: input data name and shape are not needed.</p> </li> </ul> <p> <code>DataInputConfig</code> supports the following parameters for <code>CoreML</code> <a>OutputConfig$TargetDevice</a> (ML Model format):</p> <ul> <li> <p> <code>shape</code>: Input shape, for example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [1,224,224,3]}}</code>. In addition to static input shapes, CoreML converter supports Flexible input shapes:</p> <ul> <li> <p>Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: <code>{&quot;input</em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3]}}</code> </p> </li> <li> <p>Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [[1, 224, 224, 3], [1, 160, 160, 3]]}}</code> </p> </li> </ul> </li> <li> <p> <code>default</em>shape</code>: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3], &quot;default</em>shape&quot;: [1, 224, 224, 3]}}</code> </p> </li> <li> <p> <code>type</code>: Input type. Allowed values: <code>Image</code> and <code>Tensor</code>. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as <code>bias</code> and <code>scale</code>.</p> </li> <li> <p> <code>bias</code>: If the input type is an Image, you need to provide the bias vector.</p> </li> <li> <p> <code>scale</code>: If the input type is an Image, you need to provide a scale factor.</p> </li> </ul> <p>CoreML <code>ClassifierConfig</code> parameters can be specified using <a>OutputConfig$CompilerOptions</a>. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:</p> <ul> <li> <p>Tensor type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default</em>shape&quot;: [1,224,224,3]}}</code> </p> </li> </ul> </li> <li> <p>Tensor type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224]}]</code> </p> </li> </ul> </li> <li> <p>Image type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input</em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default<em>shape&quot;: [1,224,224,3], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> <li> <p>Image type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}]</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> </ul> <p>Depending on the model format, <code>DataInputConfig</code> requires the following parameters for <code>ml<em>eia2</code> &lt;a href=&quot;https://docs.aws.amazon.com/sagemaker/latest/APIReference/API</em>OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice&quot;&gt;OutputConfig:TargetDevice</a>.</p> <ul> <li> <p>For TensorFlow models saved in the SavedModel format, specify the input names from <code>signature<em>def</em>key</code> and the input model shapes for <code>DataInputConfig</code>. Specify the <code>signature<em>def</em>key</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a> if the model does not use TensorFlow&#39;s default signature def key. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;inputs&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;signature<em>def</em>key&quot;: &quot;serving<em>custom&quot;}</code> </p> </li> </ul> </li> <li> <p>For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in <code>DataInputConfig</code> and the output tensor names for <code>output</em>names</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a>. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>tensor:0&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;output</em>names&quot;: [&quot;output_tensor:0&quot;]}</code> </p> </li> </ul> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        +         +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:1542
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input</em>1&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Exam...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:4148
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...> <code>shape</code>: Input shape, for example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [1,224,224,3]}}</code>. In addition ...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 7419 |     /// <p><p>Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are <a>InputConfig$Framework</a> specific. </p> <ul> <li> <p> <code>TensorFlow</code>: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>KERAS</code>: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, <code>DataInputConfig</code> should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input</em>1&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>MXNET/ONNX/DARKNET</code>: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>PyTorch</code>: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.</p> <ul> <li> <p>Examples for one input in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Example for one input in list format: <code>[[1,3,224,224]]</code> </p> </li> <li> <p>Examples for two inputs in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]} </code> </p> </li> </ul> </li> <li> <p>Example for two inputs in list format: <code>[[1,3,224,224], [1,3,224,224]]</code> </p> </li> </ul> </li> <li> <p> <code>XGBOOST</code>: input data name and shape are not needed.</p> </li> </ul> <p> <code>DataInputConfig</code> supports the following parameters for <code>CoreML</code> <a>OutputConfig$TargetDevice</a> (ML Model format):</p> <ul> <li> <p> <code>shape</code>: Input shape, for example <code>{&quot;`input<em>`1&quot;: {&quot;shape&quot;: [1,224,224,3]}}</code>. In addition to static input shapes, CoreML converter supports Flexible input shapes:</p> <ul> <li> <p>Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: <code>{&quot;input</em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3]}}</code> </p> </li> <li> <p>Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [[1, 224, 224, 3], [1, 160, 160, 3]]}}</code> </p> </li> </ul> </li> <li> <p> <code>default</em>shape</code>: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3], &quot;default</em>shape&quot;: [1, 224, 224, 3]}}</code> </p> </li> <li> <p> <code>type</code>: Input type. Allowed values: <code>Image</code> and <code>Tensor</code>. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as <code>bias</code> and <code>scale</code>.</p> </li> <li> <p> <code>bias</code>: If the input type is an Image, you need to provide the bias vector.</p> </li> <li> <p> <code>scale</code>: If the input type is an Image, you need to provide a scale factor.</p> </li> </ul> <p>CoreML <code>ClassifierConfig</code> parameters can be specified using <a>OutputConfig$CompilerOptions</a>. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:</p> <ul> <li> <p>Tensor type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default</em>shape&quot;: [1,224,224,3]}}</code> </p> </li> </ul> </li> <li> <p>Tensor type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224]}]</code> </p> </li> </ul> </li> <li> <p>Image type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input</em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default<em>shape&quot;: [1,224,224,3], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> <li> <p>Image type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}]</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> </ul> <p>Depending on the model format, <code>DataInputConfig</code> requires the following parameters for <code>ml<em>eia2</code> &lt;a href=&quot;https://docs.aws.amazon.com/sagemaker/latest/APIReference/API</em>OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice&quot;&gt;OutputConfig:TargetDevice</a>.</p> <ul> <li> <p>For TensorFlow models saved in the SavedModel format, specify the input names from <code>signature<em>def</em>key</code> and the input model shapes for <code>DataInputConfig</code>. Specify the <code>signature<em>def</em>key</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a> if the model does not use TensorFlow&#39;s default signature def key. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;inputs&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;signature<em>def</em>key&quot;: &quot;serving<em>custom&quot;}</code> </p> </li> </ul> </li> <li> <p>For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in <code>DataInputConfig</code> and the output tensor names for <code>output</em>names</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a>. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>tensor:0&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;output</em>names&quot;: [&quot;output_tensor:0&quot;]}</code> </p> </li> </ul> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               +         +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:4480
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...ific interval in that dimension, for example: <code>{&quot;input</em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3]}}</...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:4745
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...erate all supported input shapes, for example: <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [[1, 224, 224, 3], [1, 160, 160, 3]]...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 7419 |     /// <p><p>Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are <a>InputConfig$Framework</a> specific. </p> <ul> <li> <p> <code>TensorFlow</code>: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>KERAS</code>: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, <code>DataInputConfig</code> should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input</em>1&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>MXNET/ONNX/DARKNET</code>: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>PyTorch</code>: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.</p> <ul> <li> <p>Examples for one input in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Example for one input in list format: <code>[[1,3,224,224]]</code> </p> </li> <li> <p>Examples for two inputs in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]} </code> </p> </li> </ul> </li> <li> <p>Example for two inputs in list format: <code>[[1,3,224,224], [1,3,224,224]]</code> </p> </li> </ul> </li> <li> <p> <code>XGBOOST</code>: input data name and shape are not needed.</p> </li> </ul> <p> <code>DataInputConfig</code> supports the following parameters for <code>CoreML</code> <a>OutputConfig$TargetDevice</a> (ML Model format):</p> <ul> <li> <p> <code>shape</code>: Input shape, for example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [1,224,224,3]}}</code>. In addition to static input shapes, CoreML converter supports Flexible input shapes:</p> <ul> <li> <p>Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: <code>{&quot;input</em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3]}}</code> </p> </li> <li> <p>Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: <code>{&quot;`input<em>`1&quot;: {&quot;shape&quot;: [[1, 224, 224, 3], [1, 160, 160, 3]]}}</code> </p> </li> </ul> </li> <li> <p> <code>default</em>shape</code>: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3], &quot;default</em>shape&quot;: [1, 224, 224, 3]}}</code> </p> </li> <li> <p> <code>type</code>: Input type. Allowed values: <code>Image</code> and <code>Tensor</code>. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as <code>bias</code> and <code>scale</code>.</p> </li> <li> <p> <code>bias</code>: If the input type is an Image, you need to provide the bias vector.</p> </li> <li> <p> <code>scale</code>: If the input type is an Image, you need to provide a scale factor.</p> </li> </ul> <p>CoreML <code>ClassifierConfig</code> parameters can be specified using <a>OutputConfig$CompilerOptions</a>. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:</p> <ul> <li> <p>Tensor type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default</em>shape&quot;: [1,224,224,3]}}</code> </p> </li> </ul> </li> <li> <p>Tensor type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224]}]</code> </p> </li> </ul> </li> <li> <p>Image type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input</em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default<em>shape&quot;: [1,224,224,3], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> <li> <p>Image type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}]</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> </ul> <p>Depending on the model format, <code>DataInputConfig</code> requires the following parameters for <code>ml<em>eia2</code> &lt;a href=&quot;https://docs.aws.amazon.com/sagemaker/latest/APIReference/API</em>OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice&quot;&gt;OutputConfig:TargetDevice</a>.</p> <ul> <li> <p>For TensorFlow models saved in the SavedModel format, specify the input names from <code>signature<em>def</em>key</code> and the input model shapes for <code>DataInputConfig</code>. Specify the <code>signature<em>def</em>key</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a> if the model does not use TensorFlow&#39;s default signature def key. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;inputs&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;signature<em>def</em>key&quot;: &quot;serving<em>custom&quot;}</code> </p> </li> </ul> </li> <li> <p>For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in <code>DataInputConfig</code> and the output tensor names for <code>output</em>names</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a>. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>tensor:0&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;output</em>names&quot;: [&quot;output_tensor:0&quot;]}</code> </p> </li> </ul> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    +         +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:4869
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ... 160, 3]]}}</code> </p> </li> </ul> </li> <li> <p> <code>default</em>shape</code>: Default input shape. You can set a default shape du...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:6340
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224]}]</code> </p> </li> </ul> </li> <li> <...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 7419 |     /// <p><p>Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are <a>InputConfig$Framework</a> specific. </p> <ul> <li> <p> <code>TensorFlow</code>: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>KERAS</code>: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, <code>DataInputConfig</code> should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input</em>1&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>MXNET/ONNX/DARKNET</code>: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>PyTorch</code>: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.</p> <ul> <li> <p>Examples for one input in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Example for one input in list format: <code>[[1,3,224,224]]</code> </p> </li> <li> <p>Examples for two inputs in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]} </code> </p> </li> </ul> </li> <li> <p>Example for two inputs in list format: <code>[[1,3,224,224], [1,3,224,224]]</code> </p> </li> </ul> </li> <li> <p> <code>XGBOOST</code>: input data name and shape are not needed.</p> </li> </ul> <p> <code>DataInputConfig</code> supports the following parameters for <code>CoreML</code> <a>OutputConfig$TargetDevice</a> (ML Model format):</p> <ul> <li> <p> <code>shape</code>: Input shape, for example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [1,224,224,3]}}</code>. In addition to static input shapes, CoreML converter supports Flexible input shapes:</p> <ul> <li> <p>Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: <code>{&quot;input</em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3]}}</code> </p> </li> <li> <p>Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [[1, 224, 224, 3], [1, 160, 160, 3]]}}</code> </p> </li> </ul> </li> <li> <p> <code>default</em>shape</code>: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3], &quot;default</em>shape&quot;: [1, 224, 224, 3]}}</code> </p> </li> <li> <p> <code>type</code>: Input type. Allowed values: <code>Image</code> and <code>Tensor</code>. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as <code>bias</code> and <code>scale</code>.</p> </li> <li> <p> <code>bias</code>: If the input type is an Image, you need to provide the bias vector.</p> </li> <li> <p> <code>scale</code>: If the input type is an Image, you need to provide a scale factor.</p> </li> </ul> <p>CoreML <code>ClassifierConfig</code> parameters can be specified using <a>OutputConfig$CompilerOptions</a>. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:</p> <ul> <li> <p>Tensor type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default</em>shape&quot;: [1,224,224,3]}}</code> </p> </li> </ul> </li> <li> <p>Tensor type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;`default<em>`shape&quot;: [1,3,224,224]}]</code> </p> </li> </ul> </li> <li> <p>Image type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input</em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default<em>shape&quot;: [1,224,224,3], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> <li> <p>Image type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}]</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> </ul> <p>Depending on the model format, <code>DataInputConfig</code> requires the following parameters for <code>ml<em>eia2</code> &lt;a href=&quot;https://docs.aws.amazon.com/sagemaker/latest/APIReference/API</em>OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice&quot;&gt;OutputConfig:TargetDevice</a>.</p> <ul> <li> <p>For TensorFlow models saved in the SavedModel format, specify the input names from <code>signature<em>def</em>key</code> and the input model shapes for <code>DataInputConfig</code>. Specify the <code>signature<em>def</em>key</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a> if the model does not use TensorFlow&#39;s default signature def key. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;inputs&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;signature<em>def</em>key&quot;: &quot;serving<em>custom&quot;}</code> </p> </li> </ul> </li> <li> <p>For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in <code>DataInputConfig</code> and the output tensor names for <code>output</em>names</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a>. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>tensor:0&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;output</em>names&quot;: [&quot;output_tensor:0&quot;]}</code> </p> </li> </ul> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             +           +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:6494
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input</em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quo...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:6573
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...{&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default<em>shape&quot;: [1,224,224,3], &quot;type&quot;: &quot;Image&quot;, ...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 7419 |     /// <p><p>Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are <a>InputConfig$Framework</a> specific. </p> <ul> <li> <p> <code>TensorFlow</code>: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>KERAS</code>: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, <code>DataInputConfig</code> should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input</em>1&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>MXNET/ONNX/DARKNET</code>: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>PyTorch</code>: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.</p> <ul> <li> <p>Examples for one input in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Example for one input in list format: <code>[[1,3,224,224]]</code> </p> </li> <li> <p>Examples for two inputs in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]} </code> </p> </li> </ul> </li> <li> <p>Example for two inputs in list format: <code>[[1,3,224,224], [1,3,224,224]]</code> </p> </li> </ul> </li> <li> <p> <code>XGBOOST</code>: input data name and shape are not needed.</p> </li> </ul> <p> <code>DataInputConfig</code> supports the following parameters for <code>CoreML</code> <a>OutputConfig$TargetDevice</a> (ML Model format):</p> <ul> <li> <p> <code>shape</code>: Input shape, for example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [1,224,224,3]}}</code>. In addition to static input shapes, CoreML converter supports Flexible input shapes:</p> <ul> <li> <p>Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: <code>{&quot;input</em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3]}}</code> </p> </li> <li> <p>Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [[1, 224, 224, 3], [1, 160, 160, 3]]}}</code> </p> </li> </ul> </li> <li> <p> <code>default</em>shape</code>: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3], &quot;default</em>shape&quot;: [1, 224, 224, 3]}}</code> </p> </li> <li> <p> <code>type</code>: Input type. Allowed values: <code>Image</code> and <code>Tensor</code>. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as <code>bias</code> and <code>scale</code>.</p> </li> <li> <p> <code>bias</code>: If the input type is an Image, you need to provide the bias vector.</p> </li> <li> <p> <code>scale</code>: If the input type is an Image, you need to provide a scale factor.</p> </li> </ul> <p>CoreML <code>ClassifierConfig</code> parameters can be specified using <a>OutputConfig$CompilerOptions</a>. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:</p> <ul> <li> <p>Tensor type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default</em>shape&quot;: [1,224,224,3]}}</code> </p> </li> </ul> </li> <li> <p>Tensor type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224]}]</code> </p> </li> </ul> </li> <li> <p>Image type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input</em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;`default<em>`shape&quot;: [1,224,224,3], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> <li> <p>Image type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}]</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> </ul> <p>Depending on the model format, <code>DataInputConfig</code> requires the following parameters for <code>ml<em>eia2</code> &lt;a href=&quot;https://docs.aws.amazon.com/sagemaker/latest/APIReference/API</em>OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice&quot;&gt;OutputConfig:TargetDevice</a>.</p> <ul> <li> <p>For TensorFlow models saved in the SavedModel format, specify the input names from <code>signature<em>def</em>key</code> and the input model shapes for <code>DataInputConfig</code>. Specify the <code>signature<em>def</em>key</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a> if the model does not use TensorFlow&#39;s default signature def key. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;inputs&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;signature<em>def</em>key&quot;: &quot;serving<em>custom&quot;}</code> </p> </li> </ul> </li> <li> <p>For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in <code>DataInputConfig</code> and the output tensor names for <code>output</em>names</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a>. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>tensor:0&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;output</em>names&quot;: [&quot;output_tensor:0&quot;]}</code> </p> </li> </ul> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      +           +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:6782
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code>...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:7050
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224], &quot;type&quot;: &quot;Image&quot;, ...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 7419 |     /// <p><p>Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are <a>InputConfig$Framework</a> specific. </p> <ul> <li> <p> <code>TensorFlow</code>: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>KERAS</code>: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, <code>DataInputConfig</code> should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input</em>1&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>MXNET/ONNX/DARKNET</code>: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>PyTorch</code>: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.</p> <ul> <li> <p>Examples for one input in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Example for one input in list format: <code>[[1,3,224,224]]</code> </p> </li> <li> <p>Examples for two inputs in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]} </code> </p> </li> </ul> </li> <li> <p>Example for two inputs in list format: <code>[[1,3,224,224], [1,3,224,224]]</code> </p> </li> </ul> </li> <li> <p> <code>XGBOOST</code>: input data name and shape are not needed.</p> </li> </ul> <p> <code>DataInputConfig</code> supports the following parameters for <code>CoreML</code> <a>OutputConfig$TargetDevice</a> (ML Model format):</p> <ul> <li> <p> <code>shape</code>: Input shape, for example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [1,224,224,3]}}</code>. In addition to static input shapes, CoreML converter supports Flexible input shapes:</p> <ul> <li> <p>Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: <code>{&quot;input</em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3]}}</code> </p> </li> <li> <p>Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [[1, 224, 224, 3], [1, 160, 160, 3]]}}</code> </p> </li> </ul> </li> <li> <p> <code>default</em>shape</code>: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3], &quot;default</em>shape&quot;: [1, 224, 224, 3]}}</code> </p> </li> <li> <p> <code>type</code>: Input type. Allowed values: <code>Image</code> and <code>Tensor</code>. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as <code>bias</code> and <code>scale</code>.</p> </li> <li> <p> <code>bias</code>: If the input type is an Image, you need to provide the bias vector.</p> </li> <li> <p> <code>scale</code>: If the input type is an Image, you need to provide a scale factor.</p> </li> </ul> <p>CoreML <code>ClassifierConfig</code> parameters can be specified using <a>OutputConfig$CompilerOptions</a>. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:</p> <ul> <li> <p>Tensor type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default</em>shape&quot;: [1,224,224,3]}}</code> </p> </li> </ul> </li> <li> <p>Tensor type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224]}]</code> </p> </li> </ul> </li> <li> <p>Image type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input</em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default<em>shape&quot;: [1,224,224,3], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> <li> <p>Image type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;`default<em>`shape&quot;: [1,3,224,224], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}]</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> </ul> <p>Depending on the model format, <code>DataInputConfig</code> requires the following parameters for <code>ml<em>eia2</code> &lt;a href=&quot;https://docs.aws.amazon.com/sagemaker/latest/APIReference/API</em>OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice&quot;&gt;OutputConfig:TargetDevice</a>.</p> <ul> <li> <p>For TensorFlow models saved in the SavedModel format, specify the input names from <code>signature<em>def</em>key</code> and the input model shapes for <code>DataInputConfig</code>. Specify the <code>signature<em>def</em>key</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a> if the model does not use TensorFlow&#39;s default signature def key. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;inputs&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;signature<em>def</em>key&quot;: &quot;serving<em>custom&quot;}</code> </p> </li> </ul> </li> <li> <p>For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in <code>DataInputConfig</code> and the output tensor names for <code>output</em>names</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a>. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>tensor:0&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;output</em>names&quot;: [&quot;output_tensor:0&quot;]}</code> </p> </li> </ul> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   +           +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:7259
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code>...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:7468
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...InputConfig</code> requires the following parameters for <code>ml<em>eia2</code> &lt;a href=&quot;https://docs.aws.amazon.com/sagemake...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 7419 |     /// <p><p>Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are <a>InputConfig$Framework</a> specific. </p> <ul> <li> <p> <code>TensorFlow</code>: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>KERAS</code>: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, <code>DataInputConfig</code> should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input</em>1&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>MXNET/ONNX/DARKNET</code>: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>PyTorch</code>: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.</p> <ul> <li> <p>Examples for one input in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Example for one input in list format: <code>[[1,3,224,224]]</code> </p> </li> <li> <p>Examples for two inputs in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]} </code> </p> </li> </ul> </li> <li> <p>Example for two inputs in list format: <code>[[1,3,224,224], [1,3,224,224]]</code> </p> </li> </ul> </li> <li> <p> <code>XGBOOST</code>: input data name and shape are not needed.</p> </li> </ul> <p> <code>DataInputConfig</code> supports the following parameters for <code>CoreML</code> <a>OutputConfig$TargetDevice</a> (ML Model format):</p> <ul> <li> <p> <code>shape</code>: Input shape, for example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [1,224,224,3]}}</code>. In addition to static input shapes, CoreML converter supports Flexible input shapes:</p> <ul> <li> <p>Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: <code>{&quot;input</em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3]}}</code> </p> </li> <li> <p>Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [[1, 224, 224, 3], [1, 160, 160, 3]]}}</code> </p> </li> </ul> </li> <li> <p> <code>default</em>shape</code>: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3], &quot;default</em>shape&quot;: [1, 224, 224, 3]}}</code> </p> </li> <li> <p> <code>type</code>: Input type. Allowed values: <code>Image</code> and <code>Tensor</code>. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as <code>bias</code> and <code>scale</code>.</p> </li> <li> <p> <code>bias</code>: If the input type is an Image, you need to provide the bias vector.</p> </li> <li> <p> <code>scale</code>: If the input type is an Image, you need to provide a scale factor.</p> </li> </ul> <p>CoreML <code>ClassifierConfig</code> parameters can be specified using <a>OutputConfig$CompilerOptions</a>. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:</p> <ul> <li> <p>Tensor type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default</em>shape&quot;: [1,224,224,3]}}</code> </p> </li> </ul> </li> <li> <p>Tensor type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224]}]</code> </p> </li> </ul> </li> <li> <p>Image type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input</em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default<em>shape&quot;: [1,224,224,3], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> <li> <p>Image type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}]</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> </ul> <p>Depending on the model format, <code>DataInputConfig</code> requires the following parameters for <code>`ml<em>`eia2</code> &lt;a href=&quot;https://docs.aws.amazon.com/sagemaker/latest/APIReference/API</em>OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice&quot;&gt;OutputConfig:TargetDevice</a>.</p> <ul> <li> <p>For TensorFlow models saved in the SavedModel format, specify the input names from <code>signature<em>def</em>key</code> and the input model shapes for <code>DataInputConfig</code>. Specify the <code>signature<em>def</em>key</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a> if the model does not use TensorFlow&#39;s default signature def key. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;inputs&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;signature<em>def</em>key&quot;: &quot;serving<em>custom&quot;}</code> </p> </li> </ul> </li> <li> <p>For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in <code>DataInputConfig</code> and the output tensor names for <code>output</em>names</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a>. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>tensor:0&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;output</em>names&quot;: [&quot;output_tensor:0&quot;]}</code> </p> </li> </ul> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          +      +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:7562
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...ot;https://docs.aws.amazon.com/sagemaker/latest/APIReference/API</em>OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice&quot;&...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `a`
[INFO] [stdout]     --> src/generated.rs:7419:7660
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...Type-OutputConfig-TargetDevice&quot;&gt;OutputConfig:TargetDevice</a>.</p> <ul> <li> <p>For TensorFlow models saved in the SavedModel ...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:8389
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...tions&quot;: {&quot;signature<em>def</em>key&quot;: &quot;serving<em>custom&quot;}</code> </p> </li> </ul> </li> <li> <p>For TensorFlo...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 7419 |     /// <p><p>Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are <a>InputConfig$Framework</a> specific. </p> <ul> <li> <p> <code>TensorFlow</code>: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>KERAS</code>: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, <code>DataInputConfig</code> should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input</em>1&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>MXNET/ONNX/DARKNET</code>: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>PyTorch</code>: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.</p> <ul> <li> <p>Examples for one input in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Example for one input in list format: <code>[[1,3,224,224]]</code> </p> </li> <li> <p>Examples for two inputs in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]} </code> </p> </li> </ul> </li> <li> <p>Example for two inputs in list format: <code>[[1,3,224,224], [1,3,224,224]]</code> </p> </li> </ul> </li> <li> <p> <code>XGBOOST</code>: input data name and shape are not needed.</p> </li> </ul> <p> <code>DataInputConfig</code> supports the following parameters for <code>CoreML</code> <a>OutputConfig$TargetDevice</a> (ML Model format):</p> <ul> <li> <p> <code>shape</code>: Input shape, for example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [1,224,224,3]}}</code>. In addition to static input shapes, CoreML converter supports Flexible input shapes:</p> <ul> <li> <p>Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: <code>{&quot;input</em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3]}}</code> </p> </li> <li> <p>Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [[1, 224, 224, 3], [1, 160, 160, 3]]}}</code> </p> </li> </ul> </li> <li> <p> <code>default</em>shape</code>: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3], &quot;default</em>shape&quot;: [1, 224, 224, 3]}}</code> </p> </li> <li> <p> <code>type</code>: Input type. Allowed values: <code>Image</code> and <code>Tensor</code>. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as <code>bias</code> and <code>scale</code>.</p> </li> <li> <p> <code>bias</code>: If the input type is an Image, you need to provide the bias vector.</p> </li> <li> <p> <code>scale</code>: If the input type is an Image, you need to provide a scale factor.</p> </li> </ul> <p>CoreML <code>ClassifierConfig</code> parameters can be specified using <a>OutputConfig$CompilerOptions</a>. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:</p> <ul> <li> <p>Tensor type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default</em>shape&quot;: [1,224,224,3]}}</code> </p> </li> </ul> </li> <li> <p>Tensor type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224]}]</code> </p> </li> </ul> </li> <li> <p>Image type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input</em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default<em>shape&quot;: [1,224,224,3], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> <li> <p>Image type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}]</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> </ul> <p>Depending on the model format, <code>DataInputConfig</code> requires the following parameters for <code>ml<em>eia2</code> &lt;a href=&quot;https://docs.aws.amazon.com/sagemaker/latest/APIReference/API</em>OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice&quot;&gt;OutputConfig:TargetDevice</a>.</p> <ul> <li> <p>For TensorFlow models saved in the SavedModel format, specify the input names from <code>signature<em>def</em>key</code> and the input model shapes for <code>DataInputConfig</code>. Specify the <code>signature<em>def</em>key</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a> if the model does not use TensorFlow&#39;s default signature def key. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;inputs&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;signature<em>def</em>key&quot;: &quot;`serving<em>`custom&quot;}</code> </p> </li> </ul> </li> <li> <p>For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in <code>DataInputConfig</code> and the output tensor names for <code>output</em>names</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a>. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>tensor:0&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;output</em>names&quot;: [&quot;output_tensor:0&quot;]}</code> </p> </li> </ul> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              +           +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:8610
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...aInputConfig</code> and the output tensor names for <code>output</em>names</code> in <a href="https://docs.aws.amazon.com/sagemaker/la...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:8892
[INFO] [stdout]      |
[INFO] [stdout] 7419 | .../p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>tensor:0&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <cod...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 7419 |     /// <p><p>Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are <a>InputConfig$Framework</a> specific. </p> <ul> <li> <p> <code>TensorFlow</code>: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>KERAS</code>: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, <code>DataInputConfig</code> should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input</em>1&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>MXNET/ONNX/DARKNET</code>: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>PyTorch</code>: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.</p> <ul> <li> <p>Examples for one input in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Example for one input in list format: <code>[[1,3,224,224]]</code> </p> </li> <li> <p>Examples for two inputs in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]} </code> </p> </li> </ul> </li> <li> <p>Example for two inputs in list format: <code>[[1,3,224,224], [1,3,224,224]]</code> </p> </li> </ul> </li> <li> <p> <code>XGBOOST</code>: input data name and shape are not needed.</p> </li> </ul> <p> <code>DataInputConfig</code> supports the following parameters for <code>CoreML</code> <a>OutputConfig$TargetDevice</a> (ML Model format):</p> <ul> <li> <p> <code>shape</code>: Input shape, for example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [1,224,224,3]}}</code>. In addition to static input shapes, CoreML converter supports Flexible input shapes:</p> <ul> <li> <p>Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: <code>{&quot;input</em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3]}}</code> </p> </li> <li> <p>Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [[1, 224, 224, 3], [1, 160, 160, 3]]}}</code> </p> </li> </ul> </li> <li> <p> <code>default</em>shape</code>: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3], &quot;default</em>shape&quot;: [1, 224, 224, 3]}}</code> </p> </li> <li> <p> <code>type</code>: Input type. Allowed values: <code>Image</code> and <code>Tensor</code>. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as <code>bias</code> and <code>scale</code>.</p> </li> <li> <p> <code>bias</code>: If the input type is an Image, you need to provide the bias vector.</p> </li> <li> <p> <code>scale</code>: If the input type is an Image, you need to provide a scale factor.</p> </li> </ul> <p>CoreML <code>ClassifierConfig</code> parameters can be specified using <a>OutputConfig$CompilerOptions</a>. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:</p> <ul> <li> <p>Tensor type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default</em>shape&quot;: [1,224,224,3]}}</code> </p> </li> </ul> </li> <li> <p>Tensor type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224]}]</code> </p> </li> </ul> </li> <li> <p>Image type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input</em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default<em>shape&quot;: [1,224,224,3], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> <li> <p>Image type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}]</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> </ul> <p>Depending on the model format, <code>DataInputConfig</code> requires the following parameters for <code>ml<em>eia2</code> &lt;a href=&quot;https://docs.aws.amazon.com/sagemaker/latest/APIReference/API</em>OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice&quot;&gt;OutputConfig:TargetDevice</a>.</p> <ul> <li> <p>For TensorFlow models saved in the SavedModel format, specify the input names from <code>signature<em>def</em>key</code> and the input model shapes for <code>DataInputConfig</code>. Specify the <code>signature<em>def</em>key</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a> if the model does not use TensorFlow&#39;s default signature def key. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;inputs&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;signature<em>def</em>key&quot;: &quot;serving<em>custom&quot;}</code> </p> </li> </ul> </li> <li> <p>For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in <code>DataInputConfig</code> and the output tensor names for <code>output</em>names</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a>. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;`input<em>`tensor:0&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;output</em>names&quot;: [&quot;output_tensor:0&quot;]}</code> </p> </li> </ul> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       +         +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:9005
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ... </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;output</em>names&quot;: [&quot;output_tensor:0&quot;]}</code> </p> </li> </u...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]      --> src/generated.rs:10388:8
[INFO] [stdout]       |
[INFO] [stdout] 10388 | /// <p><p/></p>
[INFO] [stdout]       |        ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]      --> src/generated.rs:10391:12
[INFO] [stdout]       |
[INFO] [stdout] 10391 |     /// <p><p/></p>
[INFO] [stdout]       |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]      --> src/generated.rs:10395:12
[INFO] [stdout]       |
[INFO] [stdout] 10395 |     /// <p><p/></p>
[INFO] [stdout]       |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]      --> src/generated.rs:10398:12
[INFO] [stdout]       |
[INFO] [stdout] 10398 |     /// <p><p/></p>
[INFO] [stdout]       |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:10689:197
[INFO] [stdout]       |
[INFO] [stdout] 10689 | ...model group is pending being created.</p> </li> <li> <p> <code>IN<em>PROGRESS</code> - The model group is in the process of being crea...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 10689 |     /// <p><p>The status of the model group. This can be one of the following values.</p> <ul> <li> <p> <code>PENDING</code> - The model group is pending being created.</p> </li> <li> <p> <code>`IN<em>`PROGRESS</code> - The model group is in the process of being created.</p> </li> <li> <p> <code>COMPLETED</code> - The model group was successfully created.</p> </li> <li> <p> <code>FAILED</code> - The model group failed.</p> </li> <li> <p> <code>DELETING</code> - The model group is in the process of being deleted.</p> </li> <li> <p> <code>DELETE</em>FAILED</code> - SageMaker failed to delete the model group.</p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                   +      +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:10689:548
[INFO] [stdout]       |
[INFO] [stdout] 10689 | ...in the process of being deleted.</p> </li> <li> <p> <code>DELETE</em>FAILED</code> - SageMaker failed to delete the model group.</p> <...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:413
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...pecifies the data type for the input. When compiling for <code>ml<em>*</code> (except for <code>ml</em>inf</code>) instances using PyT...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 11527 |     /// <p><p>Specifies additional parameters for compiler options in JSON format. The compiler options are <code>TargetPlatform</code> specific. It is required for NVIDIA accelerators and highly recommended for CPU compilations. For any other cases, it is optional to specify <code>CompilerOptions.</code> </p> <ul> <li> <p> <code>DTYPE</code>: Specifies the data type for the input. When compiling for <code>`ml<em>`*</code> (except for <code>ml</em>inf</code>) instances using PyTorch framework, provide the data type (dtype) of the model&#39;s input. <code>&quot;float32&quot;</code> is used if <code>&quot;DTYPE&quot;</code> is not specified. Options for data type are:</p> <ul> <li> <p>float32: Use either <code>&quot;float&quot;</code> or <code>&quot;float32&quot;</code>.</p> </li> <li> <p>int64: Use either <code>&quot;int64&quot;</code> or <code>&quot;long&quot;</code>.</p> </li> </ul> <p> For example, <code>{&quot;dtype&quot; : &quot;float32&quot;}</code>.</p> </li> <li> <p> <code>CPU</code>: Compilation for CPU supports the following compiler options.</p> <ul> <li> <p> <code>mcpu</code>: CPU micro-architecture. For example, <code>{&#39;mcpu&#39;: &#39;skylake-avx512&#39;}</code> </p> </li> <li> <p> <code>mattr</code>: CPU flags. For example, <code>{&#39;mattr&#39;: [&#39;+neon&#39;, &#39;+vfpv4&#39;]}</code> </p> </li> </ul> </li> <li> <p> <code>ARM</code>: Details of ARM CPU compilations.</p> <ul> <li> <p> <code>NEON</code>: NEON is an implementation of the Advanced SIMD extension used in ARMv7 processors.</p> <p>For example, add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to the compiler options if compiling for ARM 32-bit platform with the NEON support.</p> </li> </ul> </li> <li> <p> <code>NVIDIA</code>: Compilation for NVIDIA GPU supports the following compiler options.</p> <ul> <li> <p> <code>gpu<em>code</code>: Specifies the targeted architecture.</p> </li> <li> <p> <code>trt-ver</code>: Specifies the TensorRT versions in x.y.z. format.</p> </li> <li> <p> <code>cuda-ver</code>: Specifies the CUDA version in x.y format.</p> </li> </ul> <p>For example, <code>{&#39;gpu-code&#39;: &#39;sm</em>72&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: &#39;10.1&#39;}</code> </p> </li> <li> <p> <code>ANDROID</code>: Compilation for the Android OS supports the following compiler options:</p> <ul> <li> <p> <code>ANDROID<em>PLATFORM</code>: Specifies the Android API levels. Available levels range from 21 to 29. For example, <code>{&#39;ANDROID</em>PLATFORM&#39;: 28}</code>.</p> </li> <li> <p> <code>mattr</code>: Add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to compiler options if compiling for ARM 32-bit platform with NEON support.</p> </li> </ul> </li> <li> <p> <code>INFERENTIA</code>: Compilation for target ml<em>inf1 uses compiler options passed in as a JSON string. For example, <code>&quot;CompilerOptions&quot;: &quot;&quot;--verbose 1 --num-neuroncores 2 -O2&quot;&quot;</code>. </p> <p>For information about supported compiler options, see <a href="https://github.com/aws/aws-neuron-sdk/blob/master/docs/neuron-cc/command-line-reference.md"> Neuron Compiler CLI</a>. </p> </li> <li> <p> <code>CoreML</code>: Compilation for the CoreML <a>OutputConfig$TargetDevice</a> supports the following compiler options:</p> <ul> <li> <p> <code>class</em>labels</code>: Specifies the classification labels file name inside input tar.gz file. For example, <code>{&quot;class<em>labels&quot;: &quot;imagenet</em>labels<em>1000.txt&quot;}</code>. Labels inside the txt file should be separated by newlines.</p> </li> </ul> </li> <li> <p> <code>EIA</code>: Compilation for the Elastic Inference Accelerator supports the following compiler options:</p> <ul> <li> <p> <code>precision</em>mode</code>: Specifies the precision of compiled artifacts. Supported values are <code>&quot;FP16&quot;</code> and <code>&quot;FP32&quot;</code>. Default is <code>&quot;FP32&quot;</code>.</p> </li> <li> <p> <code>signature<em>def</em>key</code>: Specifies the signature to use for models in SavedModel format. Defaults is TensorFlow&#39;s default signature def key.</p> </li> <li> <p> <code>output<em>names</code>: Specifies a list of output tensor names for models in FrozenGraph format. Set at most one API field, either: <code>signature</em>def<em>key</code> or <code>output</em>names</code>.</p> </li> </ul> <p>For example: <code>{&quot;precision<em>mode&quot;: &quot;FP32&quot;, &quot;output</em>names&quot;: [&quot;output:0&quot;]}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                           +      +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:446
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...ut. When compiling for <code>ml<em>*</code> (except for <code>ml</em>inf</code>) instances using PyTorch framework, provide the data t...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:1837
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...ports the following compiler options.</p> <ul> <li> <p> <code>gpu<em>code</code>: Specifies the targeted architecture.</p> </li> <li> ...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 11527 |     /// <p><p>Specifies additional parameters for compiler options in JSON format. The compiler options are <code>TargetPlatform</code> specific. It is required for NVIDIA accelerators and highly recommended for CPU compilations. For any other cases, it is optional to specify <code>CompilerOptions.</code> </p> <ul> <li> <p> <code>DTYPE</code>: Specifies the data type for the input. When compiling for <code>ml<em>*</code> (except for <code>ml</em>inf</code>) instances using PyTorch framework, provide the data type (dtype) of the model&#39;s input. <code>&quot;float32&quot;</code> is used if <code>&quot;DTYPE&quot;</code> is not specified. Options for data type are:</p> <ul> <li> <p>float32: Use either <code>&quot;float&quot;</code> or <code>&quot;float32&quot;</code>.</p> </li> <li> <p>int64: Use either <code>&quot;int64&quot;</code> or <code>&quot;long&quot;</code>.</p> </li> </ul> <p> For example, <code>{&quot;dtype&quot; : &quot;float32&quot;}</code>.</p> </li> <li> <p> <code>CPU</code>: Compilation for CPU supports the following compiler options.</p> <ul> <li> <p> <code>mcpu</code>: CPU micro-architecture. For example, <code>{&#39;mcpu&#39;: &#39;skylake-avx512&#39;}</code> </p> </li> <li> <p> <code>mattr</code>: CPU flags. For example, <code>{&#39;mattr&#39;: [&#39;+neon&#39;, &#39;+vfpv4&#39;]}</code> </p> </li> </ul> </li> <li> <p> <code>ARM</code>: Details of ARM CPU compilations.</p> <ul> <li> <p> <code>NEON</code>: NEON is an implementation of the Advanced SIMD extension used in ARMv7 processors.</p> <p>For example, add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to the compiler options if compiling for ARM 32-bit platform with the NEON support.</p> </li> </ul> </li> <li> <p> <code>NVIDIA</code>: Compilation for NVIDIA GPU supports the following compiler options.</p> <ul> <li> <p> <code>`gpu<em>`code</code>: Specifies the targeted architecture.</p> </li> <li> <p> <code>trt-ver</code>: Specifies the TensorRT versions in x.y.z. format.</p> </li> <li> <p> <code>cuda-ver</code>: Specifies the CUDA version in x.y format.</p> </li> </ul> <p>For example, <code>{&#39;gpu-code&#39;: &#39;sm</em>72&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: &#39;10.1&#39;}</code> </p> </li> <li> <p> <code>ANDROID</code>: Compilation for the Android OS supports the following compiler options:</p> <ul> <li> <p> <code>ANDROID<em>PLATFORM</code>: Specifies the Android API levels. Available levels range from 21 to 29. For example, <code>{&#39;ANDROID</em>PLATFORM&#39;: 28}</code>.</p> </li> <li> <p> <code>mattr</code>: Add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to compiler options if compiling for ARM 32-bit platform with NEON support.</p> </li> </ul> </li> <li> <p> <code>INFERENTIA</code>: Compilation for target ml<em>inf1 uses compiler options passed in as a JSON string. For example, <code>&quot;CompilerOptions&quot;: &quot;&quot;--verbose 1 --num-neuroncores 2 -O2&quot;&quot;</code>. </p> <p>For information about supported compiler options, see <a href="https://github.com/aws/aws-neuron-sdk/blob/master/docs/neuron-cc/command-line-reference.md"> Neuron Compiler CLI</a>. </p> </li> <li> <p> <code>CoreML</code>: Compilation for the CoreML <a>OutputConfig$TargetDevice</a> supports the following compiler options:</p> <ul> <li> <p> <code>class</em>labels</code>: Specifies the classification labels file name inside input tar.gz file. For example, <code>{&quot;class<em>labels&quot;: &quot;imagenet</em>labels<em>1000.txt&quot;}</code>. Labels inside the txt file should be separated by newlines.</p> </li> </ul> </li> <li> <p> <code>EIA</code>: Compilation for the Elastic Inference Accelerator supports the following compiler options:</p> <ul> <li> <p> <code>precision</em>mode</code>: Specifies the precision of compiled artifacts. Supported values are <code>&quot;FP16&quot;</code> and <code>&quot;FP32&quot;</code>. Default is <code>&quot;FP32&quot;</code>.</p> </li> <li> <p> <code>signature<em>def</em>key</code>: Specifies the signature to use for models in SavedModel format. Defaults is TensorFlow&#39;s default signature def key.</p> </li> <li> <p> <code>output<em>names</code>: Specifies a list of output tensor names for models in FrozenGraph format. Set at most one API field, either: <code>signature</em>def<em>key</code> or <code>output</em>names</code>.</p> </li> </ul> <p>For example: <code>{&quot;precision<em>mode&quot;: &quot;FP32&quot;, &quot;output</em>names&quot;: [&quot;output:0&quot;]}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          +       +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:2132
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...> </li> </ul> <p>For example, <code>{&#39;gpu-code&#39;: &#39;sm</em>72&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: ...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:2370
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...s the following compiler options:</p> <ul> <li> <p> <code>ANDROID<em>PLATFORM</code>: Specifies the Android API levels. Available leve...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 11527 |     /// <p><p>Specifies additional parameters for compiler options in JSON format. The compiler options are <code>TargetPlatform</code> specific. It is required for NVIDIA accelerators and highly recommended for CPU compilations. For any other cases, it is optional to specify <code>CompilerOptions.</code> </p> <ul> <li> <p> <code>DTYPE</code>: Specifies the data type for the input. When compiling for <code>ml<em>*</code> (except for <code>ml</em>inf</code>) instances using PyTorch framework, provide the data type (dtype) of the model&#39;s input. <code>&quot;float32&quot;</code> is used if <code>&quot;DTYPE&quot;</code> is not specified. Options for data type are:</p> <ul> <li> <p>float32: Use either <code>&quot;float&quot;</code> or <code>&quot;float32&quot;</code>.</p> </li> <li> <p>int64: Use either <code>&quot;int64&quot;</code> or <code>&quot;long&quot;</code>.</p> </li> </ul> <p> For example, <code>{&quot;dtype&quot; : &quot;float32&quot;}</code>.</p> </li> <li> <p> <code>CPU</code>: Compilation for CPU supports the following compiler options.</p> <ul> <li> <p> <code>mcpu</code>: CPU micro-architecture. For example, <code>{&#39;mcpu&#39;: &#39;skylake-avx512&#39;}</code> </p> </li> <li> <p> <code>mattr</code>: CPU flags. For example, <code>{&#39;mattr&#39;: [&#39;+neon&#39;, &#39;+vfpv4&#39;]}</code> </p> </li> </ul> </li> <li> <p> <code>ARM</code>: Details of ARM CPU compilations.</p> <ul> <li> <p> <code>NEON</code>: NEON is an implementation of the Advanced SIMD extension used in ARMv7 processors.</p> <p>For example, add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to the compiler options if compiling for ARM 32-bit platform with the NEON support.</p> </li> </ul> </li> <li> <p> <code>NVIDIA</code>: Compilation for NVIDIA GPU supports the following compiler options.</p> <ul> <li> <p> <code>gpu<em>code</code>: Specifies the targeted architecture.</p> </li> <li> <p> <code>trt-ver</code>: Specifies the TensorRT versions in x.y.z. format.</p> </li> <li> <p> <code>cuda-ver</code>: Specifies the CUDA version in x.y format.</p> </li> </ul> <p>For example, <code>{&#39;gpu-code&#39;: &#39;sm</em>72&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: &#39;10.1&#39;}</code> </p> </li> <li> <p> <code>ANDROID</code>: Compilation for the Android OS supports the following compiler options:</p> <ul> <li> <p> <code>`ANDROID<em>`PLATFORM</code>: Specifies the Android API levels. Available levels range from 21 to 29. For example, <code>{&#39;ANDROID</em>PLATFORM&#39;: 28}</code>.</p> </li> <li> <p> <code>mattr</code>: Add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to compiler options if compiling for ARM 32-bit platform with NEON support.</p> </li> </ul> </li> <li> <p> <code>INFERENTIA</code>: Compilation for target ml<em>inf1 uses compiler options passed in as a JSON string. For example, <code>&quot;CompilerOptions&quot;: &quot;&quot;--verbose 1 --num-neuroncores 2 -O2&quot;&quot;</code>. </p> <p>For information about supported compiler options, see <a href="https://github.com/aws/aws-neuron-sdk/blob/master/docs/neuron-cc/command-line-reference.md"> Neuron Compiler CLI</a>. </p> </li> <li> <p> <code>CoreML</code>: Compilation for the CoreML <a>OutputConfig$TargetDevice</a> supports the following compiler options:</p> <ul> <li> <p> <code>class</em>labels</code>: Specifies the classification labels file name inside input tar.gz file. For example, <code>{&quot;class<em>labels&quot;: &quot;imagenet</em>labels<em>1000.txt&quot;}</code>. Labels inside the txt file should be separated by newlines.</p> </li> </ul> </li> <li> <p> <code>EIA</code>: Compilation for the Elastic Inference Accelerator supports the following compiler options:</p> <ul> <li> <p> <code>precision</em>mode</code>: Specifies the precision of compiled artifacts. Supported values are <code>&quot;FP16&quot;</code> and <code>&quot;FP32&quot;</code>. Default is <code>&quot;FP32&quot;</code>.</p> </li> <li> <p> <code>signature<em>def</em>key</code>: Specifies the signature to use for models in SavedModel format. Defaults is TensorFlow&#39;s default signature def key.</p> </li> <li> <p> <code>output<em>names</code>: Specifies a list of output tensor names for models in FrozenGraph format. Set at most one API field, either: <code>signature</em>def<em>key</code> or <code>output</em>names</code>.</p> </li> </ul> <p>For example: <code>{&quot;precision<em>mode&quot;: &quot;FP32&quot;, &quot;output</em>names&quot;: [&quot;output:0&quot;]}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           +           +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:2495
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...ble levels range from 21 to 29. For example, <code>{&#39;ANDROID</em>PLATFORM&#39;: 28}</code>.</p> </li> <li> <p> <code>mattr</code>:...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:2777
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...</li> <li> <p> <code>INFERENTIA</code>: Compilation for target ml<em>inf1 uses compiler options passed in as a JSON string. For exampl...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 11527 |     /// <p><p>Specifies additional parameters for compiler options in JSON format. The compiler options are <code>TargetPlatform</code> specific. It is required for NVIDIA accelerators and highly recommended for CPU compilations. For any other cases, it is optional to specify <code>CompilerOptions.</code> </p> <ul> <li> <p> <code>DTYPE</code>: Specifies the data type for the input. When compiling for <code>ml<em>*</code> (except for <code>ml</em>inf</code>) instances using PyTorch framework, provide the data type (dtype) of the model&#39;s input. <code>&quot;float32&quot;</code> is used if <code>&quot;DTYPE&quot;</code> is not specified. Options for data type are:</p> <ul> <li> <p>float32: Use either <code>&quot;float&quot;</code> or <code>&quot;float32&quot;</code>.</p> </li> <li> <p>int64: Use either <code>&quot;int64&quot;</code> or <code>&quot;long&quot;</code>.</p> </li> </ul> <p> For example, <code>{&quot;dtype&quot; : &quot;float32&quot;}</code>.</p> </li> <li> <p> <code>CPU</code>: Compilation for CPU supports the following compiler options.</p> <ul> <li> <p> <code>mcpu</code>: CPU micro-architecture. For example, <code>{&#39;mcpu&#39;: &#39;skylake-avx512&#39;}</code> </p> </li> <li> <p> <code>mattr</code>: CPU flags. For example, <code>{&#39;mattr&#39;: [&#39;+neon&#39;, &#39;+vfpv4&#39;]}</code> </p> </li> </ul> </li> <li> <p> <code>ARM</code>: Details of ARM CPU compilations.</p> <ul> <li> <p> <code>NEON</code>: NEON is an implementation of the Advanced SIMD extension used in ARMv7 processors.</p> <p>For example, add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to the compiler options if compiling for ARM 32-bit platform with the NEON support.</p> </li> </ul> </li> <li> <p> <code>NVIDIA</code>: Compilation for NVIDIA GPU supports the following compiler options.</p> <ul> <li> <p> <code>gpu<em>code</code>: Specifies the targeted architecture.</p> </li> <li> <p> <code>trt-ver</code>: Specifies the TensorRT versions in x.y.z. format.</p> </li> <li> <p> <code>cuda-ver</code>: Specifies the CUDA version in x.y format.</p> </li> </ul> <p>For example, <code>{&#39;gpu-code&#39;: &#39;sm</em>72&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: &#39;10.1&#39;}</code> </p> </li> <li> <p> <code>ANDROID</code>: Compilation for the Android OS supports the following compiler options:</p> <ul> <li> <p> <code>ANDROID<em>PLATFORM</code>: Specifies the Android API levels. Available levels range from 21 to 29. For example, <code>{&#39;ANDROID</em>PLATFORM&#39;: 28}</code>.</p> </li> <li> <p> <code>mattr</code>: Add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to compiler options if compiling for ARM 32-bit platform with NEON support.</p> </li> </ul> </li> <li> <p> <code>INFERENTIA</code>: Compilation for target `ml<em>`inf1 uses compiler options passed in as a JSON string. For example, <code>&quot;CompilerOptions&quot;: &quot;&quot;--verbose 1 --num-neuroncores 2 -O2&quot;&quot;</code>. </p> <p>For information about supported compiler options, see <a href="https://github.com/aws/aws-neuron-sdk/blob/master/docs/neuron-cc/command-line-reference.md"> Neuron Compiler CLI</a>. </p> </li> <li> <p> <code>CoreML</code>: Compilation for the CoreML <a>OutputConfig$TargetDevice</a> supports the following compiler options:</p> <ul> <li> <p> <code>class</em>labels</code>: Specifies the classification labels file name inside input tar.gz file. For example, <code>{&quot;class<em>labels&quot;: &quot;imagenet</em>labels<em>1000.txt&quot;}</code>. Labels inside the txt file should be separated by newlines.</p> </li> </ul> </li> <li> <p> <code>EIA</code>: Compilation for the Elastic Inference Accelerator supports the following compiler options:</p> <ul> <li> <p> <code>precision</em>mode</code>: Specifies the precision of compiled artifacts. Supported values are <code>&quot;FP16&quot;</code> and <code>&quot;FP32&quot;</code>. Default is <code>&quot;FP32&quot;</code>.</p> </li> <li> <p> <code>signature<em>def</em>key</code>: Specifies the signature to use for models in SavedModel format. Defaults is TensorFlow&#39;s default signature def key.</p> </li> <li> <p> <code>output<em>names</code>: Specifies a list of output tensor names for models in FrozenGraph format. Set at most one API field, either: <code>signature</em>def<em>key</code> or <code>output</em>names</code>.</p> </li> </ul> <p>For example: <code>{&quot;precision<em>mode&quot;: &quot;FP32&quot;, &quot;output</em>names&quot;: [&quot;output:0&quot;]}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       +      +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:3312
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...ts the following compiler options:</p> <ul> <li> <p> <code>class</em>labels</code>: Specifies the classification labels file name insi...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:3478
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...le, <code>{&quot;class<em>labels&quot;: &quot;imagenet</em>labels<em>1000.txt&quot;}</code>. Labels inside the txt file should be sepa...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 11527 |     /// <p><p>Specifies additional parameters for compiler options in JSON format. The compiler options are <code>TargetPlatform</code> specific. It is required for NVIDIA accelerators and highly recommended for CPU compilations. For any other cases, it is optional to specify <code>CompilerOptions.</code> </p> <ul> <li> <p> <code>DTYPE</code>: Specifies the data type for the input. When compiling for <code>ml<em>*</code> (except for <code>ml</em>inf</code>) instances using PyTorch framework, provide the data type (dtype) of the model&#39;s input. <code>&quot;float32&quot;</code> is used if <code>&quot;DTYPE&quot;</code> is not specified. Options for data type are:</p> <ul> <li> <p>float32: Use either <code>&quot;float&quot;</code> or <code>&quot;float32&quot;</code>.</p> </li> <li> <p>int64: Use either <code>&quot;int64&quot;</code> or <code>&quot;long&quot;</code>.</p> </li> </ul> <p> For example, <code>{&quot;dtype&quot; : &quot;float32&quot;}</code>.</p> </li> <li> <p> <code>CPU</code>: Compilation for CPU supports the following compiler options.</p> <ul> <li> <p> <code>mcpu</code>: CPU micro-architecture. For example, <code>{&#39;mcpu&#39;: &#39;skylake-avx512&#39;}</code> </p> </li> <li> <p> <code>mattr</code>: CPU flags. For example, <code>{&#39;mattr&#39;: [&#39;+neon&#39;, &#39;+vfpv4&#39;]}</code> </p> </li> </ul> </li> <li> <p> <code>ARM</code>: Details of ARM CPU compilations.</p> <ul> <li> <p> <code>NEON</code>: NEON is an implementation of the Advanced SIMD extension used in ARMv7 processors.</p> <p>For example, add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to the compiler options if compiling for ARM 32-bit platform with the NEON support.</p> </li> </ul> </li> <li> <p> <code>NVIDIA</code>: Compilation for NVIDIA GPU supports the following compiler options.</p> <ul> <li> <p> <code>gpu<em>code</code>: Specifies the targeted architecture.</p> </li> <li> <p> <code>trt-ver</code>: Specifies the TensorRT versions in x.y.z. format.</p> </li> <li> <p> <code>cuda-ver</code>: Specifies the CUDA version in x.y format.</p> </li> </ul> <p>For example, <code>{&#39;gpu-code&#39;: &#39;sm</em>72&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: &#39;10.1&#39;}</code> </p> </li> <li> <p> <code>ANDROID</code>: Compilation for the Android OS supports the following compiler options:</p> <ul> <li> <p> <code>ANDROID<em>PLATFORM</code>: Specifies the Android API levels. Available levels range from 21 to 29. For example, <code>{&#39;ANDROID</em>PLATFORM&#39;: 28}</code>.</p> </li> <li> <p> <code>mattr</code>: Add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to compiler options if compiling for ARM 32-bit platform with NEON support.</p> </li> </ul> </li> <li> <p> <code>INFERENTIA</code>: Compilation for target ml<em>inf1 uses compiler options passed in as a JSON string. For example, <code>&quot;CompilerOptions&quot;: &quot;&quot;--verbose 1 --num-neuroncores 2 -O2&quot;&quot;</code>. </p> <p>For information about supported compiler options, see <a href="https://github.com/aws/aws-neuron-sdk/blob/master/docs/neuron-cc/command-line-reference.md"> Neuron Compiler CLI</a>. </p> </li> <li> <p> <code>CoreML</code>: Compilation for the CoreML <a>OutputConfig$TargetDevice</a> supports the following compiler options:</p> <ul> <li> <p> <code>class</em>labels</code>: Specifies the classification labels file name inside input tar.gz file. For example, <code>{&quot;class<em>labels&quot;: &quot;imagenet</em>`labels<em>`1000.txt&quot;}</code>. Labels inside the txt file should be separated by newlines.</p> </li> </ul> </li> <li> <p> <code>EIA</code>: Compilation for the Elastic Inference Accelerator supports the following compiler options:</p> <ul> <li> <p> <code>precision</em>mode</code>: Specifies the precision of compiled artifacts. Supported values are <code>&quot;FP16&quot;</code> and <code>&quot;FP32&quot;</code>. Default is <code>&quot;FP32&quot;</code>.</p> </li> <li> <p> <code>signature<em>def</em>key</code>: Specifies the signature to use for models in SavedModel format. Defaults is TensorFlow&#39;s default signature def key.</p> </li> <li> <p> <code>output<em>names</code>: Specifies a list of output tensor names for models in FrozenGraph format. Set at most one API field, either: <code>signature</em>def<em>key</code> or <code>output</em>names</code>.</p> </li> </ul> <p>For example: <code>{&quot;precision<em>mode&quot;: &quot;FP32&quot;, &quot;output</em>names&quot;: [&quot;output:0&quot;]}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                +          +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:3739
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...he following compiler options:</p> <ul> <li> <p> <code>precision</em>mode</code>: Specifies the precision of compiled artifacts. Suppo...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:4141
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...&#39;s default signature def key.</p> </li> <li> <p> <code>output<em>names</code>: Specifies a list of output tensor names for models ...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 11527 |     /// <p><p>Specifies additional parameters for compiler options in JSON format. The compiler options are <code>TargetPlatform</code> specific. It is required for NVIDIA accelerators and highly recommended for CPU compilations. For any other cases, it is optional to specify <code>CompilerOptions.</code> </p> <ul> <li> <p> <code>DTYPE</code>: Specifies the data type for the input. When compiling for <code>ml<em>*</code> (except for <code>ml</em>inf</code>) instances using PyTorch framework, provide the data type (dtype) of the model&#39;s input. <code>&quot;float32&quot;</code> is used if <code>&quot;DTYPE&quot;</code> is not specified. Options for data type are:</p> <ul> <li> <p>float32: Use either <code>&quot;float&quot;</code> or <code>&quot;float32&quot;</code>.</p> </li> <li> <p>int64: Use either <code>&quot;int64&quot;</code> or <code>&quot;long&quot;</code>.</p> </li> </ul> <p> For example, <code>{&quot;dtype&quot; : &quot;float32&quot;}</code>.</p> </li> <li> <p> <code>CPU</code>: Compilation for CPU supports the following compiler options.</p> <ul> <li> <p> <code>mcpu</code>: CPU micro-architecture. For example, <code>{&#39;mcpu&#39;: &#39;skylake-avx512&#39;}</code> </p> </li> <li> <p> <code>mattr</code>: CPU flags. For example, <code>{&#39;mattr&#39;: [&#39;+neon&#39;, &#39;+vfpv4&#39;]}</code> </p> </li> </ul> </li> <li> <p> <code>ARM</code>: Details of ARM CPU compilations.</p> <ul> <li> <p> <code>NEON</code>: NEON is an implementation of the Advanced SIMD extension used in ARMv7 processors.</p> <p>For example, add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to the compiler options if compiling for ARM 32-bit platform with the NEON support.</p> </li> </ul> </li> <li> <p> <code>NVIDIA</code>: Compilation for NVIDIA GPU supports the following compiler options.</p> <ul> <li> <p> <code>gpu<em>code</code>: Specifies the targeted architecture.</p> </li> <li> <p> <code>trt-ver</code>: Specifies the TensorRT versions in x.y.z. format.</p> </li> <li> <p> <code>cuda-ver</code>: Specifies the CUDA version in x.y format.</p> </li> </ul> <p>For example, <code>{&#39;gpu-code&#39;: &#39;sm</em>72&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: &#39;10.1&#39;}</code> </p> </li> <li> <p> <code>ANDROID</code>: Compilation for the Android OS supports the following compiler options:</p> <ul> <li> <p> <code>ANDROID<em>PLATFORM</code>: Specifies the Android API levels. Available levels range from 21 to 29. For example, <code>{&#39;ANDROID</em>PLATFORM&#39;: 28}</code>.</p> </li> <li> <p> <code>mattr</code>: Add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to compiler options if compiling for ARM 32-bit platform with NEON support.</p> </li> </ul> </li> <li> <p> <code>INFERENTIA</code>: Compilation for target ml<em>inf1 uses compiler options passed in as a JSON string. For example, <code>&quot;CompilerOptions&quot;: &quot;&quot;--verbose 1 --num-neuroncores 2 -O2&quot;&quot;</code>. </p> <p>For information about supported compiler options, see <a href="https://github.com/aws/aws-neuron-sdk/blob/master/docs/neuron-cc/command-line-reference.md"> Neuron Compiler CLI</a>. </p> </li> <li> <p> <code>CoreML</code>: Compilation for the CoreML <a>OutputConfig$TargetDevice</a> supports the following compiler options:</p> <ul> <li> <p> <code>class</em>labels</code>: Specifies the classification labels file name inside input tar.gz file. For example, <code>{&quot;class<em>labels&quot;: &quot;imagenet</em>labels<em>1000.txt&quot;}</code>. Labels inside the txt file should be separated by newlines.</p> </li> </ul> </li> <li> <p> <code>EIA</code>: Compilation for the Elastic Inference Accelerator supports the following compiler options:</p> <ul> <li> <p> <code>precision</em>mode</code>: Specifies the precision of compiled artifacts. Supported values are <code>&quot;FP16&quot;</code> and <code>&quot;FP32&quot;</code>. Default is <code>&quot;FP32&quot;</code>.</p> </li> <li> <p> <code>signature<em>def</em>key</code>: Specifies the signature to use for models in SavedModel format. Defaults is TensorFlow&#39;s default signature def key.</p> </li> <li> <p> <code>`output<em>`names</code>: Specifies a list of output tensor names for models in FrozenGraph format. Set at most one API field, either: <code>signature</em>def<em>key</code> or <code>output</em>names</code>.</p> </li> </ul> <p>For example: <code>{&quot;precision<em>mode&quot;: &quot;FP32&quot;, &quot;output</em>names&quot;: [&quot;output:0&quot;]}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       +          +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:4283
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...Graph format. Set at most one API field, either: <code>signature</em>def<em>key</code> or <code>output</em>names</code>.</p> </li> </u...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:4291
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...ormat. Set at most one API field, either: <code>signature</em>def<em>key</code> or <code>output</em>names</code>.</p> </li> </ul> <p>F...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 11527 |     /// <p><p>Specifies additional parameters for compiler options in JSON format. The compiler options are <code>TargetPlatform</code> specific. It is required for NVIDIA accelerators and highly recommended for CPU compilations. For any other cases, it is optional to specify <code>CompilerOptions.</code> </p> <ul> <li> <p> <code>DTYPE</code>: Specifies the data type for the input. When compiling for <code>ml<em>*</code> (except for <code>ml</em>inf</code>) instances using PyTorch framework, provide the data type (dtype) of the model&#39;s input. <code>&quot;float32&quot;</code> is used if <code>&quot;DTYPE&quot;</code> is not specified. Options for data type are:</p> <ul> <li> <p>float32: Use either <code>&quot;float&quot;</code> or <code>&quot;float32&quot;</code>.</p> </li> <li> <p>int64: Use either <code>&quot;int64&quot;</code> or <code>&quot;long&quot;</code>.</p> </li> </ul> <p> For example, <code>{&quot;dtype&quot; : &quot;float32&quot;}</code>.</p> </li> <li> <p> <code>CPU</code>: Compilation for CPU supports the following compiler options.</p> <ul> <li> <p> <code>mcpu</code>: CPU micro-architecture. For example, <code>{&#39;mcpu&#39;: &#39;skylake-avx512&#39;}</code> </p> </li> <li> <p> <code>mattr</code>: CPU flags. For example, <code>{&#39;mattr&#39;: [&#39;+neon&#39;, &#39;+vfpv4&#39;]}</code> </p> </li> </ul> </li> <li> <p> <code>ARM</code>: Details of ARM CPU compilations.</p> <ul> <li> <p> <code>NEON</code>: NEON is an implementation of the Advanced SIMD extension used in ARMv7 processors.</p> <p>For example, add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to the compiler options if compiling for ARM 32-bit platform with the NEON support.</p> </li> </ul> </li> <li> <p> <code>NVIDIA</code>: Compilation for NVIDIA GPU supports the following compiler options.</p> <ul> <li> <p> <code>gpu<em>code</code>: Specifies the targeted architecture.</p> </li> <li> <p> <code>trt-ver</code>: Specifies the TensorRT versions in x.y.z. format.</p> </li> <li> <p> <code>cuda-ver</code>: Specifies the CUDA version in x.y format.</p> </li> </ul> <p>For example, <code>{&#39;gpu-code&#39;: &#39;sm</em>72&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: &#39;10.1&#39;}</code> </p> </li> <li> <p> <code>ANDROID</code>: Compilation for the Android OS supports the following compiler options:</p> <ul> <li> <p> <code>ANDROID<em>PLATFORM</code>: Specifies the Android API levels. Available levels range from 21 to 29. For example, <code>{&#39;ANDROID</em>PLATFORM&#39;: 28}</code>.</p> </li> <li> <p> <code>mattr</code>: Add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to compiler options if compiling for ARM 32-bit platform with NEON support.</p> </li> </ul> </li> <li> <p> <code>INFERENTIA</code>: Compilation for target ml<em>inf1 uses compiler options passed in as a JSON string. For example, <code>&quot;CompilerOptions&quot;: &quot;&quot;--verbose 1 --num-neuroncores 2 -O2&quot;&quot;</code>. </p> <p>For information about supported compiler options, see <a href="https://github.com/aws/aws-neuron-sdk/blob/master/docs/neuron-cc/command-line-reference.md"> Neuron Compiler CLI</a>. </p> </li> <li> <p> <code>CoreML</code>: Compilation for the CoreML <a>OutputConfig$TargetDevice</a> supports the following compiler options:</p> <ul> <li> <p> <code>class</em>labels</code>: Specifies the classification labels file name inside input tar.gz file. For example, <code>{&quot;class<em>labels&quot;: &quot;imagenet</em>labels<em>1000.txt&quot;}</code>. Labels inside the txt file should be separated by newlines.</p> </li> </ul> </li> <li> <p> <code>EIA</code>: Compilation for the Elastic Inference Accelerator supports the following compiler options:</p> <ul> <li> <p> <code>precision</em>mode</code>: Specifies the precision of compiled artifacts. Supported values are <code>&quot;FP16&quot;</code> and <code>&quot;FP32&quot;</code>. Default is <code>&quot;FP32&quot;</code>.</p> </li> <li> <p> <code>signature<em>def</em>key</code>: Specifies the signature to use for models in SavedModel format. Defaults is TensorFlow&#39;s default signature def key.</p> </li> <li> <p> <code>output<em>names</code>: Specifies a list of output tensor names for models in FrozenGraph format. Set at most one API field, either: <code>signature</em>`def<em>`key</code> or <code>output</em>names</code>.</p> </li> </ul> <p>For example: <code>{&quot;precision<em>mode&quot;: &quot;FP32&quot;, &quot;output</em>names&quot;: [&quot;output:0&quot;]}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                +       +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:4321
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...d, either: <code>signature</em>def<em>key</code> or <code>output</em>names</code>.</p> </li> </ul> <p>For example: <code>{&quot;precis...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11542:498
[INFO] [stdout]       |
[INFO] [stdout] 11542 | ...: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;ARM<em>EABIHF&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 11542 |     /// <p><p>Contains information about a target platform that you want your model to run on, such as OS, architecture, and accelerators. It is an alternative of <code>TargetDevice</code>.</p> <p>The following examples show how to configure the <code>TargetPlatform</code> and <code>CompilerOptions</code> JSON strings for popular target platforms: </p> <ul> <li> <p>Raspberry Pi 3 Model B+</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;`ARM<em>`EABIHF&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;mattr&#39;: [&#39;+neon&#39;]}</code> </p> </li> <li> <p>Jetson TX2</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;ARM64&quot;, &quot;Accelerator&quot;: &quot;NVIDIA&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;gpu-code&#39;: &#39;sm</em>62&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: &#39;10.0&#39;}</code> </p> </li> <li> <p>EC2 m5.2xlarge instance OS</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;X86<em>64&quot;, &quot;Accelerator&quot;: &quot;NVIDIA&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;mcpu&#39;: &#39;skylake-avx512&#39;}</code> </p> </li> <li> <p>RK3399</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;ARM64&quot;, &quot;Accelerator&quot;: &quot;MALI&quot;}</code> </p> </li> <li> <p>ARMv7 phone (CPU)</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;ANDROID&quot;, &quot;Arch&quot;: &quot;ARM</em>EABI&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;ANDROID<em>PLATFORM&#39;: 25, &#39;mattr&#39;: [&#39;+neon&#39;]}</code> </p> </li> <li> <p>ARMv8 phone (CPU)</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;ANDROID&quot;, &quot;Arch&quot;: &quot;ARM64&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;ANDROID</em>PLATFORM&#39;: 29}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               +       +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11542:884
[INFO] [stdout]       |
[INFO] [stdout] 11542 | ...<code> &quot;CompilerOptions&quot;: {&#39;gpu-code&#39;: &#39;sm</em>62&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: ...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11542:1128
[INFO] [stdout]       |
[INFO] [stdout] 11542 | ...: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;X86<em>64&quot;, &quot;Accelerator&quot;: &quot;NVIDIA&quot;},</code> </...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 11542 |     /// <p><p>Contains information about a target platform that you want your model to run on, such as OS, architecture, and accelerators. It is an alternative of <code>TargetDevice</code>.</p> <p>The following examples show how to configure the <code>TargetPlatform</code> and <code>CompilerOptions</code> JSON strings for popular target platforms: </p> <ul> <li> <p>Raspberry Pi 3 Model B+</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;ARM<em>EABIHF&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;mattr&#39;: [&#39;+neon&#39;]}</code> </p> </li> <li> <p>Jetson TX2</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;ARM64&quot;, &quot;Accelerator&quot;: &quot;NVIDIA&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;gpu-code&#39;: &#39;sm</em>62&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: &#39;10.0&#39;}</code> </p> </li> <li> <p>EC2 m5.2xlarge instance OS</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;`X86<em>`64&quot;, &quot;Accelerator&quot;: &quot;NVIDIA&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;mcpu&#39;: &#39;skylake-avx512&#39;}</code> </p> </li> <li> <p>RK3399</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;ARM64&quot;, &quot;Accelerator&quot;: &quot;MALI&quot;}</code> </p> </li> <li> <p>ARMv7 phone (CPU)</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;ANDROID&quot;, &quot;Arch&quot;: &quot;ARM</em>EABI&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;ANDROID<em>PLATFORM&#39;: 25, &#39;mattr&#39;: [&#39;+neon&#39;]}</code> </p> </li> <li> <p>ARMv8 phone (CPU)</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;ANDROID&quot;, &quot;Arch&quot;: &quot;ARM64&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;ANDROID</em>PLATFORM&#39;: 29}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     +       +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11542:1625
[INFO] [stdout]       |
[INFO] [stdout] 11542 | ...&quot;Os&quot;: &quot;ANDROID&quot;, &quot;Arch&quot;: &quot;ARM</em>EABI&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: ...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11542:1708
[INFO] [stdout]       |
[INFO] [stdout] 11542 | .../code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;ANDROID<em>PLATFORM&#39;: 25, &#39;mattr&#39;: [&#39;+neon&#39;]}</code> </p...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 11542 |     /// <p><p>Contains information about a target platform that you want your model to run on, such as OS, architecture, and accelerators. It is an alternative of <code>TargetDevice</code>.</p> <p>The following examples show how to configure the <code>TargetPlatform</code> and <code>CompilerOptions</code> JSON strings for popular target platforms: </p> <ul> <li> <p>Raspberry Pi 3 Model B+</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;ARM<em>EABIHF&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;mattr&#39;: [&#39;+neon&#39;]}</code> </p> </li> <li> <p>Jetson TX2</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;ARM64&quot;, &quot;Accelerator&quot;: &quot;NVIDIA&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;gpu-code&#39;: &#39;sm</em>62&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: &#39;10.0&#39;}</code> </p> </li> <li> <p>EC2 m5.2xlarge instance OS</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;X86<em>64&quot;, &quot;Accelerator&quot;: &quot;NVIDIA&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;mcpu&#39;: &#39;skylake-avx512&#39;}</code> </p> </li> <li> <p>RK3399</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;ARM64&quot;, &quot;Accelerator&quot;: &quot;MALI&quot;}</code> </p> </li> <li> <p>ARMv7 phone (CPU)</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;ANDROID&quot;, &quot;Arch&quot;: &quot;ARM</em>EABI&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;`ANDROID<em>`PLATFORM&#39;: 25, &#39;mattr&#39;: [&#39;+neon&#39;]}</code> </p> </li> <li> <p>ARMv8 phone (CPU)</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;ANDROID&quot;, &quot;Arch&quot;: &quot;ARM64&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;ANDROID</em>PLATFORM&#39;: 29}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     +           +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11542:1994
[INFO] [stdout]       |
[INFO] [stdout] 11542 | ...code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;ANDROID</em>PLATFORM&#39;: 29}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:12610:916
[INFO] [stdout]       |
[INFO] [stdout] 12610 | ...format: </p> <p> <code>[ {&quot;prefix&quot;: &quot;s3://customer<em>bucket/some/prefix/&quot;},</code> </p> <p> <code> &quot;relative...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 12610 |     /// <p><p>Depending on the value specified for the <code>S3DataType</code>, identifies either a key name prefix or a manifest. For example: </p> <ul> <li> <p> A key name prefix might look like this: <code>s3://bucketname/exampleprefix</code> </p> </li> <li> <p> A manifest might look like this: <code>s3://bucketname/example.manifest</code> </p> <p> A manifest is an S3 object which is a JSON file consisting of an array of elements. The first element is a prefix which is followed by one or more suffixes. SageMaker appends the suffix elements to the prefix to get a full set of <code>S3Uri</code>. Note that the prefix must be a valid non-empty <code>S3Uri</code> that precludes users from specifying a manifest whose individual <code>S3Uri</code> is sourced from different S3 buckets.</p> <p> The following code example shows a valid manifest format: </p> <p> <code>[ {&quot;prefix&quot;: &quot;s3://`customer<em>`bucket/some/prefix/&quot;},</code> </p> <p> <code> &quot;relative/path/to/custdata-1&quot;,</code> </p> <p> <code> &quot;relative/path/custdata-2&quot;,</code> </p> <p> <code> ...</code> </p> <p> <code> &quot;relative/path/custdata-N&quot;</code> </p> <p> <code>]</code> </p> <p> This JSON is equivalent to the following <code>S3Uri</code> list:</p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/to/custdata-1</code> </p> <p> <code>s3://customer<em>bucket/some/prefix/relative/path/custdata-2</code> </p> <p> <code>...</code> </p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/custdata-N</code> </p> <p>The complete set of <code>S3Uri</code> in this manifest is the input data for the channel for this data source. The object that each <code>S3Uri</code> points to must be readable by the IAM role that Amazon SageMaker uses to perform tasks on your behalf. </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            +            +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:12610:1293
[INFO] [stdout]       |
[INFO] [stdout] 12610 | ...e following <code>S3Uri</code> list:</p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/to/custdata-1</code> </p> <p> <c...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:12610:1380
[INFO] [stdout]       |
[INFO] [stdout] 12610 | ...x/relative/path/to/custdata-1</code> </p> <p> <code>s3://customer<em>bucket/some/prefix/relative/path/custdata-2</code> </p> <p> <code...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 12610 |     /// <p><p>Depending on the value specified for the <code>S3DataType</code>, identifies either a key name prefix or a manifest. For example: </p> <ul> <li> <p> A key name prefix might look like this: <code>s3://bucketname/exampleprefix</code> </p> </li> <li> <p> A manifest might look like this: <code>s3://bucketname/example.manifest</code> </p> <p> A manifest is an S3 object which is a JSON file consisting of an array of elements. The first element is a prefix which is followed by one or more suffixes. SageMaker appends the suffix elements to the prefix to get a full set of <code>S3Uri</code>. Note that the prefix must be a valid non-empty <code>S3Uri</code> that precludes users from specifying a manifest whose individual <code>S3Uri</code> is sourced from different S3 buckets.</p> <p> The following code example shows a valid manifest format: </p> <p> <code>[ {&quot;prefix&quot;: &quot;s3://customer<em>bucket/some/prefix/&quot;},</code> </p> <p> <code> &quot;relative/path/to/custdata-1&quot;,</code> </p> <p> <code> &quot;relative/path/custdata-2&quot;,</code> </p> <p> <code> ...</code> </p> <p> <code> &quot;relative/path/custdata-N&quot;</code> </p> <p> <code>]</code> </p> <p> This JSON is equivalent to the following <code>S3Uri</code> list:</p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/to/custdata-1</code> </p> <p> <code>s3://`customer<em>`bucket/some/prefix/relative/path/custdata-2</code> </p> <p> <code>...</code> </p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/custdata-N</code> </p> <p>The complete set of <code>S3Uri</code> in this manifest is the input data for the channel for this data source. The object that each <code>S3Uri</code> points to must be readable by the IAM role that Amazon SageMaker uses to perform tasks on your behalf. </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            +            +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:12610:1489
[INFO] [stdout]       |
[INFO] [stdout] 12610 | ...-2</code> </p> <p> <code>...</code> </p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/custdata-N</code> </p> <p>The co...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]      --> src/generated.rs:12742:563
[INFO] [stdout]       |
[INFO] [stdout] 12742 | ...al states are referred to as the job&#39;s secondary status. </p> <p/></p>
[INFO] [stdout]       |                                                                      ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:12820:220
[INFO] [stdout]       |
[INFO] [stdout] 12820 | ...operation succeeded and completed.</p> </li> <li> <p> <code>UNDER<em>CHANGE</code> - Transitive state. Operations performed might not ...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 12820 |     /// <p><p>The current status of the product.</p> <ul> <li> <p> <code>AVAILABLE</code> - Stable state, ready to perform any operation. The most recent operation succeeded and completed.</p> </li> <li> <p> <code>`UNDER<em>`CHANGE</code> - Transitive state. Operations performed might not have valid results. Wait for an AVAILABLE status before performing operations.</p> </li> <li> <p> <code>TAINTED</code> - Stable state, ready to perform any operation. The stack has completed the requested operation but is not exactly what was requested. For example, a request to update to a new version failed and the stack rolled back to the current version.</p> </li> <li> <p> <code>ERROR</code> - An unexpected error occurred. The provisioned product exists but the stack is not running. For example, CloudFormation received a parameter value that was not valid and could not launch the stack.</p> </li> <li> <p> <code>PLAN</em>IN_PROGRESS</code> - Transitive state. The plan operations were performed to provision a new product, but resources have not yet been created. After reviewing the list of resources to be created, execute the plan. Wait for an AVAILABLE status before performing operations.</p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                       +         +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:12820:916
[INFO] [stdout]       |
[INFO] [stdout] 12820 | ...id and could not launch the stack.</p> </li> <li> <p> <code>PLAN</em>IN_PROGRESS</code> - Transitive state. The plan operations were p...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:13112:84
[INFO] [stdout]       |
[INFO] [stdout] 13112 |     /// <p><p>Specifies a target platform architecture.</p> <ul> <li> <p> <code>X86<em>64</code>: 64-bit version of the x86 instruction s...
[INFO] [stdout]       |                                                                                    ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 13112 |     /// <p><p>Specifies a target platform architecture.</p> <ul> <li> <p> <code>`X86<em>`64</code>: 64-bit version of the x86 instruction set.</p> </li> <li> <p> <code>X86</code>: 32-bit version of the x86 instruction set.</p> </li> <li> <p> <code>ARM64</code>: ARMv8 64-bit CPU.</p> </li> <li> <p> <code>ARM</em>EABIHF</code>: ARMv7 32-bit, Hard Float.</p> </li> <li> <p> <code>ARM_EABI</code>: ARMv7 32-bit, Soft Float. Used by Android 32-bit ARM platform.</p> </li> </ul></p>
[INFO] [stdout]       |                                                                                 +       +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:13112:307
[INFO] [stdout]       |
[INFO] [stdout] 13112 | ...ode>ARM64</code>: ARMv8 64-bit CPU.</p> </li> <li> <p> <code>ARM</em>EABIHF</code>: ARMv7 32-bit, Hard Float.</p> </li> <li> <p> <code...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:13115:242
[INFO] [stdout]       |
[INFO] [stdout] 13115 | ...stems. Android API level can be specified using the <code>ANDROID<em>PLATFORM</code> compiler option. For example, <code>&quot;Compile...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 13115 |     /// <p><p>Specifies a target platform OS.</p> <ul> <li> <p> <code>LINUX</code>: Linux-based operating systems.</p> </li> <li> <p> <code>ANDROID</code>: Android operating systems. Android API level can be specified using the <code>`ANDROID<em>`PLATFORM</code> compiler option. For example, <code>&quot;CompilerOptions&quot;: {&#39;ANDROID</em>PLATFORM&#39;: 28}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                           +           +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:13115:340
[INFO] [stdout]       |
[INFO] [stdout] 13115 | ...n. For example, <code>&quot;CompilerOptions&quot;: {&#39;ANDROID</em>PLATFORM&#39;: 28}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]      --> src/generated.rs:13144:12
[INFO] [stdout]       |
[INFO] [stdout] 13144 |     /// <p><p/></p>
[INFO] [stdout]       |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]      --> src/generated.rs:13148:12
[INFO] [stdout]       |
[INFO] [stdout] 13148 |     /// <p><p/></p>
[INFO] [stdout]       |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]      --> src/generated.rs:13151:12
[INFO] [stdout]       |
[INFO] [stdout] 13151 |     /// <p><p/></p>
[INFO] [stdout]       |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:13649:489
[INFO] [stdout]       |
[INFO] [stdout] 13649 | ...format: </p> <p> <code>[ {&quot;prefix&quot;: &quot;s3://customer<em>bucket/some/prefix/&quot;},</code> </p> <p> <code>&quot;relative/...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 13649 |     /// <p><p>Depending on the value specified for the <code>S3DataType</code>, identifies either a key name prefix or a manifest. For example:</p> <ul> <li> <p> A key name prefix might look like this: <code>s3://bucketname/exampleprefix</code>. </p> </li> <li> <p> A manifest might look like this: <code>s3://bucketname/example.manifest</code> </p> <p> The manifest is an S3 object which is a JSON file with the following format: </p> <p> <code>[ {&quot;prefix&quot;: &quot;s3://`customer<em>`bucket/some/prefix/&quot;},</code> </p> <p> <code>&quot;relative/path/to/custdata-1&quot;,</code> </p> <p> <code>&quot;relative/path/custdata-2&quot;,</code> </p> <p> <code>...</code> </p> <p> <code>&quot;relative/path/custdata-N&quot;</code> </p> <p> <code>]</code> </p> <p> The preceding JSON matches the following <code>S3Uris</code>: </p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/to/custdata-1</code> </p> <p> <code>s3://customer<em>bucket/some/prefix/relative/path/custdata-2</code> </p> <p> <code>...</code> </p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/custdata-N</code> </p> <p> The complete set of <code>S3Uris</code> in this manifest constitutes the input data for the channel for this datasource. The object that each <code>S3Uris</code> points to must be readable by the IAM role that Amazon SageMaker uses to perform tasks on your behalf.</p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 +            +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:13649:859
[INFO] [stdout]       |
[INFO] [stdout] 13649 | ... the following <code>S3Uris</code>: </p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/to/custdata-1</code> </p> <p> <c...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:13649:946
[INFO] [stdout]       |
[INFO] [stdout] 13649 | ...x/relative/path/to/custdata-1</code> </p> <p> <code>s3://customer<em>bucket/some/prefix/relative/path/custdata-2</code> </p> <p> <code...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 13649 |     /// <p><p>Depending on the value specified for the <code>S3DataType</code>, identifies either a key name prefix or a manifest. For example:</p> <ul> <li> <p> A key name prefix might look like this: <code>s3://bucketname/exampleprefix</code>. </p> </li> <li> <p> A manifest might look like this: <code>s3://bucketname/example.manifest</code> </p> <p> The manifest is an S3 object which is a JSON file with the following format: </p> <p> <code>[ {&quot;prefix&quot;: &quot;s3://customer<em>bucket/some/prefix/&quot;},</code> </p> <p> <code>&quot;relative/path/to/custdata-1&quot;,</code> </p> <p> <code>&quot;relative/path/custdata-2&quot;,</code> </p> <p> <code>...</code> </p> <p> <code>&quot;relative/path/custdata-N&quot;</code> </p> <p> <code>]</code> </p> <p> The preceding JSON matches the following <code>S3Uris</code>: </p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/to/custdata-1</code> </p> <p> <code>s3://`customer<em>`bucket/some/prefix/relative/path/custdata-2</code> </p> <p> <code>...</code> </p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/custdata-N</code> </p> <p> The complete set of <code>S3Uris</code> in this manifest constitutes the input data for the channel for this datasource. The object that each <code>S3Uris</code> points to must be readable by the IAM role that Amazon SageMaker uses to perform tasks on your behalf.</p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          +            +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:13649:1055
[INFO] [stdout]       |
[INFO] [stdout] 13649 | ...-2</code> </p> <p> <code>...</code> </p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/custdata-N</code> </p> <p> The c...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: 106 warnings emitted
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stderr]     Finished dev [unoptimized + debuginfo] target(s) in 18.92s
[INFO] running `Command { std: "docker" "inspect" "df950d75c5c3df0b7fe84b45e7e8513b89a4940914b25bc87b249954c41a03fd", kill_on_drop: false }`
[INFO] running `Command { std: "docker" "rm" "-f" "df950d75c5c3df0b7fe84b45e7e8513b89a4940914b25bc87b249954c41a03fd", kill_on_drop: false }`
[INFO] [stdout] df950d75c5c3df0b7fe84b45e7e8513b89a4940914b25bc87b249954c41a03fd
[INFO] running `Command { std: "docker" "create" "-v" "/var/lib/crater-agent-workspace/builds/worker-0-tc1/target:/opt/rustwide/target:rw,Z" "-v" "/var/lib/crater-agent-workspace/builds/worker-0-tc1/source:/opt/rustwide/workdir:ro,Z" "-v" "/var/lib/crater-agent-workspace/cargo-home:/opt/rustwide/cargo-home:ro,Z" "-v" "/var/lib/crater-agent-workspace/rustup-home:/opt/rustwide/rustup-home:ro,Z" "-e" "SOURCE_DIR=/opt/rustwide/workdir" "-e" "CARGO_TARGET_DIR=/opt/rustwide/target" "-e" "CARGO_INCREMENTAL=0" "-e" "RUST_BACKTRACE=full" "-e" "RUSTFLAGS=--cap-lints=warn" "-e" "RUSTDOCFLAGS=--cap-lints=warn" "-e" "DOCS_RS=1" "-e" "RUSTC_BOOTSTRAP=1" "-e" "CARGO_HOME=/opt/rustwide/cargo-home" "-e" "RUSTUP_HOME=/opt/rustwide/rustup-home" "-w" "/opt/rustwide/workdir" "-m" "1610612736" "--user" "0:0" "--network" "none" "ghcr.io/rust-lang/crates-build-env/linux@sha256:5ff2268d62e97bff2cde7d5815dd6ed5b47097566f13b8d0ca110b04b60e07ed" "/opt/rustwide/cargo-home/bin/cargo" "+1.69.0" "rustdoc" "--lib" "-Zrustdoc-map" "-Z" "unstable-options" "--config" "build.rustdocflags=[\"-Z\", \"unstable-options\", \"--document-private-items\"]" "--frozen" "--message-format=json", kill_on_drop: false }`
[INFO] [stdout] 0a45b5797e47bf56fc97787166181073fed5366f9d77d8bba61ece0b43fbe07d
[INFO] running `Command { std: "docker" "start" "-a" "0a45b5797e47bf56fc97787166181073fed5366f9d77d8bba61ece0b43fbe07d", kill_on_drop: false }`
[INFO] [stderr]  Documenting rusoto_sagemaker v0.48.0 (/opt/rustwide/workdir)
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:167:12
[INFO] [stdout]     |
[INFO] [stdout] 167 |     /// <p><p/></p>
[INFO] [stdout]     |            ^^
[INFO] [stdout]     |
[INFO] [stdout]     = note: `#[warn(rustdoc::invalid_html_tags)]` on by default
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:737:12
[INFO] [stdout]     |
[INFO] [stdout] 737 |     /// <p><p/></p>
[INFO] [stdout]     |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:755:12
[INFO] [stdout]     |
[INFO] [stdout] 755 |     /// <p><p/></p>
[INFO] [stdout]     |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:759:12
[INFO] [stdout]     |
[INFO] [stdout] 759 |     /// <p><p/></p>
[INFO] [stdout]     |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:763:12
[INFO] [stdout]     |
[INFO] [stdout] 763 |     /// <p><p/></p>
[INFO] [stdout]     |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:821:12
[INFO] [stdout]     |
[INFO] [stdout] 821 |     /// <p><p/></p>
[INFO] [stdout]     |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:826:8
[INFO] [stdout]     |
[INFO] [stdout] 826 | /// <p><p/></p>
[INFO] [stdout]     |        ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:829:12
[INFO] [stdout]     |
[INFO] [stdout] 829 |     /// <p><p/></p>
[INFO] [stdout]     |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:833:12
[INFO] [stdout]     |
[INFO] [stdout] 833 |     /// <p><p/></p>
[INFO] [stdout]     |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:839:8
[INFO] [stdout]     |
[INFO] [stdout] 839 | /// <p><p/></p>
[INFO] [stdout]     |        ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:842:12
[INFO] [stdout]     |
[INFO] [stdout] 842 |     /// <p><p/></p>
[INFO] [stdout]     |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]    --> src/generated.rs:887:12
[INFO] [stdout]     |
[INFO] [stdout] 887 |     /// <p><p/> <p>Specify RecordIO as the value when input data is in raw format but the training algorithm requires the RecordIO format...
[INFO] [stdout]     |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:1913:1755
[INFO] [stdout]      |
[INFO] [stdout] 1913 | ...>) labeling jobs for this task type. </p> </li> </ul> </li> </ul> <p/> <important> <p>If you are creating an adjustment or verificatio...
[INFO] [stdout]      |                                                                      ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:1916:891
[INFO] [stdout]      |
[INFO] [stdout] 1916 | ...mat. Identify the labels you want to use by replacing <code>label<em>1</code>, <code>label</em>2</code>,<code>...</code>,<code>label<e...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 1916 |     /// <p><p>The S3 URI of the file, referred to as a <i>label category configuration file</i>, that defines the categories used to label the data objects.</p> <p>For 3D point cloud and video frame task types, you can add label category attributes and frame attributes to your label category configuration file. To learn how, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/sms-point-cloud-label-category-config.html">Create a Labeling Category Configuration File for 3D Point Cloud Labeling Jobs</a>. </p> <p>For all other <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/sms-task-types.html">built-in task types</a> and <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/sms-custom-templates.html">custom tasks</a>, your label category configuration file must be a JSON file in the following format. Identify the labels you want to use by replacing <code>`label<em>`1</code>, <code>label</em>2</code>,<code>...</code>,<code>label<em>n</code> with your label categories.</p> <p> <code>{ </code> </p> <p> <code>&quot;document-version&quot;: &quot;2018-11-28&quot;,</code> </p> <p> <code>&quot;labels&quot;: [{&quot;label&quot;: &quot;label</em>1&quot;},{&quot;label&quot;: &quot;label<em>2&quot;},...{&quot;label&quot;: &quot;label</em>n&quot;}]</code> </p> <p> <code>}</code> </p> <p>Note the following about the label category configuration file:</p> <ul> <li> <p>For image classification and text classification (single and multi-label) you must specify at least two label categories. For all other task types, the minimum number of label categories required is one. </p> </li> <li> <p>Each label category must be unique, you cannot specify duplicate label categories.</p> </li> <li> <p>If you create a 3D point cloud or video frame adjustment or verification labeling job, you must include <code>auditLabelAttributeName</code> in the label category configuration. Use this parameter to enter the <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateLabelingJob.html#sagemaker-CreateLabelingJob-request-LabelAttributeName"> <code>LabelAttributeName</code> </a> of the labeling job you want to adjust or verify annotations of.</p> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      +         +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:1916:916
[INFO] [stdout]      |
[INFO] [stdout] 1916 | ...ou want to use by replacing <code>label<em>1</code>, <code>label</em>2</code>,<code>...</code>,<code>label<em>n</code> with your label...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:1916:958
[INFO] [stdout]      |
[INFO] [stdout] 1916 | ...m>1</code>, <code>label</em>2</code>,<code>...</code>,<code>label<em>n</code> with your label categories.</p> <p> <code>{ </code> </p>...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 1916 |     /// <p><p>The S3 URI of the file, referred to as a <i>label category configuration file</i>, that defines the categories used to label the data objects.</p> <p>For 3D point cloud and video frame task types, you can add label category attributes and frame attributes to your label category configuration file. To learn how, see <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/sms-point-cloud-label-category-config.html">Create a Labeling Category Configuration File for 3D Point Cloud Labeling Jobs</a>. </p> <p>For all other <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/sms-task-types.html">built-in task types</a> and <a href="https://docs.aws.amazon.com/sagemaker/latest/dg/sms-custom-templates.html">custom tasks</a>, your label category configuration file must be a JSON file in the following format. Identify the labels you want to use by replacing <code>label<em>1</code>, <code>label</em>2</code>,<code>...</code>,<code>`label<em>`n</code> with your label categories.</p> <p> <code>{ </code> </p> <p> <code>&quot;document-version&quot;: &quot;2018-11-28&quot;,</code> </p> <p> <code>&quot;labels&quot;: [{&quot;label&quot;: &quot;label</em>1&quot;},{&quot;label&quot;: &quot;label<em>2&quot;},...{&quot;label&quot;: &quot;label</em>n&quot;}]</code> </p> <p> <code>}</code> </p> <p>Note the following about the label category configuration file:</p> <ul> <li> <p>For image classification and text classification (single and multi-label) you must specify at least two label categories. For all other task types, the minimum number of label categories required is one. </p> </li> <li> <p>Each label category must be unique, you cannot specify duplicate label categories.</p> </li> <li> <p>If you create a 3D point cloud or video frame adjustment or verification labeling job, you must include <code>auditLabelAttributeName</code> in the label category configuration. Use this parameter to enter the <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_CreateLabelingJob.html#sagemaker-CreateLabelingJob-request-LabelAttributeName"> <code>LabelAttributeName</code> </a> of the labeling job you want to adjust or verify annotations of.</p> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                         +         +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:1916:1166
[INFO] [stdout]      |
[INFO] [stdout] 1916 | ...> <p> <code>&quot;labels&quot;: [{&quot;label&quot;: &quot;label</em>1&quot;},{&quot;label&quot;: &quot;label<em>2&quot;},...{&quot;la...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `i`
[INFO] [stdout]     --> src/generated.rs:2588:118
[INFO] [stdout]      |
[INFO] [stdout] 2588 |     /// <p>Specifies the number of records to include in a mini-batch for an HTTP inference request. A <i>record</i> <i/> is a single uni...
[INFO] [stdout]      |                                                                                                                      ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2844:8
[INFO] [stdout]      |
[INFO] [stdout] 2844 | /// <p><p/></p>
[INFO] [stdout]      |        ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2847:12
[INFO] [stdout]      |
[INFO] [stdout] 2847 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2851:12
[INFO] [stdout]      |
[INFO] [stdout] 2851 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2854:12
[INFO] [stdout]      |
[INFO] [stdout] 2854 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2857:12
[INFO] [stdout]      |
[INFO] [stdout] 2857 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2861:12
[INFO] [stdout]      |
[INFO] [stdout] 2861 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2864:12
[INFO] [stdout]      |
[INFO] [stdout] 2864 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2870:8
[INFO] [stdout]      |
[INFO] [stdout] 2870 | /// <p><p/></p>
[INFO] [stdout]      |        ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2874:12
[INFO] [stdout]      |
[INFO] [stdout] 2874 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2877:12
[INFO] [stdout]      |
[INFO] [stdout] 2877 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2880:12
[INFO] [stdout]      |
[INFO] [stdout] 2880 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2883:12
[INFO] [stdout]      |
[INFO] [stdout] 2883 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:2886:12
[INFO] [stdout]      |
[INFO] [stdout] 2886 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:3543:12
[INFO] [stdout]      |
[INFO] [stdout] 3543 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:3547:12
[INFO] [stdout]      |
[INFO] [stdout] 3547 |     /// <p><p/></p>
[INFO] [stdout]      |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:5189:136
[INFO] [stdout]      |
[INFO] [stdout] 5189 | ...This is one of the following values.</p> <ul> <li> <p> <code>DATA<em>QUALITY</code> - The schedule is for a data quality monitoring jo...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 5189 |     /// <p><p>The type of the monitoring job that this schedule runs. This is one of the following values.</p> <ul> <li> <p> <code>`DATA<em>`QUALITY</code> - The schedule is for a data quality monitoring job.</p> </li> <li> <p> <code>MODEL</em>QUALITY</code> - The schedule is for a model quality monitoring job.</p> </li> <li> <p> <code>MODEL<em>BIAS</code> - The schedule is for a bias monitoring job.</p> </li> <li> <p> <code>MODEL</em>EXPLAINABILITY</code> - The schedule is for an explainability monitoring job.</p> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                    +        +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:5189:238
[INFO] [stdout]      |
[INFO] [stdout] 5189 | ...or a data quality monitoring job.</p> </li> <li> <p> <code>MODEL</em>QUALITY</code> - The schedule is for a model quality monitoring j...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:5189:342
[INFO] [stdout]      |
[INFO] [stdout] 5189 | ...or a model quality monitoring job.</p> </li> <li> <p> <code>MODEL<em>BIAS</code> - The schedule is for a bias monitoring job.</p> </li...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 5189 |     /// <p><p>The type of the monitoring job that this schedule runs. This is one of the following values.</p> <ul> <li> <p> <code>DATA<em>QUALITY</code> - The schedule is for a data quality monitoring job.</p> </li> <li> <p> <code>MODEL</em>QUALITY</code> - The schedule is for a model quality monitoring job.</p> </li> <li> <p> <code>`MODEL<em>`BIAS</code> - The schedule is for a bias monitoring job.</p> </li> <li> <p> <code>MODEL</em>EXPLAINABILITY</code> - The schedule is for an explainability monitoring job.</p> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                 +         +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:5189:433
[INFO] [stdout]      |
[INFO] [stdout] 5189 | ...ule is for a bias monitoring job.</p> </li> <li> <p> <code>MODEL</em>EXPLAINABILITY</code> - The schedule is for an explainability mon...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `i`
[INFO] [stdout]     --> src/generated.rs:5783:118
[INFO] [stdout]      |
[INFO] [stdout] 5783 |     /// <p>Specifies the number of records to include in a mini-batch for an HTTP inference request. A <i>record</i> <i/> is a single uni...
[INFO] [stdout]      |                                                                                                                      ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:6742:1469
[INFO] [stdout]      |
[INFO] [stdout] 6742 | ... filter is satisfied by training jobs with a <code>&quot;learning<em>rate&quot;</code> hyperparameter that is less than <code>&quot;0....
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 6742 | /// <p><p>A conditional statement for a search expression that includes a resource property, a Boolean operator, and a value. Resources that match the statement are returned in the results from the <a>Search</a> API.</p> <p>If you specify a <code>Value</code>, but not an <code>Operator</code>, Amazon SageMaker uses the equals operator.</p> <p>In search, there are several property types:</p> <dl> <dt>Metrics</dt> <dd> <p>To define a metric filter, enter a value using the form <code>&quot;Metrics.&lt;name&gt;&quot;</code>, where <code>&lt;name&gt;</code> is a metric name. For example, the following filter searches for training jobs with an <code>&quot;accuracy&quot;</code> metric greater than <code>&quot;0.9&quot;</code>:</p> <p> <code>{</code> </p> <p> <code>&quot;Name&quot;: &quot;Metrics.accuracy&quot;,</code> </p> <p> <code>&quot;Operator&quot;: &quot;GreaterThan&quot;,</code> </p> <p> <code>&quot;Value&quot;: &quot;0.9&quot;</code> </p> <p> <code>}</code> </p> </dd> <dt>HyperParameters</dt> <dd> <p>To define a hyperparameter filter, enter a value with the form <code>&quot;HyperParameters.&lt;name&gt;&quot;</code>. Decimal hyperparameter values are treated as a decimal in a comparison if the specified <code>Value</code> is also a decimal value. If the specified <code>Value</code> is an integer, the decimal hyperparameter values are treated as integers. For example, the following filter is satisfied by training jobs with a <code>&quot;`learning<em>`rate&quot;</code> hyperparameter that is less than <code>&quot;0.5&quot;</code>:</p> <p> <code> {</code> </p> <p> <code> &quot;Name&quot;: &quot;HyperParameters.learning</em>rate&quot;,</code> </p> <p> <code> &quot;Operator&quot;: &quot;LessThan&quot;,</code> </p> <p> <code> &quot;Value&quot;: &quot;0.5&quot;</code> </p> <p> <code> }</code> </p> </dd> <dt>Tags</dt> <dd> <p>To define a tag filter, enter a value with the form <code>Tags.&lt;key&gt;</code>.</p> </dd> </dl></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     +            +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:6742:1642
[INFO] [stdout]      |
[INFO] [stdout] 6742 | ...</p> <p> <code> &quot;Name&quot;: &quot;HyperParameters.learning</em>rate&quot;,</code> </p> <p> <code> &quot;Operator&quot;: &quot;Le...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]     --> src/generated.rs:7078:640
[INFO] [stdout]      |
[INFO] [stdout] 7078 | ...Amazon S3, the model artifacts, and intermediate information.</p> <p/> <p>For more information about input modes, see <a href="https:/...
[INFO] [stdout]      |                                                                      ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7308:85
[INFO] [stdout]      |
[INFO] [stdout] 7308 |     /// <p><p>Specifies one of the following:</p> <dl> <dt>IDENTICAL<em>DATA</em>AND<em>ALGORITHM</dt> <dd> <p>The new hyperparameter tun...
[INFO] [stdout]      |                                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 7308 |     /// <p><p>Specifies one of the following:</p> <dl> <dt>IDENTICAL<em>DATA</em>`AND<em>`ALGORITHM</dt> <dd> <p>The new hyperparameter tuning job uses the same input data and training image as the parent tuning jobs. You can change the hyperparameter ranges to search and the maximum number of training jobs that the hyperparameter tuning job launches. You cannot use a new version of the training algorithm, unless the changes in the new version do not affect the algorithm itself. For example, changes that improve logging or adding support for a different data format are allowed. You can also change hyperparameters from tunable to static, and from static to tunable, but the total number of static plus tunable hyperparameters must remain the same as it is in all parent jobs. The objective metric for the new tuning job must be the same as for all parent jobs.</p> </dd> <dt>TRANSFER</em>LEARNING</dt> <dd> <p>The new hyperparameter tuning job can include input data, hyperparameter ranges, maximum number of concurrent training jobs, and maximum number of training jobs that are different than those of its parent hyperparameter tuning jobs. The training image can also be a different version from the version used in the parent hyperparameter tuning job. You can also change hyperparameters from tunable to static, and from static to tunable, but the total number of static plus tunable hyperparameters must remain the same as it is in all parent jobs. The objective metric for the new tuning job must be the same as for all parent jobs.</p> </dd> </dl></p>
[INFO] [stdout]      |                                                                                  +       +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7308:889
[INFO] [stdout]      |
[INFO] [stdout] 7308 | ... must be the same as for all parent jobs.</p> </dd> <dt>TRANSFER</em>LEARNING</dt> <dd> <p>The new hyperparameter tuning job can inclu...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:1453
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ... input:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 7419 |     /// <p><p>Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are <a>InputConfig$Framework</a> specific. </p> <ul> <li> <p> <code>TensorFlow</code>: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>KERAS</code>: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, <code>DataInputConfig</code> should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;`input<em>`1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input</em>1&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>MXNET/ONNX/DARKNET</code>: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>PyTorch</code>: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.</p> <ul> <li> <p>Examples for one input in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Example for one input in list format: <code>[[1,3,224,224]]</code> </p> </li> <li> <p>Examples for two inputs in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]} </code> </p> </li> </ul> </li> <li> <p>Example for two inputs in list format: <code>[[1,3,224,224], [1,3,224,224]]</code> </p> </li> </ul> </li> <li> <p> <code>XGBOOST</code>: input data name and shape are not needed.</p> </li> </ul> <p> <code>DataInputConfig</code> supports the following parameters for <code>CoreML</code> <a>OutputConfig$TargetDevice</a> (ML Model format):</p> <ul> <li> <p> <code>shape</code>: Input shape, for example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [1,224,224,3]}}</code>. In addition to static input shapes, CoreML converter supports Flexible input shapes:</p> <ul> <li> <p>Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: <code>{&quot;input</em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3]}}</code> </p> </li> <li> <p>Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [[1, 224, 224, 3], [1, 160, 160, 3]]}}</code> </p> </li> </ul> </li> <li> <p> <code>default</em>shape</code>: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3], &quot;default</em>shape&quot;: [1, 224, 224, 3]}}</code> </p> </li> <li> <p> <code>type</code>: Input type. Allowed values: <code>Image</code> and <code>Tensor</code>. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as <code>bias</code> and <code>scale</code>.</p> </li> <li> <p> <code>bias</code>: If the input type is an Image, you need to provide the bias vector.</p> </li> <li> <p> <code>scale</code>: If the input type is an Image, you need to provide a scale factor.</p> </li> </ul> <p>CoreML <code>ClassifierConfig</code> parameters can be specified using <a>OutputConfig$CompilerOptions</a>. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:</p> <ul> <li> <p>Tensor type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default</em>shape&quot;: [1,224,224,3]}}</code> </p> </li> </ul> </li> <li> <p>Tensor type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224]}]</code> </p> </li> </ul> </li> <li> <p>Image type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input</em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default<em>shape&quot;: [1,224,224,3], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> <li> <p>Image type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}]</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> </ul> <p>Depending on the model format, <code>DataInputConfig</code> requires the following parameters for <code>ml<em>eia2</code> &lt;a href=&quot;https://docs.aws.amazon.com/sagemaker/latest/APIReference/API</em>OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice&quot;&gt;OutputConfig:TargetDevice</a>.</p> <ul> <li> <p>For TensorFlow models saved in the SavedModel format, specify the input names from <code>signature<em>def</em>key</code> and the input model shapes for <code>DataInputConfig</code>. Specify the <code>signature<em>def</em>key</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a> if the model does not use TensorFlow&#39;s default signature def key. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;inputs&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;signature<em>def</em>key&quot;: &quot;serving<em>custom&quot;}</code> </p> </li> </ul> </li> <li> <p>For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in <code>DataInputConfig</code> and the output tensor names for <code>output</em>names</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a>. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>tensor:0&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;output</em>names&quot;: [&quot;output_tensor:0&quot;]}</code> </p> </li> </ul> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        +         +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:1542
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input</em>1&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Exam...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:4148
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...> <code>shape</code>: Input shape, for example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [1,224,224,3]}}</code>. In addition ...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 7419 |     /// <p><p>Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are <a>InputConfig$Framework</a> specific. </p> <ul> <li> <p> <code>TensorFlow</code>: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>KERAS</code>: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, <code>DataInputConfig</code> should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input</em>1&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>MXNET/ONNX/DARKNET</code>: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>PyTorch</code>: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.</p> <ul> <li> <p>Examples for one input in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Example for one input in list format: <code>[[1,3,224,224]]</code> </p> </li> <li> <p>Examples for two inputs in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]} </code> </p> </li> </ul> </li> <li> <p>Example for two inputs in list format: <code>[[1,3,224,224], [1,3,224,224]]</code> </p> </li> </ul> </li> <li> <p> <code>XGBOOST</code>: input data name and shape are not needed.</p> </li> </ul> <p> <code>DataInputConfig</code> supports the following parameters for <code>CoreML</code> <a>OutputConfig$TargetDevice</a> (ML Model format):</p> <ul> <li> <p> <code>shape</code>: Input shape, for example <code>{&quot;`input<em>`1&quot;: {&quot;shape&quot;: [1,224,224,3]}}</code>. In addition to static input shapes, CoreML converter supports Flexible input shapes:</p> <ul> <li> <p>Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: <code>{&quot;input</em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3]}}</code> </p> </li> <li> <p>Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [[1, 224, 224, 3], [1, 160, 160, 3]]}}</code> </p> </li> </ul> </li> <li> <p> <code>default</em>shape</code>: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3], &quot;default</em>shape&quot;: [1, 224, 224, 3]}}</code> </p> </li> <li> <p> <code>type</code>: Input type. Allowed values: <code>Image</code> and <code>Tensor</code>. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as <code>bias</code> and <code>scale</code>.</p> </li> <li> <p> <code>bias</code>: If the input type is an Image, you need to provide the bias vector.</p> </li> <li> <p> <code>scale</code>: If the input type is an Image, you need to provide a scale factor.</p> </li> </ul> <p>CoreML <code>ClassifierConfig</code> parameters can be specified using <a>OutputConfig$CompilerOptions</a>. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:</p> <ul> <li> <p>Tensor type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default</em>shape&quot;: [1,224,224,3]}}</code> </p> </li> </ul> </li> <li> <p>Tensor type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224]}]</code> </p> </li> </ul> </li> <li> <p>Image type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input</em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default<em>shape&quot;: [1,224,224,3], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> <li> <p>Image type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}]</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> </ul> <p>Depending on the model format, <code>DataInputConfig</code> requires the following parameters for <code>ml<em>eia2</code> &lt;a href=&quot;https://docs.aws.amazon.com/sagemaker/latest/APIReference/API</em>OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice&quot;&gt;OutputConfig:TargetDevice</a>.</p> <ul> <li> <p>For TensorFlow models saved in the SavedModel format, specify the input names from <code>signature<em>def</em>key</code> and the input model shapes for <code>DataInputConfig</code>. Specify the <code>signature<em>def</em>key</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a> if the model does not use TensorFlow&#39;s default signature def key. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;inputs&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;signature<em>def</em>key&quot;: &quot;serving<em>custom&quot;}</code> </p> </li> </ul> </li> <li> <p>For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in <code>DataInputConfig</code> and the output tensor names for <code>output</em>names</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a>. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>tensor:0&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;output</em>names&quot;: [&quot;output_tensor:0&quot;]}</code> </p> </li> </ul> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               +         +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:4480
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...ific interval in that dimension, for example: <code>{&quot;input</em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3]}}</...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:4745
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...erate all supported input shapes, for example: <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [[1, 224, 224, 3], [1, 160, 160, 3]]...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 7419 |     /// <p><p>Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are <a>InputConfig$Framework</a> specific. </p> <ul> <li> <p> <code>TensorFlow</code>: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>KERAS</code>: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, <code>DataInputConfig</code> should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input</em>1&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>MXNET/ONNX/DARKNET</code>: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>PyTorch</code>: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.</p> <ul> <li> <p>Examples for one input in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Example for one input in list format: <code>[[1,3,224,224]]</code> </p> </li> <li> <p>Examples for two inputs in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]} </code> </p> </li> </ul> </li> <li> <p>Example for two inputs in list format: <code>[[1,3,224,224], [1,3,224,224]]</code> </p> </li> </ul> </li> <li> <p> <code>XGBOOST</code>: input data name and shape are not needed.</p> </li> </ul> <p> <code>DataInputConfig</code> supports the following parameters for <code>CoreML</code> <a>OutputConfig$TargetDevice</a> (ML Model format):</p> <ul> <li> <p> <code>shape</code>: Input shape, for example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [1,224,224,3]}}</code>. In addition to static input shapes, CoreML converter supports Flexible input shapes:</p> <ul> <li> <p>Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: <code>{&quot;input</em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3]}}</code> </p> </li> <li> <p>Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: <code>{&quot;`input<em>`1&quot;: {&quot;shape&quot;: [[1, 224, 224, 3], [1, 160, 160, 3]]}}</code> </p> </li> </ul> </li> <li> <p> <code>default</em>shape</code>: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3], &quot;default</em>shape&quot;: [1, 224, 224, 3]}}</code> </p> </li> <li> <p> <code>type</code>: Input type. Allowed values: <code>Image</code> and <code>Tensor</code>. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as <code>bias</code> and <code>scale</code>.</p> </li> <li> <p> <code>bias</code>: If the input type is an Image, you need to provide the bias vector.</p> </li> <li> <p> <code>scale</code>: If the input type is an Image, you need to provide a scale factor.</p> </li> </ul> <p>CoreML <code>ClassifierConfig</code> parameters can be specified using <a>OutputConfig$CompilerOptions</a>. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:</p> <ul> <li> <p>Tensor type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default</em>shape&quot;: [1,224,224,3]}}</code> </p> </li> </ul> </li> <li> <p>Tensor type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224]}]</code> </p> </li> </ul> </li> <li> <p>Image type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input</em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default<em>shape&quot;: [1,224,224,3], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> <li> <p>Image type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}]</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> </ul> <p>Depending on the model format, <code>DataInputConfig</code> requires the following parameters for <code>ml<em>eia2</code> &lt;a href=&quot;https://docs.aws.amazon.com/sagemaker/latest/APIReference/API</em>OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice&quot;&gt;OutputConfig:TargetDevice</a>.</p> <ul> <li> <p>For TensorFlow models saved in the SavedModel format, specify the input names from <code>signature<em>def</em>key</code> and the input model shapes for <code>DataInputConfig</code>. Specify the <code>signature<em>def</em>key</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a> if the model does not use TensorFlow&#39;s default signature def key. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;inputs&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;signature<em>def</em>key&quot;: &quot;serving<em>custom&quot;}</code> </p> </li> </ul> </li> <li> <p>For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in <code>DataInputConfig</code> and the output tensor names for <code>output</em>names</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a>. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>tensor:0&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;output</em>names&quot;: [&quot;output_tensor:0&quot;]}</code> </p> </li> </ul> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                    +         +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:4869
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ... 160, 3]]}}</code> </p> </li> </ul> </li> <li> <p> <code>default</em>shape</code>: Default input shape. You can set a default shape du...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:6340
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224]}]</code> </p> </li> </ul> </li> <li> <...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 7419 |     /// <p><p>Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are <a>InputConfig$Framework</a> specific. </p> <ul> <li> <p> <code>TensorFlow</code>: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>KERAS</code>: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, <code>DataInputConfig</code> should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input</em>1&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>MXNET/ONNX/DARKNET</code>: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>PyTorch</code>: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.</p> <ul> <li> <p>Examples for one input in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Example for one input in list format: <code>[[1,3,224,224]]</code> </p> </li> <li> <p>Examples for two inputs in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]} </code> </p> </li> </ul> </li> <li> <p>Example for two inputs in list format: <code>[[1,3,224,224], [1,3,224,224]]</code> </p> </li> </ul> </li> <li> <p> <code>XGBOOST</code>: input data name and shape are not needed.</p> </li> </ul> <p> <code>DataInputConfig</code> supports the following parameters for <code>CoreML</code> <a>OutputConfig$TargetDevice</a> (ML Model format):</p> <ul> <li> <p> <code>shape</code>: Input shape, for example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [1,224,224,3]}}</code>. In addition to static input shapes, CoreML converter supports Flexible input shapes:</p> <ul> <li> <p>Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: <code>{&quot;input</em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3]}}</code> </p> </li> <li> <p>Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [[1, 224, 224, 3], [1, 160, 160, 3]]}}</code> </p> </li> </ul> </li> <li> <p> <code>default</em>shape</code>: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3], &quot;default</em>shape&quot;: [1, 224, 224, 3]}}</code> </p> </li> <li> <p> <code>type</code>: Input type. Allowed values: <code>Image</code> and <code>Tensor</code>. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as <code>bias</code> and <code>scale</code>.</p> </li> <li> <p> <code>bias</code>: If the input type is an Image, you need to provide the bias vector.</p> </li> <li> <p> <code>scale</code>: If the input type is an Image, you need to provide a scale factor.</p> </li> </ul> <p>CoreML <code>ClassifierConfig</code> parameters can be specified using <a>OutputConfig$CompilerOptions</a>. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:</p> <ul> <li> <p>Tensor type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default</em>shape&quot;: [1,224,224,3]}}</code> </p> </li> </ul> </li> <li> <p>Tensor type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;`default<em>`shape&quot;: [1,3,224,224]}]</code> </p> </li> </ul> </li> <li> <p>Image type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input</em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default<em>shape&quot;: [1,224,224,3], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> <li> <p>Image type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}]</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> </ul> <p>Depending on the model format, <code>DataInputConfig</code> requires the following parameters for <code>ml<em>eia2</code> &lt;a href=&quot;https://docs.aws.amazon.com/sagemaker/latest/APIReference/API</em>OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice&quot;&gt;OutputConfig:TargetDevice</a>.</p> <ul> <li> <p>For TensorFlow models saved in the SavedModel format, specify the input names from <code>signature<em>def</em>key</code> and the input model shapes for <code>DataInputConfig</code>. Specify the <code>signature<em>def</em>key</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a> if the model does not use TensorFlow&#39;s default signature def key. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;inputs&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;signature<em>def</em>key&quot;: &quot;serving<em>custom&quot;}</code> </p> </li> </ul> </li> <li> <p>For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in <code>DataInputConfig</code> and the output tensor names for <code>output</em>names</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a>. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>tensor:0&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;output</em>names&quot;: [&quot;output_tensor:0&quot;]}</code> </p> </li> </ul> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             +           +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:6494
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input</em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quo...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:6573
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...{&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default<em>shape&quot;: [1,224,224,3], &quot;type&quot;: &quot;Image&quot;, ...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 7419 |     /// <p><p>Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are <a>InputConfig$Framework</a> specific. </p> <ul> <li> <p> <code>TensorFlow</code>: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>KERAS</code>: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, <code>DataInputConfig</code> should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input</em>1&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>MXNET/ONNX/DARKNET</code>: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>PyTorch</code>: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.</p> <ul> <li> <p>Examples for one input in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Example for one input in list format: <code>[[1,3,224,224]]</code> </p> </li> <li> <p>Examples for two inputs in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]} </code> </p> </li> </ul> </li> <li> <p>Example for two inputs in list format: <code>[[1,3,224,224], [1,3,224,224]]</code> </p> </li> </ul> </li> <li> <p> <code>XGBOOST</code>: input data name and shape are not needed.</p> </li> </ul> <p> <code>DataInputConfig</code> supports the following parameters for <code>CoreML</code> <a>OutputConfig$TargetDevice</a> (ML Model format):</p> <ul> <li> <p> <code>shape</code>: Input shape, for example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [1,224,224,3]}}</code>. In addition to static input shapes, CoreML converter supports Flexible input shapes:</p> <ul> <li> <p>Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: <code>{&quot;input</em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3]}}</code> </p> </li> <li> <p>Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [[1, 224, 224, 3], [1, 160, 160, 3]]}}</code> </p> </li> </ul> </li> <li> <p> <code>default</em>shape</code>: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3], &quot;default</em>shape&quot;: [1, 224, 224, 3]}}</code> </p> </li> <li> <p> <code>type</code>: Input type. Allowed values: <code>Image</code> and <code>Tensor</code>. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as <code>bias</code> and <code>scale</code>.</p> </li> <li> <p> <code>bias</code>: If the input type is an Image, you need to provide the bias vector.</p> </li> <li> <p> <code>scale</code>: If the input type is an Image, you need to provide a scale factor.</p> </li> </ul> <p>CoreML <code>ClassifierConfig</code> parameters can be specified using <a>OutputConfig$CompilerOptions</a>. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:</p> <ul> <li> <p>Tensor type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default</em>shape&quot;: [1,224,224,3]}}</code> </p> </li> </ul> </li> <li> <p>Tensor type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224]}]</code> </p> </li> </ul> </li> <li> <p>Image type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input</em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;`default<em>`shape&quot;: [1,224,224,3], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> <li> <p>Image type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}]</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> </ul> <p>Depending on the model format, <code>DataInputConfig</code> requires the following parameters for <code>ml<em>eia2</code> &lt;a href=&quot;https://docs.aws.amazon.com/sagemaker/latest/APIReference/API</em>OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice&quot;&gt;OutputConfig:TargetDevice</a>.</p> <ul> <li> <p>For TensorFlow models saved in the SavedModel format, specify the input names from <code>signature<em>def</em>key</code> and the input model shapes for <code>DataInputConfig</code>. Specify the <code>signature<em>def</em>key</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a> if the model does not use TensorFlow&#39;s default signature def key. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;inputs&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;signature<em>def</em>key&quot;: &quot;serving<em>custom&quot;}</code> </p> </li> </ul> </li> <li> <p>For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in <code>DataInputConfig</code> and the output tensor names for <code>output</em>names</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a>. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>tensor:0&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;output</em>names&quot;: [&quot;output_tensor:0&quot;]}</code> </p> </li> </ul> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      +           +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:6782
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code>...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:7050
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224], &quot;type&quot;: &quot;Image&quot;, ...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 7419 |     /// <p><p>Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are <a>InputConfig$Framework</a> specific. </p> <ul> <li> <p> <code>TensorFlow</code>: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>KERAS</code>: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, <code>DataInputConfig</code> should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input</em>1&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>MXNET/ONNX/DARKNET</code>: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>PyTorch</code>: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.</p> <ul> <li> <p>Examples for one input in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Example for one input in list format: <code>[[1,3,224,224]]</code> </p> </li> <li> <p>Examples for two inputs in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]} </code> </p> </li> </ul> </li> <li> <p>Example for two inputs in list format: <code>[[1,3,224,224], [1,3,224,224]]</code> </p> </li> </ul> </li> <li> <p> <code>XGBOOST</code>: input data name and shape are not needed.</p> </li> </ul> <p> <code>DataInputConfig</code> supports the following parameters for <code>CoreML</code> <a>OutputConfig$TargetDevice</a> (ML Model format):</p> <ul> <li> <p> <code>shape</code>: Input shape, for example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [1,224,224,3]}}</code>. In addition to static input shapes, CoreML converter supports Flexible input shapes:</p> <ul> <li> <p>Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: <code>{&quot;input</em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3]}}</code> </p> </li> <li> <p>Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [[1, 224, 224, 3], [1, 160, 160, 3]]}}</code> </p> </li> </ul> </li> <li> <p> <code>default</em>shape</code>: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3], &quot;default</em>shape&quot;: [1, 224, 224, 3]}}</code> </p> </li> <li> <p> <code>type</code>: Input type. Allowed values: <code>Image</code> and <code>Tensor</code>. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as <code>bias</code> and <code>scale</code>.</p> </li> <li> <p> <code>bias</code>: If the input type is an Image, you need to provide the bias vector.</p> </li> <li> <p> <code>scale</code>: If the input type is an Image, you need to provide a scale factor.</p> </li> </ul> <p>CoreML <code>ClassifierConfig</code> parameters can be specified using <a>OutputConfig$CompilerOptions</a>. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:</p> <ul> <li> <p>Tensor type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default</em>shape&quot;: [1,224,224,3]}}</code> </p> </li> </ul> </li> <li> <p>Tensor type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224]}]</code> </p> </li> </ul> </li> <li> <p>Image type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input</em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default<em>shape&quot;: [1,224,224,3], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> <li> <p>Image type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;`default<em>`shape&quot;: [1,3,224,224], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}]</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> </ul> <p>Depending on the model format, <code>DataInputConfig</code> requires the following parameters for <code>ml<em>eia2</code> &lt;a href=&quot;https://docs.aws.amazon.com/sagemaker/latest/APIReference/API</em>OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice&quot;&gt;OutputConfig:TargetDevice</a>.</p> <ul> <li> <p>For TensorFlow models saved in the SavedModel format, specify the input names from <code>signature<em>def</em>key</code> and the input model shapes for <code>DataInputConfig</code>. Specify the <code>signature<em>def</em>key</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a> if the model does not use TensorFlow&#39;s default signature def key. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;inputs&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;signature<em>def</em>key&quot;: &quot;serving<em>custom&quot;}</code> </p> </li> </ul> </li> <li> <p>For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in <code>DataInputConfig</code> and the output tensor names for <code>output</em>names</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a>. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>tensor:0&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;output</em>names&quot;: [&quot;output_tensor:0&quot;]}</code> </p> </li> </ul> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   +           +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:7259
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code>...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:7468
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...InputConfig</code> requires the following parameters for <code>ml<em>eia2</code> &lt;a href=&quot;https://docs.aws.amazon.com/sagemake...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 7419 |     /// <p><p>Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are <a>InputConfig$Framework</a> specific. </p> <ul> <li> <p> <code>TensorFlow</code>: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>KERAS</code>: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, <code>DataInputConfig</code> should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input</em>1&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>MXNET/ONNX/DARKNET</code>: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>PyTorch</code>: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.</p> <ul> <li> <p>Examples for one input in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Example for one input in list format: <code>[[1,3,224,224]]</code> </p> </li> <li> <p>Examples for two inputs in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]} </code> </p> </li> </ul> </li> <li> <p>Example for two inputs in list format: <code>[[1,3,224,224], [1,3,224,224]]</code> </p> </li> </ul> </li> <li> <p> <code>XGBOOST</code>: input data name and shape are not needed.</p> </li> </ul> <p> <code>DataInputConfig</code> supports the following parameters for <code>CoreML</code> <a>OutputConfig$TargetDevice</a> (ML Model format):</p> <ul> <li> <p> <code>shape</code>: Input shape, for example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [1,224,224,3]}}</code>. In addition to static input shapes, CoreML converter supports Flexible input shapes:</p> <ul> <li> <p>Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: <code>{&quot;input</em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3]}}</code> </p> </li> <li> <p>Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [[1, 224, 224, 3], [1, 160, 160, 3]]}}</code> </p> </li> </ul> </li> <li> <p> <code>default</em>shape</code>: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3], &quot;default</em>shape&quot;: [1, 224, 224, 3]}}</code> </p> </li> <li> <p> <code>type</code>: Input type. Allowed values: <code>Image</code> and <code>Tensor</code>. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as <code>bias</code> and <code>scale</code>.</p> </li> <li> <p> <code>bias</code>: If the input type is an Image, you need to provide the bias vector.</p> </li> <li> <p> <code>scale</code>: If the input type is an Image, you need to provide a scale factor.</p> </li> </ul> <p>CoreML <code>ClassifierConfig</code> parameters can be specified using <a>OutputConfig$CompilerOptions</a>. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:</p> <ul> <li> <p>Tensor type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default</em>shape&quot;: [1,224,224,3]}}</code> </p> </li> </ul> </li> <li> <p>Tensor type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224]}]</code> </p> </li> </ul> </li> <li> <p>Image type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input</em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default<em>shape&quot;: [1,224,224,3], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> <li> <p>Image type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}]</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> </ul> <p>Depending on the model format, <code>DataInputConfig</code> requires the following parameters for <code>`ml<em>`eia2</code> &lt;a href=&quot;https://docs.aws.amazon.com/sagemaker/latest/APIReference/API</em>OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice&quot;&gt;OutputConfig:TargetDevice</a>.</p> <ul> <li> <p>For TensorFlow models saved in the SavedModel format, specify the input names from <code>signature<em>def</em>key</code> and the input model shapes for <code>DataInputConfig</code>. Specify the <code>signature<em>def</em>key</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a> if the model does not use TensorFlow&#39;s default signature def key. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;inputs&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;signature<em>def</em>key&quot;: &quot;serving<em>custom&quot;}</code> </p> </li> </ul> </li> <li> <p>For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in <code>DataInputConfig</code> and the output tensor names for <code>output</em>names</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a>. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>tensor:0&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;output</em>names&quot;: [&quot;output_tensor:0&quot;]}</code> </p> </li> </ul> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          +      +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:7562
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...ot;https://docs.aws.amazon.com/sagemaker/latest/APIReference/API</em>OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice&quot;&...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `a`
[INFO] [stdout]     --> src/generated.rs:7419:7660
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...Type-OutputConfig-TargetDevice&quot;&gt;OutputConfig:TargetDevice</a>.</p> <ul> <li> <p>For TensorFlow models saved in the SavedModel ...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:8389
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...tions&quot;: {&quot;signature<em>def</em>key&quot;: &quot;serving<em>custom&quot;}</code> </p> </li> </ul> </li> <li> <p>For TensorFlo...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 7419 |     /// <p><p>Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are <a>InputConfig$Framework</a> specific. </p> <ul> <li> <p> <code>TensorFlow</code>: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>KERAS</code>: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, <code>DataInputConfig</code> should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input</em>1&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>MXNET/ONNX/DARKNET</code>: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>PyTorch</code>: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.</p> <ul> <li> <p>Examples for one input in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Example for one input in list format: <code>[[1,3,224,224]]</code> </p> </li> <li> <p>Examples for two inputs in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]} </code> </p> </li> </ul> </li> <li> <p>Example for two inputs in list format: <code>[[1,3,224,224], [1,3,224,224]]</code> </p> </li> </ul> </li> <li> <p> <code>XGBOOST</code>: input data name and shape are not needed.</p> </li> </ul> <p> <code>DataInputConfig</code> supports the following parameters for <code>CoreML</code> <a>OutputConfig$TargetDevice</a> (ML Model format):</p> <ul> <li> <p> <code>shape</code>: Input shape, for example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [1,224,224,3]}}</code>. In addition to static input shapes, CoreML converter supports Flexible input shapes:</p> <ul> <li> <p>Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: <code>{&quot;input</em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3]}}</code> </p> </li> <li> <p>Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [[1, 224, 224, 3], [1, 160, 160, 3]]}}</code> </p> </li> </ul> </li> <li> <p> <code>default</em>shape</code>: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3], &quot;default</em>shape&quot;: [1, 224, 224, 3]}}</code> </p> </li> <li> <p> <code>type</code>: Input type. Allowed values: <code>Image</code> and <code>Tensor</code>. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as <code>bias</code> and <code>scale</code>.</p> </li> <li> <p> <code>bias</code>: If the input type is an Image, you need to provide the bias vector.</p> </li> <li> <p> <code>scale</code>: If the input type is an Image, you need to provide a scale factor.</p> </li> </ul> <p>CoreML <code>ClassifierConfig</code> parameters can be specified using <a>OutputConfig$CompilerOptions</a>. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:</p> <ul> <li> <p>Tensor type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default</em>shape&quot;: [1,224,224,3]}}</code> </p> </li> </ul> </li> <li> <p>Tensor type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224]}]</code> </p> </li> </ul> </li> <li> <p>Image type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input</em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default<em>shape&quot;: [1,224,224,3], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> <li> <p>Image type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}]</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> </ul> <p>Depending on the model format, <code>DataInputConfig</code> requires the following parameters for <code>ml<em>eia2</code> &lt;a href=&quot;https://docs.aws.amazon.com/sagemaker/latest/APIReference/API</em>OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice&quot;&gt;OutputConfig:TargetDevice</a>.</p> <ul> <li> <p>For TensorFlow models saved in the SavedModel format, specify the input names from <code>signature<em>def</em>key</code> and the input model shapes for <code>DataInputConfig</code>. Specify the <code>signature<em>def</em>key</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a> if the model does not use TensorFlow&#39;s default signature def key. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;inputs&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;signature<em>def</em>key&quot;: &quot;`serving<em>`custom&quot;}</code> </p> </li> </ul> </li> <li> <p>For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in <code>DataInputConfig</code> and the output tensor names for <code>output</em>names</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a>. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>tensor:0&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;output</em>names&quot;: [&quot;output_tensor:0&quot;]}</code> </p> </li> </ul> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              +           +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:8610
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ...aInputConfig</code> and the output tensor names for <code>output</em>names</code> in <a href="https://docs.aws.amazon.com/sagemaker/la...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:8892
[INFO] [stdout]      |
[INFO] [stdout] 7419 | .../p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>tensor:0&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <cod...
[INFO] [stdout]      |                                                                     ^^^^
[INFO] [stdout]      |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]      |
[INFO] [stdout] 7419 |     /// <p><p>Specifies the name and shape of the expected data inputs for your trained model with a JSON dictionary form. The data inputs are <a>InputConfig$Framework</a> specific. </p> <ul> <li> <p> <code>TensorFlow</code>: You must specify the name and shape (NHWC format) of the expected data inputs using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input&quot;:[1,1024,1024,3]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data1&quot;: [1,28,28,1], &quot;data2&quot;:[1,28,28,1]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>KERAS</code>: You must specify the name and shape (NCHW format) of expected data inputs using a dictionary format for your trained model. Note that while Keras model artifacts should be uploaded in NHWC (channel-last) format, <code>DataInputConfig</code> should be specified in NCHW (channel-first) format. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input</em>1&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input<em>1&quot;: [1,3,224,224], &quot;input</em>2&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>MXNET/ONNX/DARKNET</code>: You must specify the name and shape (NCHW format) of the expected data inputs in order using a dictionary format for your trained model. The dictionary formats required for the console and CLI are different.</p> <ul> <li> <p>Examples for one input:</p> <ul> <li> <p>If using the console, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;data&quot;:[1,3,1024,1024]}</code> </p> </li> </ul> </li> <li> <p>Examples for two inputs:</p> <ul> <li> <p>If using the console, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]} </code> </p> </li> <li> <p>If using the CLI, <code>{&quot;var1&quot;: [1,1,28,28], &quot;var2&quot;:[1,1,28,28]}</code> </p> </li> </ul> </li> </ul> </li> <li> <p> <code>PyTorch</code>: You can either specify the name and shape (NCHW format) of expected data inputs in order using a dictionary format for your trained model or you can specify the shape only using a list format. The dictionary formats required for the console and CLI are different. The list formats for the console and CLI are the same.</p> <ul> <li> <p>Examples for one input in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224]}</code> </p> </li> </ul> </li> <li> <p>Example for one input in list format: <code>[[1,3,224,224]]</code> </p> </li> <li> <p>Examples for two inputs in dictionary format:</p> <ul> <li> <p>If using the console, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]}</code> </p> </li> <li> <p>If using the CLI, <code>{&quot;input0&quot;:[1,3,224,224], &quot;input1&quot;:[1,3,224,224]} </code> </p> </li> </ul> </li> <li> <p>Example for two inputs in list format: <code>[[1,3,224,224], [1,3,224,224]]</code> </p> </li> </ul> </li> <li> <p> <code>XGBOOST</code>: input data name and shape are not needed.</p> </li> </ul> <p> <code>DataInputConfig</code> supports the following parameters for <code>CoreML</code> <a>OutputConfig$TargetDevice</a> (ML Model format):</p> <ul> <li> <p> <code>shape</code>: Input shape, for example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [1,224,224,3]}}</code>. In addition to static input shapes, CoreML converter supports Flexible input shapes:</p> <ul> <li> <p>Range Dimension. You can use the Range Dimension feature if you know the input shape will be within some specific interval in that dimension, for example: <code>{&quot;input</em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3]}}</code> </p> </li> <li> <p>Enumerated shapes. Sometimes, the models are trained to work only on a select set of inputs. You can enumerate all supported input shapes, for example: <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [[1, 224, 224, 3], [1, 160, 160, 3]]}}</code> </p> </li> </ul> </li> <li> <p> <code>default</em>shape</code>: Default input shape. You can set a default shape during conversion for both Range Dimension and Enumerated Shapes. For example <code>{&quot;input<em>1&quot;: {&quot;shape&quot;: [&quot;1..10&quot;, 224, 224, 3], &quot;default</em>shape&quot;: [1, 224, 224, 3]}}</code> </p> </li> <li> <p> <code>type</code>: Input type. Allowed values: <code>Image</code> and <code>Tensor</code>. By default, the converter generates an ML Model with inputs of type Tensor (MultiArray). User can set input type to be Image. Image input type requires additional input parameters such as <code>bias</code> and <code>scale</code>.</p> </li> <li> <p> <code>bias</code>: If the input type is an Image, you need to provide the bias vector.</p> </li> <li> <p> <code>scale</code>: If the input type is an Image, you need to provide a scale factor.</p> </li> </ul> <p>CoreML <code>ClassifierConfig</code> parameters can be specified using <a>OutputConfig$CompilerOptions</a>. CoreML converter supports Tensorflow and PyTorch models. CoreML conversion examples:</p> <ul> <li> <p>Tensor type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input<em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default</em>shape&quot;: [1,224,224,3]}}</code> </p> </li> </ul> </li> <li> <p>Tensor type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224]}]</code> </p> </li> </ul> </li> <li> <p>Image type input:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;input</em>1&quot;: {&quot;shape&quot;: [[1,224,224,3], [1,160,160,3]], &quot;default<em>shape&quot;: [1,224,224,3], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> <li> <p>Image type input without input name (PyTorch):</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: [{&quot;shape&quot;: [[1,3,224,224], [1,3,160,160]], &quot;default<em>shape&quot;: [1,3,224,224], &quot;type&quot;: &quot;Image&quot;, &quot;bias&quot;: [-1,-1,-1], &quot;scale&quot;: 0.007843137255}]</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;class</em>labels&quot;: &quot;imagenet<em>labels</em>1000.txt&quot;}</code> </p> </li> </ul> </li> </ul> <p>Depending on the model format, <code>DataInputConfig</code> requires the following parameters for <code>ml<em>eia2</code> &lt;a href=&quot;https://docs.aws.amazon.com/sagemaker/latest/APIReference/API</em>OutputConfig.html#sagemaker-Type-OutputConfig-TargetDevice&quot;&gt;OutputConfig:TargetDevice</a>.</p> <ul> <li> <p>For TensorFlow models saved in the SavedModel format, specify the input names from <code>signature<em>def</em>key</code> and the input model shapes for <code>DataInputConfig</code>. Specify the <code>signature<em>def</em>key</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a> if the model does not use TensorFlow&#39;s default signature def key. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;inputs&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;signature<em>def</em>key&quot;: &quot;serving<em>custom&quot;}</code> </p> </li> </ul> </li> <li> <p>For TensorFlow models saved as a frozen graph, specify the input tensor names and shapes in <code>DataInputConfig</code> and the output tensor names for <code>output</em>names</code> in <a href="https://docs.aws.amazon.com/sagemaker/latest/APIReference/API_OutputConfig.html#sagemaker-Type-OutputConfig-CompilerOptions"> <code>OutputConfig:CompilerOptions</code> </a>. For example:</p> <ul> <li> <p> <code>&quot;DataInputConfig&quot;: {&quot;`input<em>`tensor:0&quot;: [1, 224, 224, 3]}</code> </p> </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;output</em>names&quot;: [&quot;output_tensor:0&quot;]}</code> </p> </li> </ul> </li> </ul></p>
[INFO] [stdout]      |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       +         +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]     --> src/generated.rs:7419:9005
[INFO] [stdout]      |
[INFO] [stdout] 7419 | ... </li> <li> <p> <code>&quot;CompilerOptions&quot;: {&quot;output</em>names&quot;: [&quot;output_tensor:0&quot;]}</code> </p> </li> </u...
[INFO] [stdout]      |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]      --> src/generated.rs:10388:8
[INFO] [stdout]       |
[INFO] [stdout] 10388 | /// <p><p/></p>
[INFO] [stdout]       |        ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]      --> src/generated.rs:10391:12
[INFO] [stdout]       |
[INFO] [stdout] 10391 |     /// <p><p/></p>
[INFO] [stdout]       |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]      --> src/generated.rs:10395:12
[INFO] [stdout]       |
[INFO] [stdout] 10395 |     /// <p><p/></p>
[INFO] [stdout]       |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]      --> src/generated.rs:10398:12
[INFO] [stdout]       |
[INFO] [stdout] 10398 |     /// <p><p/></p>
[INFO] [stdout]       |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:10689:197
[INFO] [stdout]       |
[INFO] [stdout] 10689 | ...model group is pending being created.</p> </li> <li> <p> <code>IN<em>PROGRESS</code> - The model group is in the process of being crea...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 10689 |     /// <p><p>The status of the model group. This can be one of the following values.</p> <ul> <li> <p> <code>PENDING</code> - The model group is pending being created.</p> </li> <li> <p> <code>`IN<em>`PROGRESS</code> - The model group is in the process of being created.</p> </li> <li> <p> <code>COMPLETED</code> - The model group was successfully created.</p> </li> <li> <p> <code>FAILED</code> - The model group failed.</p> </li> <li> <p> <code>DELETING</code> - The model group is in the process of being deleted.</p> </li> <li> <p> <code>DELETE</em>FAILED</code> - SageMaker failed to delete the model group.</p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                   +      +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:10689:548
[INFO] [stdout]       |
[INFO] [stdout] 10689 | ...in the process of being deleted.</p> </li> <li> <p> <code>DELETE</em>FAILED</code> - SageMaker failed to delete the model group.</p> <...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:413
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...pecifies the data type for the input. When compiling for <code>ml<em>*</code> (except for <code>ml</em>inf</code>) instances using PyT...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 11527 |     /// <p><p>Specifies additional parameters for compiler options in JSON format. The compiler options are <code>TargetPlatform</code> specific. It is required for NVIDIA accelerators and highly recommended for CPU compilations. For any other cases, it is optional to specify <code>CompilerOptions.</code> </p> <ul> <li> <p> <code>DTYPE</code>: Specifies the data type for the input. When compiling for <code>`ml<em>`*</code> (except for <code>ml</em>inf</code>) instances using PyTorch framework, provide the data type (dtype) of the model&#39;s input. <code>&quot;float32&quot;</code> is used if <code>&quot;DTYPE&quot;</code> is not specified. Options for data type are:</p> <ul> <li> <p>float32: Use either <code>&quot;float&quot;</code> or <code>&quot;float32&quot;</code>.</p> </li> <li> <p>int64: Use either <code>&quot;int64&quot;</code> or <code>&quot;long&quot;</code>.</p> </li> </ul> <p> For example, <code>{&quot;dtype&quot; : &quot;float32&quot;}</code>.</p> </li> <li> <p> <code>CPU</code>: Compilation for CPU supports the following compiler options.</p> <ul> <li> <p> <code>mcpu</code>: CPU micro-architecture. For example, <code>{&#39;mcpu&#39;: &#39;skylake-avx512&#39;}</code> </p> </li> <li> <p> <code>mattr</code>: CPU flags. For example, <code>{&#39;mattr&#39;: [&#39;+neon&#39;, &#39;+vfpv4&#39;]}</code> </p> </li> </ul> </li> <li> <p> <code>ARM</code>: Details of ARM CPU compilations.</p> <ul> <li> <p> <code>NEON</code>: NEON is an implementation of the Advanced SIMD extension used in ARMv7 processors.</p> <p>For example, add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to the compiler options if compiling for ARM 32-bit platform with the NEON support.</p> </li> </ul> </li> <li> <p> <code>NVIDIA</code>: Compilation for NVIDIA GPU supports the following compiler options.</p> <ul> <li> <p> <code>gpu<em>code</code>: Specifies the targeted architecture.</p> </li> <li> <p> <code>trt-ver</code>: Specifies the TensorRT versions in x.y.z. format.</p> </li> <li> <p> <code>cuda-ver</code>: Specifies the CUDA version in x.y format.</p> </li> </ul> <p>For example, <code>{&#39;gpu-code&#39;: &#39;sm</em>72&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: &#39;10.1&#39;}</code> </p> </li> <li> <p> <code>ANDROID</code>: Compilation for the Android OS supports the following compiler options:</p> <ul> <li> <p> <code>ANDROID<em>PLATFORM</code>: Specifies the Android API levels. Available levels range from 21 to 29. For example, <code>{&#39;ANDROID</em>PLATFORM&#39;: 28}</code>.</p> </li> <li> <p> <code>mattr</code>: Add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to compiler options if compiling for ARM 32-bit platform with NEON support.</p> </li> </ul> </li> <li> <p> <code>INFERENTIA</code>: Compilation for target ml<em>inf1 uses compiler options passed in as a JSON string. For example, <code>&quot;CompilerOptions&quot;: &quot;&quot;--verbose 1 --num-neuroncores 2 -O2&quot;&quot;</code>. </p> <p>For information about supported compiler options, see <a href="https://github.com/aws/aws-neuron-sdk/blob/master/docs/neuron-cc/command-line-reference.md"> Neuron Compiler CLI</a>. </p> </li> <li> <p> <code>CoreML</code>: Compilation for the CoreML <a>OutputConfig$TargetDevice</a> supports the following compiler options:</p> <ul> <li> <p> <code>class</em>labels</code>: Specifies the classification labels file name inside input tar.gz file. For example, <code>{&quot;class<em>labels&quot;: &quot;imagenet</em>labels<em>1000.txt&quot;}</code>. Labels inside the txt file should be separated by newlines.</p> </li> </ul> </li> <li> <p> <code>EIA</code>: Compilation for the Elastic Inference Accelerator supports the following compiler options:</p> <ul> <li> <p> <code>precision</em>mode</code>: Specifies the precision of compiled artifacts. Supported values are <code>&quot;FP16&quot;</code> and <code>&quot;FP32&quot;</code>. Default is <code>&quot;FP32&quot;</code>.</p> </li> <li> <p> <code>signature<em>def</em>key</code>: Specifies the signature to use for models in SavedModel format. Defaults is TensorFlow&#39;s default signature def key.</p> </li> <li> <p> <code>output<em>names</code>: Specifies a list of output tensor names for models in FrozenGraph format. Set at most one API field, either: <code>signature</em>def<em>key</code> or <code>output</em>names</code>.</p> </li> </ul> <p>For example: <code>{&quot;precision<em>mode&quot;: &quot;FP32&quot;, &quot;output</em>names&quot;: [&quot;output:0&quot;]}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                           +      +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:446
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...ut. When compiling for <code>ml<em>*</code> (except for <code>ml</em>inf</code>) instances using PyTorch framework, provide the data t...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:1837
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...ports the following compiler options.</p> <ul> <li> <p> <code>gpu<em>code</code>: Specifies the targeted architecture.</p> </li> <li> ...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 11527 |     /// <p><p>Specifies additional parameters for compiler options in JSON format. The compiler options are <code>TargetPlatform</code> specific. It is required for NVIDIA accelerators and highly recommended for CPU compilations. For any other cases, it is optional to specify <code>CompilerOptions.</code> </p> <ul> <li> <p> <code>DTYPE</code>: Specifies the data type for the input. When compiling for <code>ml<em>*</code> (except for <code>ml</em>inf</code>) instances using PyTorch framework, provide the data type (dtype) of the model&#39;s input. <code>&quot;float32&quot;</code> is used if <code>&quot;DTYPE&quot;</code> is not specified. Options for data type are:</p> <ul> <li> <p>float32: Use either <code>&quot;float&quot;</code> or <code>&quot;float32&quot;</code>.</p> </li> <li> <p>int64: Use either <code>&quot;int64&quot;</code> or <code>&quot;long&quot;</code>.</p> </li> </ul> <p> For example, <code>{&quot;dtype&quot; : &quot;float32&quot;}</code>.</p> </li> <li> <p> <code>CPU</code>: Compilation for CPU supports the following compiler options.</p> <ul> <li> <p> <code>mcpu</code>: CPU micro-architecture. For example, <code>{&#39;mcpu&#39;: &#39;skylake-avx512&#39;}</code> </p> </li> <li> <p> <code>mattr</code>: CPU flags. For example, <code>{&#39;mattr&#39;: [&#39;+neon&#39;, &#39;+vfpv4&#39;]}</code> </p> </li> </ul> </li> <li> <p> <code>ARM</code>: Details of ARM CPU compilations.</p> <ul> <li> <p> <code>NEON</code>: NEON is an implementation of the Advanced SIMD extension used in ARMv7 processors.</p> <p>For example, add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to the compiler options if compiling for ARM 32-bit platform with the NEON support.</p> </li> </ul> </li> <li> <p> <code>NVIDIA</code>: Compilation for NVIDIA GPU supports the following compiler options.</p> <ul> <li> <p> <code>`gpu<em>`code</code>: Specifies the targeted architecture.</p> </li> <li> <p> <code>trt-ver</code>: Specifies the TensorRT versions in x.y.z. format.</p> </li> <li> <p> <code>cuda-ver</code>: Specifies the CUDA version in x.y format.</p> </li> </ul> <p>For example, <code>{&#39;gpu-code&#39;: &#39;sm</em>72&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: &#39;10.1&#39;}</code> </p> </li> <li> <p> <code>ANDROID</code>: Compilation for the Android OS supports the following compiler options:</p> <ul> <li> <p> <code>ANDROID<em>PLATFORM</code>: Specifies the Android API levels. Available levels range from 21 to 29. For example, <code>{&#39;ANDROID</em>PLATFORM&#39;: 28}</code>.</p> </li> <li> <p> <code>mattr</code>: Add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to compiler options if compiling for ARM 32-bit platform with NEON support.</p> </li> </ul> </li> <li> <p> <code>INFERENTIA</code>: Compilation for target ml<em>inf1 uses compiler options passed in as a JSON string. For example, <code>&quot;CompilerOptions&quot;: &quot;&quot;--verbose 1 --num-neuroncores 2 -O2&quot;&quot;</code>. </p> <p>For information about supported compiler options, see <a href="https://github.com/aws/aws-neuron-sdk/blob/master/docs/neuron-cc/command-line-reference.md"> Neuron Compiler CLI</a>. </p> </li> <li> <p> <code>CoreML</code>: Compilation for the CoreML <a>OutputConfig$TargetDevice</a> supports the following compiler options:</p> <ul> <li> <p> <code>class</em>labels</code>: Specifies the classification labels file name inside input tar.gz file. For example, <code>{&quot;class<em>labels&quot;: &quot;imagenet</em>labels<em>1000.txt&quot;}</code>. Labels inside the txt file should be separated by newlines.</p> </li> </ul> </li> <li> <p> <code>EIA</code>: Compilation for the Elastic Inference Accelerator supports the following compiler options:</p> <ul> <li> <p> <code>precision</em>mode</code>: Specifies the precision of compiled artifacts. Supported values are <code>&quot;FP16&quot;</code> and <code>&quot;FP32&quot;</code>. Default is <code>&quot;FP32&quot;</code>.</p> </li> <li> <p> <code>signature<em>def</em>key</code>: Specifies the signature to use for models in SavedModel format. Defaults is TensorFlow&#39;s default signature def key.</p> </li> <li> <p> <code>output<em>names</code>: Specifies a list of output tensor names for models in FrozenGraph format. Set at most one API field, either: <code>signature</em>def<em>key</code> or <code>output</em>names</code>.</p> </li> </ul> <p>For example: <code>{&quot;precision<em>mode&quot;: &quot;FP32&quot;, &quot;output</em>names&quot;: [&quot;output:0&quot;]}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          +       +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:2132
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...> </li> </ul> <p>For example, <code>{&#39;gpu-code&#39;: &#39;sm</em>72&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: ...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:2370
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...s the following compiler options:</p> <ul> <li> <p> <code>ANDROID<em>PLATFORM</code>: Specifies the Android API levels. Available leve...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 11527 |     /// <p><p>Specifies additional parameters for compiler options in JSON format. The compiler options are <code>TargetPlatform</code> specific. It is required for NVIDIA accelerators and highly recommended for CPU compilations. For any other cases, it is optional to specify <code>CompilerOptions.</code> </p> <ul> <li> <p> <code>DTYPE</code>: Specifies the data type for the input. When compiling for <code>ml<em>*</code> (except for <code>ml</em>inf</code>) instances using PyTorch framework, provide the data type (dtype) of the model&#39;s input. <code>&quot;float32&quot;</code> is used if <code>&quot;DTYPE&quot;</code> is not specified. Options for data type are:</p> <ul> <li> <p>float32: Use either <code>&quot;float&quot;</code> or <code>&quot;float32&quot;</code>.</p> </li> <li> <p>int64: Use either <code>&quot;int64&quot;</code> or <code>&quot;long&quot;</code>.</p> </li> </ul> <p> For example, <code>{&quot;dtype&quot; : &quot;float32&quot;}</code>.</p> </li> <li> <p> <code>CPU</code>: Compilation for CPU supports the following compiler options.</p> <ul> <li> <p> <code>mcpu</code>: CPU micro-architecture. For example, <code>{&#39;mcpu&#39;: &#39;skylake-avx512&#39;}</code> </p> </li> <li> <p> <code>mattr</code>: CPU flags. For example, <code>{&#39;mattr&#39;: [&#39;+neon&#39;, &#39;+vfpv4&#39;]}</code> </p> </li> </ul> </li> <li> <p> <code>ARM</code>: Details of ARM CPU compilations.</p> <ul> <li> <p> <code>NEON</code>: NEON is an implementation of the Advanced SIMD extension used in ARMv7 processors.</p> <p>For example, add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to the compiler options if compiling for ARM 32-bit platform with the NEON support.</p> </li> </ul> </li> <li> <p> <code>NVIDIA</code>: Compilation for NVIDIA GPU supports the following compiler options.</p> <ul> <li> <p> <code>gpu<em>code</code>: Specifies the targeted architecture.</p> </li> <li> <p> <code>trt-ver</code>: Specifies the TensorRT versions in x.y.z. format.</p> </li> <li> <p> <code>cuda-ver</code>: Specifies the CUDA version in x.y format.</p> </li> </ul> <p>For example, <code>{&#39;gpu-code&#39;: &#39;sm</em>72&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: &#39;10.1&#39;}</code> </p> </li> <li> <p> <code>ANDROID</code>: Compilation for the Android OS supports the following compiler options:</p> <ul> <li> <p> <code>`ANDROID<em>`PLATFORM</code>: Specifies the Android API levels. Available levels range from 21 to 29. For example, <code>{&#39;ANDROID</em>PLATFORM&#39;: 28}</code>.</p> </li> <li> <p> <code>mattr</code>: Add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to compiler options if compiling for ARM 32-bit platform with NEON support.</p> </li> </ul> </li> <li> <p> <code>INFERENTIA</code>: Compilation for target ml<em>inf1 uses compiler options passed in as a JSON string. For example, <code>&quot;CompilerOptions&quot;: &quot;&quot;--verbose 1 --num-neuroncores 2 -O2&quot;&quot;</code>. </p> <p>For information about supported compiler options, see <a href="https://github.com/aws/aws-neuron-sdk/blob/master/docs/neuron-cc/command-line-reference.md"> Neuron Compiler CLI</a>. </p> </li> <li> <p> <code>CoreML</code>: Compilation for the CoreML <a>OutputConfig$TargetDevice</a> supports the following compiler options:</p> <ul> <li> <p> <code>class</em>labels</code>: Specifies the classification labels file name inside input tar.gz file. For example, <code>{&quot;class<em>labels&quot;: &quot;imagenet</em>labels<em>1000.txt&quot;}</code>. Labels inside the txt file should be separated by newlines.</p> </li> </ul> </li> <li> <p> <code>EIA</code>: Compilation for the Elastic Inference Accelerator supports the following compiler options:</p> <ul> <li> <p> <code>precision</em>mode</code>: Specifies the precision of compiled artifacts. Supported values are <code>&quot;FP16&quot;</code> and <code>&quot;FP32&quot;</code>. Default is <code>&quot;FP32&quot;</code>.</p> </li> <li> <p> <code>signature<em>def</em>key</code>: Specifies the signature to use for models in SavedModel format. Defaults is TensorFlow&#39;s default signature def key.</p> </li> <li> <p> <code>output<em>names</code>: Specifies a list of output tensor names for models in FrozenGraph format. Set at most one API field, either: <code>signature</em>def<em>key</code> or <code>output</em>names</code>.</p> </li> </ul> <p>For example: <code>{&quot;precision<em>mode&quot;: &quot;FP32&quot;, &quot;output</em>names&quot;: [&quot;output:0&quot;]}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           +           +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:2495
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...ble levels range from 21 to 29. For example, <code>{&#39;ANDROID</em>PLATFORM&#39;: 28}</code>.</p> </li> <li> <p> <code>mattr</code>:...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:2777
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...</li> <li> <p> <code>INFERENTIA</code>: Compilation for target ml<em>inf1 uses compiler options passed in as a JSON string. For exampl...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 11527 |     /// <p><p>Specifies additional parameters for compiler options in JSON format. The compiler options are <code>TargetPlatform</code> specific. It is required for NVIDIA accelerators and highly recommended for CPU compilations. For any other cases, it is optional to specify <code>CompilerOptions.</code> </p> <ul> <li> <p> <code>DTYPE</code>: Specifies the data type for the input. When compiling for <code>ml<em>*</code> (except for <code>ml</em>inf</code>) instances using PyTorch framework, provide the data type (dtype) of the model&#39;s input. <code>&quot;float32&quot;</code> is used if <code>&quot;DTYPE&quot;</code> is not specified. Options for data type are:</p> <ul> <li> <p>float32: Use either <code>&quot;float&quot;</code> or <code>&quot;float32&quot;</code>.</p> </li> <li> <p>int64: Use either <code>&quot;int64&quot;</code> or <code>&quot;long&quot;</code>.</p> </li> </ul> <p> For example, <code>{&quot;dtype&quot; : &quot;float32&quot;}</code>.</p> </li> <li> <p> <code>CPU</code>: Compilation for CPU supports the following compiler options.</p> <ul> <li> <p> <code>mcpu</code>: CPU micro-architecture. For example, <code>{&#39;mcpu&#39;: &#39;skylake-avx512&#39;}</code> </p> </li> <li> <p> <code>mattr</code>: CPU flags. For example, <code>{&#39;mattr&#39;: [&#39;+neon&#39;, &#39;+vfpv4&#39;]}</code> </p> </li> </ul> </li> <li> <p> <code>ARM</code>: Details of ARM CPU compilations.</p> <ul> <li> <p> <code>NEON</code>: NEON is an implementation of the Advanced SIMD extension used in ARMv7 processors.</p> <p>For example, add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to the compiler options if compiling for ARM 32-bit platform with the NEON support.</p> </li> </ul> </li> <li> <p> <code>NVIDIA</code>: Compilation for NVIDIA GPU supports the following compiler options.</p> <ul> <li> <p> <code>gpu<em>code</code>: Specifies the targeted architecture.</p> </li> <li> <p> <code>trt-ver</code>: Specifies the TensorRT versions in x.y.z. format.</p> </li> <li> <p> <code>cuda-ver</code>: Specifies the CUDA version in x.y format.</p> </li> </ul> <p>For example, <code>{&#39;gpu-code&#39;: &#39;sm</em>72&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: &#39;10.1&#39;}</code> </p> </li> <li> <p> <code>ANDROID</code>: Compilation for the Android OS supports the following compiler options:</p> <ul> <li> <p> <code>ANDROID<em>PLATFORM</code>: Specifies the Android API levels. Available levels range from 21 to 29. For example, <code>{&#39;ANDROID</em>PLATFORM&#39;: 28}</code>.</p> </li> <li> <p> <code>mattr</code>: Add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to compiler options if compiling for ARM 32-bit platform with NEON support.</p> </li> </ul> </li> <li> <p> <code>INFERENTIA</code>: Compilation for target `ml<em>`inf1 uses compiler options passed in as a JSON string. For example, <code>&quot;CompilerOptions&quot;: &quot;&quot;--verbose 1 --num-neuroncores 2 -O2&quot;&quot;</code>. </p> <p>For information about supported compiler options, see <a href="https://github.com/aws/aws-neuron-sdk/blob/master/docs/neuron-cc/command-line-reference.md"> Neuron Compiler CLI</a>. </p> </li> <li> <p> <code>CoreML</code>: Compilation for the CoreML <a>OutputConfig$TargetDevice</a> supports the following compiler options:</p> <ul> <li> <p> <code>class</em>labels</code>: Specifies the classification labels file name inside input tar.gz file. For example, <code>{&quot;class<em>labels&quot;: &quot;imagenet</em>labels<em>1000.txt&quot;}</code>. Labels inside the txt file should be separated by newlines.</p> </li> </ul> </li> <li> <p> <code>EIA</code>: Compilation for the Elastic Inference Accelerator supports the following compiler options:</p> <ul> <li> <p> <code>precision</em>mode</code>: Specifies the precision of compiled artifacts. Supported values are <code>&quot;FP16&quot;</code> and <code>&quot;FP32&quot;</code>. Default is <code>&quot;FP32&quot;</code>.</p> </li> <li> <p> <code>signature<em>def</em>key</code>: Specifies the signature to use for models in SavedModel format. Defaults is TensorFlow&#39;s default signature def key.</p> </li> <li> <p> <code>output<em>names</code>: Specifies a list of output tensor names for models in FrozenGraph format. Set at most one API field, either: <code>signature</em>def<em>key</code> or <code>output</em>names</code>.</p> </li> </ul> <p>For example: <code>{&quot;precision<em>mode&quot;: &quot;FP32&quot;, &quot;output</em>names&quot;: [&quot;output:0&quot;]}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       +      +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:3312
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...ts the following compiler options:</p> <ul> <li> <p> <code>class</em>labels</code>: Specifies the classification labels file name insi...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:3478
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...le, <code>{&quot;class<em>labels&quot;: &quot;imagenet</em>labels<em>1000.txt&quot;}</code>. Labels inside the txt file should be sepa...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 11527 |     /// <p><p>Specifies additional parameters for compiler options in JSON format. The compiler options are <code>TargetPlatform</code> specific. It is required for NVIDIA accelerators and highly recommended for CPU compilations. For any other cases, it is optional to specify <code>CompilerOptions.</code> </p> <ul> <li> <p> <code>DTYPE</code>: Specifies the data type for the input. When compiling for <code>ml<em>*</code> (except for <code>ml</em>inf</code>) instances using PyTorch framework, provide the data type (dtype) of the model&#39;s input. <code>&quot;float32&quot;</code> is used if <code>&quot;DTYPE&quot;</code> is not specified. Options for data type are:</p> <ul> <li> <p>float32: Use either <code>&quot;float&quot;</code> or <code>&quot;float32&quot;</code>.</p> </li> <li> <p>int64: Use either <code>&quot;int64&quot;</code> or <code>&quot;long&quot;</code>.</p> </li> </ul> <p> For example, <code>{&quot;dtype&quot; : &quot;float32&quot;}</code>.</p> </li> <li> <p> <code>CPU</code>: Compilation for CPU supports the following compiler options.</p> <ul> <li> <p> <code>mcpu</code>: CPU micro-architecture. For example, <code>{&#39;mcpu&#39;: &#39;skylake-avx512&#39;}</code> </p> </li> <li> <p> <code>mattr</code>: CPU flags. For example, <code>{&#39;mattr&#39;: [&#39;+neon&#39;, &#39;+vfpv4&#39;]}</code> </p> </li> </ul> </li> <li> <p> <code>ARM</code>: Details of ARM CPU compilations.</p> <ul> <li> <p> <code>NEON</code>: NEON is an implementation of the Advanced SIMD extension used in ARMv7 processors.</p> <p>For example, add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to the compiler options if compiling for ARM 32-bit platform with the NEON support.</p> </li> </ul> </li> <li> <p> <code>NVIDIA</code>: Compilation for NVIDIA GPU supports the following compiler options.</p> <ul> <li> <p> <code>gpu<em>code</code>: Specifies the targeted architecture.</p> </li> <li> <p> <code>trt-ver</code>: Specifies the TensorRT versions in x.y.z. format.</p> </li> <li> <p> <code>cuda-ver</code>: Specifies the CUDA version in x.y format.</p> </li> </ul> <p>For example, <code>{&#39;gpu-code&#39;: &#39;sm</em>72&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: &#39;10.1&#39;}</code> </p> </li> <li> <p> <code>ANDROID</code>: Compilation for the Android OS supports the following compiler options:</p> <ul> <li> <p> <code>ANDROID<em>PLATFORM</code>: Specifies the Android API levels. Available levels range from 21 to 29. For example, <code>{&#39;ANDROID</em>PLATFORM&#39;: 28}</code>.</p> </li> <li> <p> <code>mattr</code>: Add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to compiler options if compiling for ARM 32-bit platform with NEON support.</p> </li> </ul> </li> <li> <p> <code>INFERENTIA</code>: Compilation for target ml<em>inf1 uses compiler options passed in as a JSON string. For example, <code>&quot;CompilerOptions&quot;: &quot;&quot;--verbose 1 --num-neuroncores 2 -O2&quot;&quot;</code>. </p> <p>For information about supported compiler options, see <a href="https://github.com/aws/aws-neuron-sdk/blob/master/docs/neuron-cc/command-line-reference.md"> Neuron Compiler CLI</a>. </p> </li> <li> <p> <code>CoreML</code>: Compilation for the CoreML <a>OutputConfig$TargetDevice</a> supports the following compiler options:</p> <ul> <li> <p> <code>class</em>labels</code>: Specifies the classification labels file name inside input tar.gz file. For example, <code>{&quot;class<em>labels&quot;: &quot;imagenet</em>`labels<em>`1000.txt&quot;}</code>. Labels inside the txt file should be separated by newlines.</p> </li> </ul> </li> <li> <p> <code>EIA</code>: Compilation for the Elastic Inference Accelerator supports the following compiler options:</p> <ul> <li> <p> <code>precision</em>mode</code>: Specifies the precision of compiled artifacts. Supported values are <code>&quot;FP16&quot;</code> and <code>&quot;FP32&quot;</code>. Default is <code>&quot;FP32&quot;</code>.</p> </li> <li> <p> <code>signature<em>def</em>key</code>: Specifies the signature to use for models in SavedModel format. Defaults is TensorFlow&#39;s default signature def key.</p> </li> <li> <p> <code>output<em>names</code>: Specifies a list of output tensor names for models in FrozenGraph format. Set at most one API field, either: <code>signature</em>def<em>key</code> or <code>output</em>names</code>.</p> </li> </ul> <p>For example: <code>{&quot;precision<em>mode&quot;: &quot;FP32&quot;, &quot;output</em>names&quot;: [&quot;output:0&quot;]}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                +          +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:3739
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...he following compiler options:</p> <ul> <li> <p> <code>precision</em>mode</code>: Specifies the precision of compiled artifacts. Suppo...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:4141
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...&#39;s default signature def key.</p> </li> <li> <p> <code>output<em>names</code>: Specifies a list of output tensor names for models ...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 11527 |     /// <p><p>Specifies additional parameters for compiler options in JSON format. The compiler options are <code>TargetPlatform</code> specific. It is required for NVIDIA accelerators and highly recommended for CPU compilations. For any other cases, it is optional to specify <code>CompilerOptions.</code> </p> <ul> <li> <p> <code>DTYPE</code>: Specifies the data type for the input. When compiling for <code>ml<em>*</code> (except for <code>ml</em>inf</code>) instances using PyTorch framework, provide the data type (dtype) of the model&#39;s input. <code>&quot;float32&quot;</code> is used if <code>&quot;DTYPE&quot;</code> is not specified. Options for data type are:</p> <ul> <li> <p>float32: Use either <code>&quot;float&quot;</code> or <code>&quot;float32&quot;</code>.</p> </li> <li> <p>int64: Use either <code>&quot;int64&quot;</code> or <code>&quot;long&quot;</code>.</p> </li> </ul> <p> For example, <code>{&quot;dtype&quot; : &quot;float32&quot;}</code>.</p> </li> <li> <p> <code>CPU</code>: Compilation for CPU supports the following compiler options.</p> <ul> <li> <p> <code>mcpu</code>: CPU micro-architecture. For example, <code>{&#39;mcpu&#39;: &#39;skylake-avx512&#39;}</code> </p> </li> <li> <p> <code>mattr</code>: CPU flags. For example, <code>{&#39;mattr&#39;: [&#39;+neon&#39;, &#39;+vfpv4&#39;]}</code> </p> </li> </ul> </li> <li> <p> <code>ARM</code>: Details of ARM CPU compilations.</p> <ul> <li> <p> <code>NEON</code>: NEON is an implementation of the Advanced SIMD extension used in ARMv7 processors.</p> <p>For example, add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to the compiler options if compiling for ARM 32-bit platform with the NEON support.</p> </li> </ul> </li> <li> <p> <code>NVIDIA</code>: Compilation for NVIDIA GPU supports the following compiler options.</p> <ul> <li> <p> <code>gpu<em>code</code>: Specifies the targeted architecture.</p> </li> <li> <p> <code>trt-ver</code>: Specifies the TensorRT versions in x.y.z. format.</p> </li> <li> <p> <code>cuda-ver</code>: Specifies the CUDA version in x.y format.</p> </li> </ul> <p>For example, <code>{&#39;gpu-code&#39;: &#39;sm</em>72&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: &#39;10.1&#39;}</code> </p> </li> <li> <p> <code>ANDROID</code>: Compilation for the Android OS supports the following compiler options:</p> <ul> <li> <p> <code>ANDROID<em>PLATFORM</code>: Specifies the Android API levels. Available levels range from 21 to 29. For example, <code>{&#39;ANDROID</em>PLATFORM&#39;: 28}</code>.</p> </li> <li> <p> <code>mattr</code>: Add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to compiler options if compiling for ARM 32-bit platform with NEON support.</p> </li> </ul> </li> <li> <p> <code>INFERENTIA</code>: Compilation for target ml<em>inf1 uses compiler options passed in as a JSON string. For example, <code>&quot;CompilerOptions&quot;: &quot;&quot;--verbose 1 --num-neuroncores 2 -O2&quot;&quot;</code>. </p> <p>For information about supported compiler options, see <a href="https://github.com/aws/aws-neuron-sdk/blob/master/docs/neuron-cc/command-line-reference.md"> Neuron Compiler CLI</a>. </p> </li> <li> <p> <code>CoreML</code>: Compilation for the CoreML <a>OutputConfig$TargetDevice</a> supports the following compiler options:</p> <ul> <li> <p> <code>class</em>labels</code>: Specifies the classification labels file name inside input tar.gz file. For example, <code>{&quot;class<em>labels&quot;: &quot;imagenet</em>labels<em>1000.txt&quot;}</code>. Labels inside the txt file should be separated by newlines.</p> </li> </ul> </li> <li> <p> <code>EIA</code>: Compilation for the Elastic Inference Accelerator supports the following compiler options:</p> <ul> <li> <p> <code>precision</em>mode</code>: Specifies the precision of compiled artifacts. Supported values are <code>&quot;FP16&quot;</code> and <code>&quot;FP32&quot;</code>. Default is <code>&quot;FP32&quot;</code>.</p> </li> <li> <p> <code>signature<em>def</em>key</code>: Specifies the signature to use for models in SavedModel format. Defaults is TensorFlow&#39;s default signature def key.</p> </li> <li> <p> <code>`output<em>`names</code>: Specifies a list of output tensor names for models in FrozenGraph format. Set at most one API field, either: <code>signature</em>def<em>key</code> or <code>output</em>names</code>.</p> </li> </ul> <p>For example: <code>{&quot;precision<em>mode&quot;: &quot;FP32&quot;, &quot;output</em>names&quot;: [&quot;output:0&quot;]}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                       +          +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:4283
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...Graph format. Set at most one API field, either: <code>signature</em>def<em>key</code> or <code>output</em>names</code>.</p> </li> </u...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:4291
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...ormat. Set at most one API field, either: <code>signature</em>def<em>key</code> or <code>output</em>names</code>.</p> </li> </ul> <p>F...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 11527 |     /// <p><p>Specifies additional parameters for compiler options in JSON format. The compiler options are <code>TargetPlatform</code> specific. It is required for NVIDIA accelerators and highly recommended for CPU compilations. For any other cases, it is optional to specify <code>CompilerOptions.</code> </p> <ul> <li> <p> <code>DTYPE</code>: Specifies the data type for the input. When compiling for <code>ml<em>*</code> (except for <code>ml</em>inf</code>) instances using PyTorch framework, provide the data type (dtype) of the model&#39;s input. <code>&quot;float32&quot;</code> is used if <code>&quot;DTYPE&quot;</code> is not specified. Options for data type are:</p> <ul> <li> <p>float32: Use either <code>&quot;float&quot;</code> or <code>&quot;float32&quot;</code>.</p> </li> <li> <p>int64: Use either <code>&quot;int64&quot;</code> or <code>&quot;long&quot;</code>.</p> </li> </ul> <p> For example, <code>{&quot;dtype&quot; : &quot;float32&quot;}</code>.</p> </li> <li> <p> <code>CPU</code>: Compilation for CPU supports the following compiler options.</p> <ul> <li> <p> <code>mcpu</code>: CPU micro-architecture. For example, <code>{&#39;mcpu&#39;: &#39;skylake-avx512&#39;}</code> </p> </li> <li> <p> <code>mattr</code>: CPU flags. For example, <code>{&#39;mattr&#39;: [&#39;+neon&#39;, &#39;+vfpv4&#39;]}</code> </p> </li> </ul> </li> <li> <p> <code>ARM</code>: Details of ARM CPU compilations.</p> <ul> <li> <p> <code>NEON</code>: NEON is an implementation of the Advanced SIMD extension used in ARMv7 processors.</p> <p>For example, add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to the compiler options if compiling for ARM 32-bit platform with the NEON support.</p> </li> </ul> </li> <li> <p> <code>NVIDIA</code>: Compilation for NVIDIA GPU supports the following compiler options.</p> <ul> <li> <p> <code>gpu<em>code</code>: Specifies the targeted architecture.</p> </li> <li> <p> <code>trt-ver</code>: Specifies the TensorRT versions in x.y.z. format.</p> </li> <li> <p> <code>cuda-ver</code>: Specifies the CUDA version in x.y format.</p> </li> </ul> <p>For example, <code>{&#39;gpu-code&#39;: &#39;sm</em>72&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: &#39;10.1&#39;}</code> </p> </li> <li> <p> <code>ANDROID</code>: Compilation for the Android OS supports the following compiler options:</p> <ul> <li> <p> <code>ANDROID<em>PLATFORM</code>: Specifies the Android API levels. Available levels range from 21 to 29. For example, <code>{&#39;ANDROID</em>PLATFORM&#39;: 28}</code>.</p> </li> <li> <p> <code>mattr</code>: Add <code>{&#39;mattr&#39;: [&#39;+neon&#39;]}</code> to compiler options if compiling for ARM 32-bit platform with NEON support.</p> </li> </ul> </li> <li> <p> <code>INFERENTIA</code>: Compilation for target ml<em>inf1 uses compiler options passed in as a JSON string. For example, <code>&quot;CompilerOptions&quot;: &quot;&quot;--verbose 1 --num-neuroncores 2 -O2&quot;&quot;</code>. </p> <p>For information about supported compiler options, see <a href="https://github.com/aws/aws-neuron-sdk/blob/master/docs/neuron-cc/command-line-reference.md"> Neuron Compiler CLI</a>. </p> </li> <li> <p> <code>CoreML</code>: Compilation for the CoreML <a>OutputConfig$TargetDevice</a> supports the following compiler options:</p> <ul> <li> <p> <code>class</em>labels</code>: Specifies the classification labels file name inside input tar.gz file. For example, <code>{&quot;class<em>labels&quot;: &quot;imagenet</em>labels<em>1000.txt&quot;}</code>. Labels inside the txt file should be separated by newlines.</p> </li> </ul> </li> <li> <p> <code>EIA</code>: Compilation for the Elastic Inference Accelerator supports the following compiler options:</p> <ul> <li> <p> <code>precision</em>mode</code>: Specifies the precision of compiled artifacts. Supported values are <code>&quot;FP16&quot;</code> and <code>&quot;FP32&quot;</code>. Default is <code>&quot;FP32&quot;</code>.</p> </li> <li> <p> <code>signature<em>def</em>key</code>: Specifies the signature to use for models in SavedModel format. Defaults is TensorFlow&#39;s default signature def key.</p> </li> <li> <p> <code>output<em>names</code>: Specifies a list of output tensor names for models in FrozenGraph format. Set at most one API field, either: <code>signature</em>`def<em>`key</code> or <code>output</em>names</code>.</p> </li> </ul> <p>For example: <code>{&quot;precision<em>mode&quot;: &quot;FP32&quot;, &quot;output</em>names&quot;: [&quot;output:0&quot;]}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                +       +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11527:4321
[INFO] [stdout]       |
[INFO] [stdout] 11527 | ...d, either: <code>signature</em>def<em>key</code> or <code>output</em>names</code>.</p> </li> </ul> <p>For example: <code>{&quot;precis...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11542:498
[INFO] [stdout]       |
[INFO] [stdout] 11542 | ...: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;ARM<em>EABIHF&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 11542 |     /// <p><p>Contains information about a target platform that you want your model to run on, such as OS, architecture, and accelerators. It is an alternative of <code>TargetDevice</code>.</p> <p>The following examples show how to configure the <code>TargetPlatform</code> and <code>CompilerOptions</code> JSON strings for popular target platforms: </p> <ul> <li> <p>Raspberry Pi 3 Model B+</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;`ARM<em>`EABIHF&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;mattr&#39;: [&#39;+neon&#39;]}</code> </p> </li> <li> <p>Jetson TX2</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;ARM64&quot;, &quot;Accelerator&quot;: &quot;NVIDIA&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;gpu-code&#39;: &#39;sm</em>62&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: &#39;10.0&#39;}</code> </p> </li> <li> <p>EC2 m5.2xlarge instance OS</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;X86<em>64&quot;, &quot;Accelerator&quot;: &quot;NVIDIA&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;mcpu&#39;: &#39;skylake-avx512&#39;}</code> </p> </li> <li> <p>RK3399</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;ARM64&quot;, &quot;Accelerator&quot;: &quot;MALI&quot;}</code> </p> </li> <li> <p>ARMv7 phone (CPU)</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;ANDROID&quot;, &quot;Arch&quot;: &quot;ARM</em>EABI&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;ANDROID<em>PLATFORM&#39;: 25, &#39;mattr&#39;: [&#39;+neon&#39;]}</code> </p> </li> <li> <p>ARMv8 phone (CPU)</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;ANDROID&quot;, &quot;Arch&quot;: &quot;ARM64&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;ANDROID</em>PLATFORM&#39;: 29}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               +       +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11542:884
[INFO] [stdout]       |
[INFO] [stdout] 11542 | ...<code> &quot;CompilerOptions&quot;: {&#39;gpu-code&#39;: &#39;sm</em>62&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: ...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11542:1128
[INFO] [stdout]       |
[INFO] [stdout] 11542 | ...: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;X86<em>64&quot;, &quot;Accelerator&quot;: &quot;NVIDIA&quot;},</code> </...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 11542 |     /// <p><p>Contains information about a target platform that you want your model to run on, such as OS, architecture, and accelerators. It is an alternative of <code>TargetDevice</code>.</p> <p>The following examples show how to configure the <code>TargetPlatform</code> and <code>CompilerOptions</code> JSON strings for popular target platforms: </p> <ul> <li> <p>Raspberry Pi 3 Model B+</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;ARM<em>EABIHF&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;mattr&#39;: [&#39;+neon&#39;]}</code> </p> </li> <li> <p>Jetson TX2</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;ARM64&quot;, &quot;Accelerator&quot;: &quot;NVIDIA&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;gpu-code&#39;: &#39;sm</em>62&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: &#39;10.0&#39;}</code> </p> </li> <li> <p>EC2 m5.2xlarge instance OS</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;`X86<em>`64&quot;, &quot;Accelerator&quot;: &quot;NVIDIA&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;mcpu&#39;: &#39;skylake-avx512&#39;}</code> </p> </li> <li> <p>RK3399</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;ARM64&quot;, &quot;Accelerator&quot;: &quot;MALI&quot;}</code> </p> </li> <li> <p>ARMv7 phone (CPU)</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;ANDROID&quot;, &quot;Arch&quot;: &quot;ARM</em>EABI&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;ANDROID<em>PLATFORM&#39;: 25, &#39;mattr&#39;: [&#39;+neon&#39;]}</code> </p> </li> <li> <p>ARMv8 phone (CPU)</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;ANDROID&quot;, &quot;Arch&quot;: &quot;ARM64&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;ANDROID</em>PLATFORM&#39;: 29}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     +       +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11542:1625
[INFO] [stdout]       |
[INFO] [stdout] 11542 | ...&quot;Os&quot;: &quot;ANDROID&quot;, &quot;Arch&quot;: &quot;ARM</em>EABI&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: ...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11542:1708
[INFO] [stdout]       |
[INFO] [stdout] 11542 | .../code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;ANDROID<em>PLATFORM&#39;: 25, &#39;mattr&#39;: [&#39;+neon&#39;]}</code> </p...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 11542 |     /// <p><p>Contains information about a target platform that you want your model to run on, such as OS, architecture, and accelerators. It is an alternative of <code>TargetDevice</code>.</p> <p>The following examples show how to configure the <code>TargetPlatform</code> and <code>CompilerOptions</code> JSON strings for popular target platforms: </p> <ul> <li> <p>Raspberry Pi 3 Model B+</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;ARM<em>EABIHF&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;mattr&#39;: [&#39;+neon&#39;]}</code> </p> </li> <li> <p>Jetson TX2</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;ARM64&quot;, &quot;Accelerator&quot;: &quot;NVIDIA&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;gpu-code&#39;: &#39;sm</em>62&#39;, &#39;trt-ver&#39;: &#39;6.0.1&#39;, &#39;cuda-ver&#39;: &#39;10.0&#39;}</code> </p> </li> <li> <p>EC2 m5.2xlarge instance OS</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;X86<em>64&quot;, &quot;Accelerator&quot;: &quot;NVIDIA&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;mcpu&#39;: &#39;skylake-avx512&#39;}</code> </p> </li> <li> <p>RK3399</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;LINUX&quot;, &quot;Arch&quot;: &quot;ARM64&quot;, &quot;Accelerator&quot;: &quot;MALI&quot;}</code> </p> </li> <li> <p>ARMv7 phone (CPU)</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;ANDROID&quot;, &quot;Arch&quot;: &quot;ARM</em>EABI&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;`ANDROID<em>`PLATFORM&#39;: 25, &#39;mattr&#39;: [&#39;+neon&#39;]}</code> </p> </li> <li> <p>ARMv8 phone (CPU)</p> <p> <code>&quot;TargetPlatform&quot;: {&quot;Os&quot;: &quot;ANDROID&quot;, &quot;Arch&quot;: &quot;ARM64&quot;},</code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;ANDROID</em>PLATFORM&#39;: 29}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                     +           +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:11542:1994
[INFO] [stdout]       |
[INFO] [stdout] 11542 | ...code> </p> <p> <code> &quot;CompilerOptions&quot;: {&#39;ANDROID</em>PLATFORM&#39;: 29}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:12610:916
[INFO] [stdout]       |
[INFO] [stdout] 12610 | ...format: </p> <p> <code>[ {&quot;prefix&quot;: &quot;s3://customer<em>bucket/some/prefix/&quot;},</code> </p> <p> <code> &quot;relative...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 12610 |     /// <p><p>Depending on the value specified for the <code>S3DataType</code>, identifies either a key name prefix or a manifest. For example: </p> <ul> <li> <p> A key name prefix might look like this: <code>s3://bucketname/exampleprefix</code> </p> </li> <li> <p> A manifest might look like this: <code>s3://bucketname/example.manifest</code> </p> <p> A manifest is an S3 object which is a JSON file consisting of an array of elements. The first element is a prefix which is followed by one or more suffixes. SageMaker appends the suffix elements to the prefix to get a full set of <code>S3Uri</code>. Note that the prefix must be a valid non-empty <code>S3Uri</code> that precludes users from specifying a manifest whose individual <code>S3Uri</code> is sourced from different S3 buckets.</p> <p> The following code example shows a valid manifest format: </p> <p> <code>[ {&quot;prefix&quot;: &quot;s3://`customer<em>`bucket/some/prefix/&quot;},</code> </p> <p> <code> &quot;relative/path/to/custdata-1&quot;,</code> </p> <p> <code> &quot;relative/path/custdata-2&quot;,</code> </p> <p> <code> ...</code> </p> <p> <code> &quot;relative/path/custdata-N&quot;</code> </p> <p> <code>]</code> </p> <p> This JSON is equivalent to the following <code>S3Uri</code> list:</p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/to/custdata-1</code> </p> <p> <code>s3://customer<em>bucket/some/prefix/relative/path/custdata-2</code> </p> <p> <code>...</code> </p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/custdata-N</code> </p> <p>The complete set of <code>S3Uri</code> in this manifest is the input data for the channel for this data source. The object that each <code>S3Uri</code> points to must be readable by the IAM role that Amazon SageMaker uses to perform tasks on your behalf. </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            +            +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:12610:1293
[INFO] [stdout]       |
[INFO] [stdout] 12610 | ...e following <code>S3Uri</code> list:</p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/to/custdata-1</code> </p> <p> <c...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:12610:1380
[INFO] [stdout]       |
[INFO] [stdout] 12610 | ...x/relative/path/to/custdata-1</code> </p> <p> <code>s3://customer<em>bucket/some/prefix/relative/path/custdata-2</code> </p> <p> <code...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 12610 |     /// <p><p>Depending on the value specified for the <code>S3DataType</code>, identifies either a key name prefix or a manifest. For example: </p> <ul> <li> <p> A key name prefix might look like this: <code>s3://bucketname/exampleprefix</code> </p> </li> <li> <p> A manifest might look like this: <code>s3://bucketname/example.manifest</code> </p> <p> A manifest is an S3 object which is a JSON file consisting of an array of elements. The first element is a prefix which is followed by one or more suffixes. SageMaker appends the suffix elements to the prefix to get a full set of <code>S3Uri</code>. Note that the prefix must be a valid non-empty <code>S3Uri</code> that precludes users from specifying a manifest whose individual <code>S3Uri</code> is sourced from different S3 buckets.</p> <p> The following code example shows a valid manifest format: </p> <p> <code>[ {&quot;prefix&quot;: &quot;s3://customer<em>bucket/some/prefix/&quot;},</code> </p> <p> <code> &quot;relative/path/to/custdata-1&quot;,</code> </p> <p> <code> &quot;relative/path/custdata-2&quot;,</code> </p> <p> <code> ...</code> </p> <p> <code> &quot;relative/path/custdata-N&quot;</code> </p> <p> <code>]</code> </p> <p> This JSON is equivalent to the following <code>S3Uri</code> list:</p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/to/custdata-1</code> </p> <p> <code>s3://`customer<em>`bucket/some/prefix/relative/path/custdata-2</code> </p> <p> <code>...</code> </p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/custdata-N</code> </p> <p>The complete set of <code>S3Uri</code> in this manifest is the input data for the channel for this data source. The object that each <code>S3Uri</code> points to must be readable by the IAM role that Amazon SageMaker uses to perform tasks on your behalf. </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            +            +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:12610:1489
[INFO] [stdout]       |
[INFO] [stdout] 12610 | ...-2</code> </p> <p> <code>...</code> </p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/custdata-N</code> </p> <p>The co...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]      --> src/generated.rs:12742:563
[INFO] [stdout]       |
[INFO] [stdout] 12742 | ...al states are referred to as the job&#39;s secondary status. </p> <p/></p>
[INFO] [stdout]       |                                                                      ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:12820:220
[INFO] [stdout]       |
[INFO] [stdout] 12820 | ...operation succeeded and completed.</p> </li> <li> <p> <code>UNDER<em>CHANGE</code> - Transitive state. Operations performed might not ...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 12820 |     /// <p><p>The current status of the product.</p> <ul> <li> <p> <code>AVAILABLE</code> - Stable state, ready to perform any operation. The most recent operation succeeded and completed.</p> </li> <li> <p> <code>`UNDER<em>`CHANGE</code> - Transitive state. Operations performed might not have valid results. Wait for an AVAILABLE status before performing operations.</p> </li> <li> <p> <code>TAINTED</code> - Stable state, ready to perform any operation. The stack has completed the requested operation but is not exactly what was requested. For example, a request to update to a new version failed and the stack rolled back to the current version.</p> </li> <li> <p> <code>ERROR</code> - An unexpected error occurred. The provisioned product exists but the stack is not running. For example, CloudFormation received a parameter value that was not valid and could not launch the stack.</p> </li> <li> <p> <code>PLAN</em>IN_PROGRESS</code> - Transitive state. The plan operations were performed to provision a new product, but resources have not yet been created. After reviewing the list of resources to be created, execute the plan. Wait for an AVAILABLE status before performing operations.</p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                       +         +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:12820:916
[INFO] [stdout]       |
[INFO] [stdout] 12820 | ...id and could not launch the stack.</p> </li> <li> <p> <code>PLAN</em>IN_PROGRESS</code> - Transitive state. The plan operations were p...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:13112:84
[INFO] [stdout]       |
[INFO] [stdout] 13112 |     /// <p><p>Specifies a target platform architecture.</p> <ul> <li> <p> <code>X86<em>64</code>: 64-bit version of the x86 instruction s...
[INFO] [stdout]       |                                                                                    ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 13112 |     /// <p><p>Specifies a target platform architecture.</p> <ul> <li> <p> <code>`X86<em>`64</code>: 64-bit version of the x86 instruction set.</p> </li> <li> <p> <code>X86</code>: 32-bit version of the x86 instruction set.</p> </li> <li> <p> <code>ARM64</code>: ARMv8 64-bit CPU.</p> </li> <li> <p> <code>ARM</em>EABIHF</code>: ARMv7 32-bit, Hard Float.</p> </li> <li> <p> <code>ARM_EABI</code>: ARMv7 32-bit, Soft Float. Used by Android 32-bit ARM platform.</p> </li> </ul></p>
[INFO] [stdout]       |                                                                                 +       +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:13112:307
[INFO] [stdout]       |
[INFO] [stdout] 13112 | ...ode>ARM64</code>: ARMv8 64-bit CPU.</p> </li> <li> <p> <code>ARM</em>EABIHF</code>: ARMv7 32-bit, Hard Float.</p> </li> <li> <p> <code...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:13115:242
[INFO] [stdout]       |
[INFO] [stdout] 13115 | ...stems. Android API level can be specified using the <code>ANDROID<em>PLATFORM</code> compiler option. For example, <code>&quot;Compile...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 13115 |     /// <p><p>Specifies a target platform OS.</p> <ul> <li> <p> <code>LINUX</code>: Linux-based operating systems.</p> </li> <li> <p> <code>ANDROID</code>: Android operating systems. Android API level can be specified using the <code>`ANDROID<em>`PLATFORM</code> compiler option. For example, <code>&quot;CompilerOptions&quot;: {&#39;ANDROID</em>PLATFORM&#39;: 28}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                           +           +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:13115:340
[INFO] [stdout]       |
[INFO] [stdout] 13115 | ...n. For example, <code>&quot;CompilerOptions&quot;: {&#39;ANDROID</em>PLATFORM&#39;: 28}</code> </p> </li> </ul></p>
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]      --> src/generated.rs:13144:12
[INFO] [stdout]       |
[INFO] [stdout] 13144 |     /// <p><p/></p>
[INFO] [stdout]       |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]      --> src/generated.rs:13148:12
[INFO] [stdout]       |
[INFO] [stdout] 13148 |     /// <p><p/></p>
[INFO] [stdout]       |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: invalid self-closing HTML tag `p`
[INFO] [stdout]      --> src/generated.rs:13151:12
[INFO] [stdout]       |
[INFO] [stdout] 13151 |     /// <p><p/></p>
[INFO] [stdout]       |            ^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:13649:489
[INFO] [stdout]       |
[INFO] [stdout] 13649 | ...format: </p> <p> <code>[ {&quot;prefix&quot;: &quot;s3://customer<em>bucket/some/prefix/&quot;},</code> </p> <p> <code>&quot;relative/...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 13649 |     /// <p><p>Depending on the value specified for the <code>S3DataType</code>, identifies either a key name prefix or a manifest. For example:</p> <ul> <li> <p> A key name prefix might look like this: <code>s3://bucketname/exampleprefix</code>. </p> </li> <li> <p> A manifest might look like this: <code>s3://bucketname/example.manifest</code> </p> <p> The manifest is an S3 object which is a JSON file with the following format: </p> <p> <code>[ {&quot;prefix&quot;: &quot;s3://`customer<em>`bucket/some/prefix/&quot;},</code> </p> <p> <code>&quot;relative/path/to/custdata-1&quot;,</code> </p> <p> <code>&quot;relative/path/custdata-2&quot;,</code> </p> <p> <code>...</code> </p> <p> <code>&quot;relative/path/custdata-N&quot;</code> </p> <p> <code>]</code> </p> <p> The preceding JSON matches the following <code>S3Uris</code>: </p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/to/custdata-1</code> </p> <p> <code>s3://customer<em>bucket/some/prefix/relative/path/custdata-2</code> </p> <p> <code>...</code> </p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/custdata-N</code> </p> <p> The complete set of <code>S3Uris</code> in this manifest constitutes the input data for the channel for this datasource. The object that each <code>S3Uris</code> points to must be readable by the IAM role that Amazon SageMaker uses to perform tasks on your behalf.</p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                 +            +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:13649:859
[INFO] [stdout]       |
[INFO] [stdout] 13649 | ... the following <code>S3Uris</code>: </p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/to/custdata-1</code> </p> <p> <c...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unclosed HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:13649:946
[INFO] [stdout]       |
[INFO] [stdout] 13649 | ...x/relative/path/to/custdata-1</code> </p> <p> <code>s3://customer<em>bucket/some/prefix/relative/path/custdata-2</code> </p> <p> <code...
[INFO] [stdout]       |                                                                     ^^^^
[INFO] [stdout]       |
[INFO] [stdout] help: try marking as source code
[INFO] [stdout]       |
[INFO] [stdout] 13649 |     /// <p><p>Depending on the value specified for the <code>S3DataType</code>, identifies either a key name prefix or a manifest. For example:</p> <ul> <li> <p> A key name prefix might look like this: <code>s3://bucketname/exampleprefix</code>. </p> </li> <li> <p> A manifest might look like this: <code>s3://bucketname/example.manifest</code> </p> <p> The manifest is an S3 object which is a JSON file with the following format: </p> <p> <code>[ {&quot;prefix&quot;: &quot;s3://customer<em>bucket/some/prefix/&quot;},</code> </p> <p> <code>&quot;relative/path/to/custdata-1&quot;,</code> </p> <p> <code>&quot;relative/path/custdata-2&quot;,</code> </p> <p> <code>...</code> </p> <p> <code>&quot;relative/path/custdata-N&quot;</code> </p> <p> <code>]</code> </p> <p> The preceding JSON matches the following <code>S3Uris</code>: </p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/to/custdata-1</code> </p> <p> <code>s3://`customer<em>`bucket/some/prefix/relative/path/custdata-2</code> </p> <p> <code>...</code> </p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/custdata-N</code> </p> <p> The complete set of <code>S3Uris</code> in this manifest constitutes the input data for the channel for this datasource. The object that each <code>S3Uris</code> points to must be readable by the IAM role that Amazon SageMaker uses to perform tasks on your behalf.</p> </li> </ul></p>
[INFO] [stdout]       |                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          +            +
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: unopened HTML tag `em`
[INFO] [stdout]      --> src/generated.rs:13649:1055
[INFO] [stdout]       |
[INFO] [stdout] 13649 | ...-2</code> </p> <p> <code>...</code> </p> <p> <code>s3://customer</em>bucket/some/prefix/relative/path/custdata-N</code> </p> <p> The c...
[INFO] [stdout]       |                                                                    ^^^^^
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stdout] warning: 106 warnings emitted
[INFO] [stdout] 
[INFO] [stdout] 
[INFO] [stderr]     Finished dev [unoptimized + debuginfo] target(s) in 10.31s
[INFO] running `Command { std: "docker" "inspect" "0a45b5797e47bf56fc97787166181073fed5366f9d77d8bba61ece0b43fbe07d", kill_on_drop: false }`
[INFO] running `Command { std: "docker" "rm" "-f" "0a45b5797e47bf56fc97787166181073fed5366f9d77d8bba61ece0b43fbe07d", kill_on_drop: false }`
[INFO] [stdout] 0a45b5797e47bf56fc97787166181073fed5366f9d77d8bba61ece0b43fbe07d
