diff --git a/.gitignore b/.gitignore index d5690d8d20..decd97e7ef 100644 --- a/.gitignore +++ b/.gitignore @@ -2,6 +2,7 @@ _site .sass-cache .jekyll-metadata *.out +.venv # direnv, posh-direnv .envrc diff --git a/_config.yml b/_config.yml index 246af39127..13bc44e3bf 100644 --- a/_config.yml +++ b/_config.yml @@ -11,15 +11,18 @@ kramdown: parse_block_html: true toc_levels: "1,2,3" logo: "/images/ONNX-Runtime-logo.svg" -aux_links: +aux_links: + + "Onnx Runtime": + - "/" + "Install": + - "/docs/install/" + "Get Started": + - "/docs/get-started/" "Tutorials": - "/docs/tutorials/" - "How to": - - "/docs/how-to/" - "Reference": - - "/docs/reference/" - "Resources": - - "/docs/resources/" + "API Docs": + - "/docs/api/" "GitHub": - "https://github.com/microsoft/onnxruntime" ga_tracking: UA-156955408-1 diff --git a/about.html b/about.html index 64562c58b1..6a3ce251d3 100644 --- a/about.html +++ b/about.html @@ -88,7 +88,7 @@

Optimization and acceleration

- Run any ONNX model using a single set of inference APIs that provide access to the best hardware acceleration available. Built-in optimization features trim and consolidate nodes without impacting model accuracy. Additionally, full backwards compatibility for ONNX and ONNX-ML ensures all ONNX models can be inferenced. + Run any ONNX model using a single set of inference APIs that provide access to the best hardware acceleration available. Built-in optimization features trim and consolidate nodes without impacting model accuracy. Additionally, full backwards compatibility for ONNX and ONNX-ML ensures all ONNX models can be inferenced.

@@ -99,7 +99,7 @@

API and platform support

- Take advantage of the benefits of ONNX Runtime without changing your technology stack. Access ONNX Runtime using your preferred API — C#, C++, C, Python, or Java. Support for Linux, Windows and Mac allows you to build and deploy applications without worry. + Take advantage of the benefits of ONNX Runtime without changing your technology stack. Access ONNX Runtime using your preferred API — C#, C++, C, Python, or Java. Support for Linux, Windows and Mac allows you to build and deploy applications without worry.

@@ -173,7 +173,7 @@ Tutorials
  • - + APIs
    • diff --git a/docs/reference/api/csharp-api-reference.md b/docs/api/csharp-api.md similarity index 97% rename from docs/reference/api/csharp-api-reference.md rename to docs/api/csharp-api.md index 2f6e392c8c..17c14ae3da 100644 --- a/docs/reference/api/csharp-api-reference.md +++ b/docs/api/csharp-api.md @@ -1,8 +1,11 @@ --- -nav_exclude: true +title: C# API +parent: API Docs +nav_order: 2 --- # C# API Reference +{: .no_toc } ### OrtEnv ```cs @@ -149,7 +152,7 @@ SetSessionExecutionMode(ExecutionMode execution_mode); ``` * ORT_SEQUENTIAL - execute operators in the graph sequentially. * ORT_PARALLEL - execute operators in the graph in parallel. -See [How to tune performance](../../how-to/tune-performance.md) for more details. +See [How to tune performance](../performance/tune-performance.md) for more details. ### NodeMetadata Container of metadata for a model graph node, used for communicating the shape and type of the input and output nodes. diff --git a/docs/api/index.md b/docs/api/index.md new file mode 100644 index 0000000000..b090fd3497 --- /dev/null +++ b/docs/api/index.md @@ -0,0 +1,15 @@ +--- +title: API Docs +has_children: true +nav_order: 5 +--- +# ORT API docs +{: .no_toc } + +|:----------------------------------------------------------------------------------| +| [Python API Docs](./python/api_summary.html){: .btn } | +| [Java API Docs](./java/index.html){: .btn} | +| [Objective C Docs](./objectivec/index.html){: .btn} | +| [WinRT API Docs](https://docs.microsoft.com/windows/ai/windows-ml/api-reference){: .btn} | +| [C# API Docs](./csharp-api){: .btn} | +| [Other API Docs](./other-apis){: .btn} | \ No newline at end of file diff --git a/docs/api/java-api.md b/docs/api/java-api.md new file mode 100644 index 0000000000..ddbc83a4a0 --- /dev/null +++ b/docs/api/java-api.md @@ -0,0 +1,10 @@ +--- +title: Java API +parent: API Docs +nav_order: 3 +--- + +# ORT Java Docs +{: .no_toc } + + [Go to the Java Docs](./java/index.html){: .btn .mr-4 target="_blank"} diff --git a/java/ai/onnxruntime/MapInfo.html b/docs/api/java/ai/onnxruntime/MapInfo.html similarity index 100% rename from java/ai/onnxruntime/MapInfo.html rename to docs/api/java/ai/onnxruntime/MapInfo.html diff --git a/java/ai/onnxruntime/NodeInfo.html b/docs/api/java/ai/onnxruntime/NodeInfo.html similarity index 100% rename from java/ai/onnxruntime/NodeInfo.html rename to docs/api/java/ai/onnxruntime/NodeInfo.html diff --git a/java/ai/onnxruntime/OnnxJavaType.html b/docs/api/java/ai/onnxruntime/OnnxJavaType.html similarity index 100% rename from java/ai/onnxruntime/OnnxJavaType.html rename to docs/api/java/ai/onnxruntime/OnnxJavaType.html diff --git a/java/ai/onnxruntime/OnnxMap.OnnxMapValueType.html b/docs/api/java/ai/onnxruntime/OnnxMap.OnnxMapValueType.html similarity index 100% rename from java/ai/onnxruntime/OnnxMap.OnnxMapValueType.html rename to docs/api/java/ai/onnxruntime/OnnxMap.OnnxMapValueType.html diff --git a/java/ai/onnxruntime/OnnxMap.html b/docs/api/java/ai/onnxruntime/OnnxMap.html similarity index 100% rename from java/ai/onnxruntime/OnnxMap.html rename to docs/api/java/ai/onnxruntime/OnnxMap.html diff --git a/java/ai/onnxruntime/OnnxSequence.html b/docs/api/java/ai/onnxruntime/OnnxSequence.html similarity index 100% rename from java/ai/onnxruntime/OnnxSequence.html rename to docs/api/java/ai/onnxruntime/OnnxSequence.html diff --git a/java/ai/onnxruntime/OnnxTensor.html b/docs/api/java/ai/onnxruntime/OnnxTensor.html similarity index 100% rename from java/ai/onnxruntime/OnnxTensor.html rename to docs/api/java/ai/onnxruntime/OnnxTensor.html diff --git a/java/ai/onnxruntime/OnnxValue.OnnxValueType.html b/docs/api/java/ai/onnxruntime/OnnxValue.OnnxValueType.html similarity index 100% rename from java/ai/onnxruntime/OnnxValue.OnnxValueType.html rename to docs/api/java/ai/onnxruntime/OnnxValue.OnnxValueType.html diff --git a/java/ai/onnxruntime/OnnxValue.html b/docs/api/java/ai/onnxruntime/OnnxValue.html similarity index 100% rename from java/ai/onnxruntime/OnnxValue.html rename to docs/api/java/ai/onnxruntime/OnnxValue.html diff --git a/java/ai/onnxruntime/OrtEnvironment.LoggingLevel.html b/docs/api/java/ai/onnxruntime/OrtEnvironment.LoggingLevel.html similarity index 100% rename from java/ai/onnxruntime/OrtEnvironment.LoggingLevel.html rename to docs/api/java/ai/onnxruntime/OrtEnvironment.LoggingLevel.html diff --git a/java/ai/onnxruntime/OrtEnvironment.html b/docs/api/java/ai/onnxruntime/OrtEnvironment.html similarity index 100% rename from java/ai/onnxruntime/OrtEnvironment.html rename to docs/api/java/ai/onnxruntime/OrtEnvironment.html diff --git a/java/ai/onnxruntime/OrtException.OrtErrorCode.html b/docs/api/java/ai/onnxruntime/OrtException.OrtErrorCode.html similarity index 100% rename from java/ai/onnxruntime/OrtException.OrtErrorCode.html rename to docs/api/java/ai/onnxruntime/OrtException.OrtErrorCode.html diff --git a/java/ai/onnxruntime/OrtException.html b/docs/api/java/ai/onnxruntime/OrtException.html similarity index 100% rename from java/ai/onnxruntime/OrtException.html rename to docs/api/java/ai/onnxruntime/OrtException.html diff --git a/java/ai/onnxruntime/OrtSession.Result.html b/docs/api/java/ai/onnxruntime/OrtSession.Result.html similarity index 100% rename from java/ai/onnxruntime/OrtSession.Result.html rename to docs/api/java/ai/onnxruntime/OrtSession.Result.html diff --git a/java/ai/onnxruntime/OrtSession.SessionOptions.ExecutionMode.html b/docs/api/java/ai/onnxruntime/OrtSession.SessionOptions.ExecutionMode.html similarity index 100% rename from java/ai/onnxruntime/OrtSession.SessionOptions.ExecutionMode.html rename to docs/api/java/ai/onnxruntime/OrtSession.SessionOptions.ExecutionMode.html diff --git a/java/ai/onnxruntime/OrtSession.SessionOptions.OptLevel.html b/docs/api/java/ai/onnxruntime/OrtSession.SessionOptions.OptLevel.html similarity index 100% rename from java/ai/onnxruntime/OrtSession.SessionOptions.OptLevel.html rename to docs/api/java/ai/onnxruntime/OrtSession.SessionOptions.OptLevel.html diff --git a/java/ai/onnxruntime/OrtSession.SessionOptions.html b/docs/api/java/ai/onnxruntime/OrtSession.SessionOptions.html similarity index 100% rename from java/ai/onnxruntime/OrtSession.SessionOptions.html rename to docs/api/java/ai/onnxruntime/OrtSession.SessionOptions.html diff --git a/java/ai/onnxruntime/OrtSession.html b/docs/api/java/ai/onnxruntime/OrtSession.html similarity index 100% rename from java/ai/onnxruntime/OrtSession.html rename to docs/api/java/ai/onnxruntime/OrtSession.html diff --git a/java/ai/onnxruntime/OrtUtil.html b/docs/api/java/ai/onnxruntime/OrtUtil.html similarity index 100% rename from java/ai/onnxruntime/OrtUtil.html rename to docs/api/java/ai/onnxruntime/OrtUtil.html diff --git a/java/ai/onnxruntime/SequenceInfo.html b/docs/api/java/ai/onnxruntime/SequenceInfo.html similarity index 100% rename from java/ai/onnxruntime/SequenceInfo.html rename to docs/api/java/ai/onnxruntime/SequenceInfo.html diff --git a/java/ai/onnxruntime/TensorInfo.OnnxTensorType.html b/docs/api/java/ai/onnxruntime/TensorInfo.OnnxTensorType.html similarity index 100% rename from java/ai/onnxruntime/TensorInfo.OnnxTensorType.html rename to docs/api/java/ai/onnxruntime/TensorInfo.OnnxTensorType.html diff --git a/java/ai/onnxruntime/TensorInfo.html b/docs/api/java/ai/onnxruntime/TensorInfo.html similarity index 100% rename from java/ai/onnxruntime/TensorInfo.html rename to docs/api/java/ai/onnxruntime/TensorInfo.html diff --git a/java/ai/onnxruntime/ValueInfo.html b/docs/api/java/ai/onnxruntime/ValueInfo.html similarity index 100% rename from java/ai/onnxruntime/ValueInfo.html rename to docs/api/java/ai/onnxruntime/ValueInfo.html diff --git a/java/ai/onnxruntime/class-use/MapInfo.html b/docs/api/java/ai/onnxruntime/class-use/MapInfo.html similarity index 100% rename from java/ai/onnxruntime/class-use/MapInfo.html rename to docs/api/java/ai/onnxruntime/class-use/MapInfo.html diff --git a/java/ai/onnxruntime/class-use/NodeInfo.html b/docs/api/java/ai/onnxruntime/class-use/NodeInfo.html similarity index 100% rename from java/ai/onnxruntime/class-use/NodeInfo.html rename to docs/api/java/ai/onnxruntime/class-use/NodeInfo.html diff --git a/java/ai/onnxruntime/class-use/OnnxJavaType.html b/docs/api/java/ai/onnxruntime/class-use/OnnxJavaType.html similarity index 100% rename from java/ai/onnxruntime/class-use/OnnxJavaType.html rename to docs/api/java/ai/onnxruntime/class-use/OnnxJavaType.html diff --git a/java/ai/onnxruntime/class-use/OnnxMap.OnnxMapValueType.html b/docs/api/java/ai/onnxruntime/class-use/OnnxMap.OnnxMapValueType.html similarity index 100% rename from java/ai/onnxruntime/class-use/OnnxMap.OnnxMapValueType.html rename to docs/api/java/ai/onnxruntime/class-use/OnnxMap.OnnxMapValueType.html diff --git a/java/ai/onnxruntime/class-use/OnnxMap.html b/docs/api/java/ai/onnxruntime/class-use/OnnxMap.html similarity index 100% rename from java/ai/onnxruntime/class-use/OnnxMap.html rename to docs/api/java/ai/onnxruntime/class-use/OnnxMap.html diff --git a/java/ai/onnxruntime/class-use/OnnxSequence.html b/docs/api/java/ai/onnxruntime/class-use/OnnxSequence.html similarity index 100% rename from java/ai/onnxruntime/class-use/OnnxSequence.html rename to docs/api/java/ai/onnxruntime/class-use/OnnxSequence.html diff --git a/java/ai/onnxruntime/class-use/OnnxTensor.html b/docs/api/java/ai/onnxruntime/class-use/OnnxTensor.html similarity index 100% rename from java/ai/onnxruntime/class-use/OnnxTensor.html rename to docs/api/java/ai/onnxruntime/class-use/OnnxTensor.html diff --git a/java/ai/onnxruntime/class-use/OnnxValue.OnnxValueType.html b/docs/api/java/ai/onnxruntime/class-use/OnnxValue.OnnxValueType.html similarity index 100% rename from java/ai/onnxruntime/class-use/OnnxValue.OnnxValueType.html rename to docs/api/java/ai/onnxruntime/class-use/OnnxValue.OnnxValueType.html diff --git a/java/ai/onnxruntime/class-use/OnnxValue.html b/docs/api/java/ai/onnxruntime/class-use/OnnxValue.html similarity index 100% rename from java/ai/onnxruntime/class-use/OnnxValue.html rename to docs/api/java/ai/onnxruntime/class-use/OnnxValue.html diff --git a/java/ai/onnxruntime/class-use/OrtEnvironment.LoggingLevel.html b/docs/api/java/ai/onnxruntime/class-use/OrtEnvironment.LoggingLevel.html similarity index 100% rename from java/ai/onnxruntime/class-use/OrtEnvironment.LoggingLevel.html rename to docs/api/java/ai/onnxruntime/class-use/OrtEnvironment.LoggingLevel.html diff --git a/java/ai/onnxruntime/class-use/OrtEnvironment.html b/docs/api/java/ai/onnxruntime/class-use/OrtEnvironment.html similarity index 100% rename from java/ai/onnxruntime/class-use/OrtEnvironment.html rename to docs/api/java/ai/onnxruntime/class-use/OrtEnvironment.html diff --git a/java/ai/onnxruntime/class-use/OrtException.OrtErrorCode.html b/docs/api/java/ai/onnxruntime/class-use/OrtException.OrtErrorCode.html similarity index 100% rename from java/ai/onnxruntime/class-use/OrtException.OrtErrorCode.html rename to docs/api/java/ai/onnxruntime/class-use/OrtException.OrtErrorCode.html diff --git a/java/ai/onnxruntime/class-use/OrtException.html b/docs/api/java/ai/onnxruntime/class-use/OrtException.html similarity index 100% rename from java/ai/onnxruntime/class-use/OrtException.html rename to docs/api/java/ai/onnxruntime/class-use/OrtException.html diff --git a/java/ai/onnxruntime/class-use/OrtSession.Result.html b/docs/api/java/ai/onnxruntime/class-use/OrtSession.Result.html similarity index 100% rename from java/ai/onnxruntime/class-use/OrtSession.Result.html rename to docs/api/java/ai/onnxruntime/class-use/OrtSession.Result.html diff --git a/java/ai/onnxruntime/class-use/OrtSession.SessionOptions.ExecutionMode.html b/docs/api/java/ai/onnxruntime/class-use/OrtSession.SessionOptions.ExecutionMode.html similarity index 100% rename from java/ai/onnxruntime/class-use/OrtSession.SessionOptions.ExecutionMode.html rename to docs/api/java/ai/onnxruntime/class-use/OrtSession.SessionOptions.ExecutionMode.html diff --git a/java/ai/onnxruntime/class-use/OrtSession.SessionOptions.OptLevel.html b/docs/api/java/ai/onnxruntime/class-use/OrtSession.SessionOptions.OptLevel.html similarity index 100% rename from java/ai/onnxruntime/class-use/OrtSession.SessionOptions.OptLevel.html rename to docs/api/java/ai/onnxruntime/class-use/OrtSession.SessionOptions.OptLevel.html diff --git a/java/ai/onnxruntime/class-use/OrtSession.SessionOptions.html b/docs/api/java/ai/onnxruntime/class-use/OrtSession.SessionOptions.html similarity index 100% rename from java/ai/onnxruntime/class-use/OrtSession.SessionOptions.html rename to docs/api/java/ai/onnxruntime/class-use/OrtSession.SessionOptions.html diff --git a/java/ai/onnxruntime/class-use/OrtSession.html b/docs/api/java/ai/onnxruntime/class-use/OrtSession.html similarity index 100% rename from java/ai/onnxruntime/class-use/OrtSession.html rename to docs/api/java/ai/onnxruntime/class-use/OrtSession.html diff --git a/java/ai/onnxruntime/class-use/OrtUtil.html b/docs/api/java/ai/onnxruntime/class-use/OrtUtil.html similarity index 100% rename from java/ai/onnxruntime/class-use/OrtUtil.html rename to docs/api/java/ai/onnxruntime/class-use/OrtUtil.html diff --git a/java/ai/onnxruntime/class-use/SequenceInfo.html b/docs/api/java/ai/onnxruntime/class-use/SequenceInfo.html similarity index 100% rename from java/ai/onnxruntime/class-use/SequenceInfo.html rename to docs/api/java/ai/onnxruntime/class-use/SequenceInfo.html diff --git a/java/ai/onnxruntime/class-use/TensorInfo.OnnxTensorType.html b/docs/api/java/ai/onnxruntime/class-use/TensorInfo.OnnxTensorType.html similarity index 100% rename from java/ai/onnxruntime/class-use/TensorInfo.OnnxTensorType.html rename to docs/api/java/ai/onnxruntime/class-use/TensorInfo.OnnxTensorType.html diff --git a/java/ai/onnxruntime/class-use/TensorInfo.html b/docs/api/java/ai/onnxruntime/class-use/TensorInfo.html similarity index 100% rename from java/ai/onnxruntime/class-use/TensorInfo.html rename to docs/api/java/ai/onnxruntime/class-use/TensorInfo.html diff --git a/java/ai/onnxruntime/class-use/ValueInfo.html b/docs/api/java/ai/onnxruntime/class-use/ValueInfo.html similarity index 100% rename from java/ai/onnxruntime/class-use/ValueInfo.html rename to docs/api/java/ai/onnxruntime/class-use/ValueInfo.html diff --git a/java/ai/onnxruntime/package-frame.html b/docs/api/java/ai/onnxruntime/package-frame.html similarity index 100% rename from java/ai/onnxruntime/package-frame.html rename to docs/api/java/ai/onnxruntime/package-frame.html diff --git a/java/ai/onnxruntime/package-summary.html b/docs/api/java/ai/onnxruntime/package-summary.html similarity index 100% rename from java/ai/onnxruntime/package-summary.html rename to docs/api/java/ai/onnxruntime/package-summary.html diff --git a/java/ai/onnxruntime/package-tree.html b/docs/api/java/ai/onnxruntime/package-tree.html similarity index 100% rename from java/ai/onnxruntime/package-tree.html rename to docs/api/java/ai/onnxruntime/package-tree.html diff --git a/java/ai/onnxruntime/package-use.html b/docs/api/java/ai/onnxruntime/package-use.html similarity index 100% rename from java/ai/onnxruntime/package-use.html rename to docs/api/java/ai/onnxruntime/package-use.html diff --git a/java/allclasses-frame.html b/docs/api/java/allclasses-frame.html similarity index 100% rename from java/allclasses-frame.html rename to docs/api/java/allclasses-frame.html diff --git a/java/allclasses-noframe.html b/docs/api/java/allclasses-noframe.html similarity index 100% rename from java/allclasses-noframe.html rename to docs/api/java/allclasses-noframe.html diff --git a/java/constant-values.html b/docs/api/java/constant-values.html similarity index 100% rename from java/constant-values.html rename to docs/api/java/constant-values.html diff --git a/java/deprecated-list.html b/docs/api/java/deprecated-list.html similarity index 100% rename from java/deprecated-list.html rename to docs/api/java/deprecated-list.html diff --git a/java/help-doc.html b/docs/api/java/help-doc.html similarity index 100% rename from java/help-doc.html rename to docs/api/java/help-doc.html diff --git a/java/index-all.html b/docs/api/java/index-all.html similarity index 100% rename from java/index-all.html rename to docs/api/java/index-all.html diff --git a/java/index.html b/docs/api/java/index.html similarity index 100% rename from java/index.html rename to docs/api/java/index.html diff --git a/java/overview-tree.html b/docs/api/java/overview-tree.html similarity index 100% rename from java/overview-tree.html rename to docs/api/java/overview-tree.html diff --git a/java/package-list b/docs/api/java/package-list similarity index 100% rename from java/package-list rename to docs/api/java/package-list diff --git a/java/script.js b/docs/api/java/script.js similarity index 100% rename from java/script.js rename to docs/api/java/script.js diff --git a/java/serialized-form.html b/docs/api/java/serialized-form.html similarity index 100% rename from java/serialized-form.html rename to docs/api/java/serialized-form.html diff --git a/java/stylesheet.css b/docs/api/java/stylesheet.css similarity index 99% rename from java/stylesheet.css rename to docs/api/java/stylesheet.css index 98055b22d6..9adb3c7cae 100644 --- a/java/stylesheet.css +++ b/docs/api/java/stylesheet.css @@ -3,7 +3,7 @@ Overall document style */ -@import url('resources/fonts/dejavu.css'); +@import url('../../../resources/fonts/dejavu.css'); body { background-color:#ffffff; diff --git a/docs/api/objectivec-api.md b/docs/api/objectivec-api.md new file mode 100644 index 0000000000..a8322f6be3 --- /dev/null +++ b/docs/api/objectivec-api.md @@ -0,0 +1,10 @@ +--- +title: Objective-C API +parent: API Docs +nav_order: 4 +--- + +# ORT Objective-C Docs +{: .no_toc } + + [Go to the Objective-C Docs](./objectivec/index.html){: .btn .mr-4 target="_blank"} diff --git a/objectivec/Classes.html b/docs/api/objectivec/Classes.html similarity index 100% rename from objectivec/Classes.html rename to docs/api/objectivec/Classes.html diff --git a/objectivec/Classes/ORTCoreMLExecutionProviderOptions.html b/docs/api/objectivec/Classes/ORTCoreMLExecutionProviderOptions.html similarity index 100% rename from objectivec/Classes/ORTCoreMLExecutionProviderOptions.html rename to docs/api/objectivec/Classes/ORTCoreMLExecutionProviderOptions.html diff --git a/objectivec/Classes/ORTEnv.html b/docs/api/objectivec/Classes/ORTEnv.html similarity index 100% rename from objectivec/Classes/ORTEnv.html rename to docs/api/objectivec/Classes/ORTEnv.html diff --git a/objectivec/Classes/ORTRunOptions.html b/docs/api/objectivec/Classes/ORTRunOptions.html similarity index 100% rename from objectivec/Classes/ORTRunOptions.html rename to docs/api/objectivec/Classes/ORTRunOptions.html diff --git a/objectivec/Classes/ORTSession.html b/docs/api/objectivec/Classes/ORTSession.html similarity index 100% rename from objectivec/Classes/ORTSession.html rename to docs/api/objectivec/Classes/ORTSession.html diff --git a/objectivec/Classes/ORTSessionOptions.html b/docs/api/objectivec/Classes/ORTSessionOptions.html similarity index 100% rename from objectivec/Classes/ORTSessionOptions.html rename to docs/api/objectivec/Classes/ORTSessionOptions.html diff --git a/objectivec/Classes/ORTTensorTypeAndShapeInfo.html b/docs/api/objectivec/Classes/ORTTensorTypeAndShapeInfo.html similarity index 100% rename from objectivec/Classes/ORTTensorTypeAndShapeInfo.html rename to docs/api/objectivec/Classes/ORTTensorTypeAndShapeInfo.html diff --git a/objectivec/Classes/ORTValue.html b/docs/api/objectivec/Classes/ORTValue.html similarity index 100% rename from objectivec/Classes/ORTValue.html rename to docs/api/objectivec/Classes/ORTValue.html diff --git a/objectivec/Classes/ORTValueTypeInfo.html b/docs/api/objectivec/Classes/ORTValueTypeInfo.html similarity index 100% rename from objectivec/Classes/ORTValueTypeInfo.html rename to docs/api/objectivec/Classes/ORTValueTypeInfo.html diff --git a/objectivec/Enums.html b/docs/api/objectivec/Enums.html similarity index 100% rename from objectivec/Enums.html rename to docs/api/objectivec/Enums.html diff --git a/objectivec/Enums/ORTGraphOptimizationLevel.html b/docs/api/objectivec/Enums/ORTGraphOptimizationLevel.html similarity index 100% rename from objectivec/Enums/ORTGraphOptimizationLevel.html rename to docs/api/objectivec/Enums/ORTGraphOptimizationLevel.html diff --git a/objectivec/Enums/ORTLoggingLevel.html b/docs/api/objectivec/Enums/ORTLoggingLevel.html similarity index 100% rename from objectivec/Enums/ORTLoggingLevel.html rename to docs/api/objectivec/Enums/ORTLoggingLevel.html diff --git a/objectivec/Enums/ORTTensorElementDataType.html b/docs/api/objectivec/Enums/ORTTensorElementDataType.html similarity index 100% rename from objectivec/Enums/ORTTensorElementDataType.html rename to docs/api/objectivec/Enums/ORTTensorElementDataType.html diff --git a/objectivec/Enums/ORTValueType.html b/docs/api/objectivec/Enums/ORTValueType.html similarity index 100% rename from objectivec/Enums/ORTValueType.html rename to docs/api/objectivec/Enums/ORTValueType.html diff --git a/objectivec/Functions.html b/docs/api/objectivec/Functions.html similarity index 100% rename from objectivec/Functions.html rename to docs/api/objectivec/Functions.html diff --git a/objectivec/css/highlight.css b/docs/api/objectivec/css/highlight.css similarity index 100% rename from objectivec/css/highlight.css rename to docs/api/objectivec/css/highlight.css diff --git a/objectivec/css/jazzy.css b/docs/api/objectivec/css/jazzy.css similarity index 100% rename from objectivec/css/jazzy.css rename to docs/api/objectivec/css/jazzy.css diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Info.plist b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Info.plist similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Info.plist rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Info.plist diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes.html b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes.html similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes.html rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes.html diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTCoreMLExecutionProviderOptions.html b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTCoreMLExecutionProviderOptions.html similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTCoreMLExecutionProviderOptions.html rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTCoreMLExecutionProviderOptions.html diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTEnv.html b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTEnv.html similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTEnv.html rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTEnv.html diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTRunOptions.html b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTRunOptions.html similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTRunOptions.html rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTRunOptions.html diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTSession.html b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTSession.html similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTSession.html rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTSession.html diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTSessionOptions.html b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTSessionOptions.html similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTSessionOptions.html rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTSessionOptions.html diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTTensorTypeAndShapeInfo.html b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTTensorTypeAndShapeInfo.html similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTTensorTypeAndShapeInfo.html rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTTensorTypeAndShapeInfo.html diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTValue.html b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTValue.html similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTValue.html rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTValue.html diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTValueTypeInfo.html b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTValueTypeInfo.html similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTValueTypeInfo.html rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Classes/ORTValueTypeInfo.html diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Enums.html b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Enums.html similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Enums.html rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Enums.html diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Enums/ORTGraphOptimizationLevel.html b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Enums/ORTGraphOptimizationLevel.html similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Enums/ORTGraphOptimizationLevel.html rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Enums/ORTGraphOptimizationLevel.html diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Enums/ORTLoggingLevel.html b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Enums/ORTLoggingLevel.html similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Enums/ORTLoggingLevel.html rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Enums/ORTLoggingLevel.html diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Enums/ORTTensorElementDataType.html b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Enums/ORTTensorElementDataType.html similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Enums/ORTTensorElementDataType.html rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Enums/ORTTensorElementDataType.html diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Enums/ORTValueType.html b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Enums/ORTValueType.html similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Enums/ORTValueType.html rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Enums/ORTValueType.html diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Functions.html b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Functions.html similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Functions.html rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/Functions.html diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/css/highlight.css b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/css/highlight.css similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/css/highlight.css rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/css/highlight.css diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/css/jazzy.css b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/css/jazzy.css similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/css/jazzy.css rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/css/jazzy.css diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/img/carat.png b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/img/carat.png similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/img/carat.png rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/img/carat.png diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/img/dash.png b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/img/dash.png similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/img/dash.png rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/img/dash.png diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/img/gh.png b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/img/gh.png similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/img/gh.png rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/img/gh.png diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/img/spinner.gif b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/img/spinner.gif similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/img/spinner.gif rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/img/spinner.gif diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/index.html b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/index.html similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/index.html rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/index.html diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/js/jazzy.js b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/js/jazzy.js similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/js/jazzy.js rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/js/jazzy.js diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/js/jazzy.search.js b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/js/jazzy.search.js similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/js/jazzy.search.js rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/js/jazzy.search.js diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/js/jquery.min.js b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/js/jquery.min.js similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/js/jquery.min.js rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/js/jquery.min.js diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/js/lunr.min.js b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/js/lunr.min.js similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/js/lunr.min.js rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/js/lunr.min.js diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/js/typeahead.jquery.js b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/js/typeahead.jquery.js similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/js/typeahead.jquery.js rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/js/typeahead.jquery.js diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/search.json b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/search.json similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/search.json rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/Documents/search.json diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/docSet.dsidx b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/docSet.dsidx similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/docSet.dsidx rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.docset/Contents/Resources/docSet.dsidx diff --git a/objectivec/docsets/ONNX Runtime Objective-C API.tgz b/docs/api/objectivec/docsets/ONNX Runtime Objective-C API.tgz similarity index 100% rename from objectivec/docsets/ONNX Runtime Objective-C API.tgz rename to docs/api/objectivec/docsets/ONNX Runtime Objective-C API.tgz diff --git a/objectivec/img/carat.png b/docs/api/objectivec/img/carat.png similarity index 100% rename from objectivec/img/carat.png rename to docs/api/objectivec/img/carat.png diff --git a/objectivec/img/dash.png b/docs/api/objectivec/img/dash.png similarity index 100% rename from objectivec/img/dash.png rename to docs/api/objectivec/img/dash.png diff --git a/objectivec/img/gh.png b/docs/api/objectivec/img/gh.png similarity index 100% rename from objectivec/img/gh.png rename to docs/api/objectivec/img/gh.png diff --git a/objectivec/img/spinner.gif b/docs/api/objectivec/img/spinner.gif similarity index 100% rename from objectivec/img/spinner.gif rename to docs/api/objectivec/img/spinner.gif diff --git a/objectivec/index.html b/docs/api/objectivec/index.html similarity index 100% rename from objectivec/index.html rename to docs/api/objectivec/index.html diff --git a/objectivec/js/jazzy.js b/docs/api/objectivec/js/jazzy.js similarity index 100% rename from objectivec/js/jazzy.js rename to docs/api/objectivec/js/jazzy.js diff --git a/objectivec/js/jazzy.search.js b/docs/api/objectivec/js/jazzy.search.js similarity index 100% rename from objectivec/js/jazzy.search.js rename to docs/api/objectivec/js/jazzy.search.js diff --git a/objectivec/js/jquery.min.js b/docs/api/objectivec/js/jquery.min.js similarity index 100% rename from objectivec/js/jquery.min.js rename to docs/api/objectivec/js/jquery.min.js diff --git a/objectivec/js/lunr.min.js b/docs/api/objectivec/js/lunr.min.js similarity index 100% rename from objectivec/js/lunr.min.js rename to docs/api/objectivec/js/lunr.min.js diff --git a/objectivec/js/typeahead.jquery.js b/docs/api/objectivec/js/typeahead.jquery.js similarity index 100% rename from objectivec/js/typeahead.jquery.js rename to docs/api/objectivec/js/typeahead.jquery.js diff --git a/objectivec/search.json b/docs/api/objectivec/search.json similarity index 100% rename from objectivec/search.json rename to docs/api/objectivec/search.json diff --git a/docs/reference/api/other-apis.md b/docs/api/other-apis.md similarity index 75% rename from docs/reference/api/other-apis.md rename to docs/api/other-apis.md index 5ff536e36e..4868d6ca0c 100644 --- a/docs/reference/api/other-apis.md +++ b/docs/api/other-apis.md @@ -1,8 +1,7 @@ --- title: Other Inference APIs -parent: API docs -grand_parent: Reference -nav_order: 9 +parent: API Docs +nav_order: 6 --- # Other APIs @@ -23,8 +22,8 @@ This is an community-contributed project and not officially supported by the cor ### API Reference {: .no_toc } -[https://github.com/ankane/onnxruntime](https://github.com/ankane/onnxruntime) +[https://github.com/ankane/onnxruntime](https://github.com/ankane/onnxruntime){:target="_blank"} ### Samples {: .no_toc } -[Ruby Samples](https://ankane.org/tensorflow-ruby) \ No newline at end of file +[Ruby Samples](https://ankane.org/tensorflow-ruby){:target="_blank"} \ No newline at end of file diff --git a/docs/api/python-api.md b/docs/api/python-api.md new file mode 100644 index 0000000000..9b822ea424 --- /dev/null +++ b/docs/api/python-api.md @@ -0,0 +1,11 @@ +--- +title: Python API +parent: API Docs +nav_order: 1 +--- + +# ORT Python API +{: .no_toc } + + + [Go to the ORT Python API Docs](./python/api_summary.html){: .btn .mr-4 target="_blank"} \ No newline at end of file diff --git a/python/.buildinfo b/docs/api/python/.buildinfo similarity index 100% rename from python/.buildinfo rename to docs/api/python/.buildinfo diff --git a/python/.nojekyll b/docs/api/python/.nojekyll similarity index 100% rename from python/.nojekyll rename to docs/api/python/.nojekyll diff --git a/python/README.html b/docs/api/python/README.html similarity index 100% rename from python/README.html rename to docs/api/python/README.html diff --git a/python/api_summary.html b/docs/api/python/api_summary.html similarity index 97% rename from python/api_summary.html rename to docs/api/python/api_summary.html index cb62bde81e..f3f890d359 100644 --- a/python/api_summary.html +++ b/docs/api/python/api_summary.html @@ -522,58 +522,7 @@ In particular it’s used in the testing suite.

    - -
    -
    ©2018-2021, Microsoft. diff --git a/python/auto_examples/index.html b/docs/api/python/auto_examples/index.html similarity index 99% rename from python/auto_examples/index.html rename to docs/api/python/auto_examples/index.html index 9dae8b6aca..95c6649f41 100644 --- a/python/auto_examples/index.html +++ b/docs/api/python/auto_examples/index.html @@ -118,13 +118,13 @@ - +

    Related Topics

    diff --git a/python/auto_examples/plot_backend.html b/docs/api/python/auto_examples/plot_backend.html similarity index 100% rename from python/auto_examples/plot_backend.html rename to docs/api/python/auto_examples/plot_backend.html diff --git a/python/auto_examples/plot_common_errors.html b/docs/api/python/auto_examples/plot_common_errors.html similarity index 100% rename from python/auto_examples/plot_common_errors.html rename to docs/api/python/auto_examples/plot_common_errors.html diff --git a/python/auto_examples/plot_convert_pipeline_vectorizer.html b/docs/api/python/auto_examples/plot_convert_pipeline_vectorizer.html similarity index 100% rename from python/auto_examples/plot_convert_pipeline_vectorizer.html rename to docs/api/python/auto_examples/plot_convert_pipeline_vectorizer.html diff --git a/python/auto_examples/plot_dl_keras.html b/docs/api/python/auto_examples/plot_dl_keras.html similarity index 100% rename from python/auto_examples/plot_dl_keras.html rename to docs/api/python/auto_examples/plot_dl_keras.html diff --git a/python/auto_examples/plot_load_and_predict.html b/docs/api/python/auto_examples/plot_load_and_predict.html similarity index 100% rename from python/auto_examples/plot_load_and_predict.html rename to docs/api/python/auto_examples/plot_load_and_predict.html diff --git a/python/auto_examples/plot_metadata.html b/docs/api/python/auto_examples/plot_metadata.html similarity index 100% rename from python/auto_examples/plot_metadata.html rename to docs/api/python/auto_examples/plot_metadata.html diff --git a/python/auto_examples/plot_pipeline.html b/docs/api/python/auto_examples/plot_pipeline.html similarity index 100% rename from python/auto_examples/plot_pipeline.html rename to docs/api/python/auto_examples/plot_pipeline.html diff --git a/python/auto_examples/plot_profiling.html b/docs/api/python/auto_examples/plot_profiling.html similarity index 100% rename from python/auto_examples/plot_profiling.html rename to docs/api/python/auto_examples/plot_profiling.html diff --git a/python/auto_examples/plot_train_convert_predict.html b/docs/api/python/auto_examples/plot_train_convert_predict.html similarity index 100% rename from python/auto_examples/plot_train_convert_predict.html rename to docs/api/python/auto_examples/plot_train_convert_predict.html diff --git a/python/auto_examples/sg_execution_times.html b/docs/api/python/auto_examples/sg_execution_times.html similarity index 100% rename from python/auto_examples/sg_execution_times.html rename to docs/api/python/auto_examples/sg_execution_times.html diff --git a/python/downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip b/docs/api/python/downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip similarity index 100% rename from python/downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip rename to docs/api/python/downloads/07fcc19ba03226cd3d83d4e40ec44385/auto_examples_python.zip diff --git a/python/downloads/1680115d3d937dfbb2d86adb705d9c5d/plot_train_convert_predict.ipynb b/docs/api/python/downloads/1680115d3d937dfbb2d86adb705d9c5d/plot_train_convert_predict.ipynb similarity index 100% rename from python/downloads/1680115d3d937dfbb2d86adb705d9c5d/plot_train_convert_predict.ipynb rename to docs/api/python/downloads/1680115d3d937dfbb2d86adb705d9c5d/plot_train_convert_predict.ipynb diff --git a/python/downloads/1b60ac13d6a5a4b72d4e4d28d1544f8d/plot_common_errors.ipynb b/docs/api/python/downloads/1b60ac13d6a5a4b72d4e4d28d1544f8d/plot_common_errors.ipynb similarity index 100% rename from python/downloads/1b60ac13d6a5a4b72d4e4d28d1544f8d/plot_common_errors.ipynb rename to docs/api/python/downloads/1b60ac13d6a5a4b72d4e4d28d1544f8d/plot_common_errors.ipynb diff --git a/python/downloads/290d1103c4874727a37c05b400ffb83c/plot_load_and_predict.ipynb b/docs/api/python/downloads/290d1103c4874727a37c05b400ffb83c/plot_load_and_predict.ipynb similarity index 100% rename from python/downloads/290d1103c4874727a37c05b400ffb83c/plot_load_and_predict.ipynb rename to docs/api/python/downloads/290d1103c4874727a37c05b400ffb83c/plot_load_and_predict.ipynb diff --git a/python/downloads/2dbd202de70c8b6a394b8a1c7c1e12b8/plot_pipeline.ipynb b/docs/api/python/downloads/2dbd202de70c8b6a394b8a1c7c1e12b8/plot_pipeline.ipynb similarity index 100% rename from python/downloads/2dbd202de70c8b6a394b8a1c7c1e12b8/plot_pipeline.ipynb rename to docs/api/python/downloads/2dbd202de70c8b6a394b8a1c7c1e12b8/plot_pipeline.ipynb diff --git a/python/downloads/3a0c2ba94405e579c84b6f356705659d/plot_train_convert_predict.ipynb b/docs/api/python/downloads/3a0c2ba94405e579c84b6f356705659d/plot_train_convert_predict.ipynb similarity index 100% rename from python/downloads/3a0c2ba94405e579c84b6f356705659d/plot_train_convert_predict.ipynb rename to docs/api/python/downloads/3a0c2ba94405e579c84b6f356705659d/plot_train_convert_predict.ipynb diff --git a/python/downloads/3a2955e44bf8f95a0eee6e71695ad788/plot_common_errors.py b/docs/api/python/downloads/3a2955e44bf8f95a0eee6e71695ad788/plot_common_errors.py similarity index 100% rename from python/downloads/3a2955e44bf8f95a0eee6e71695ad788/plot_common_errors.py rename to docs/api/python/downloads/3a2955e44bf8f95a0eee6e71695ad788/plot_common_errors.py diff --git a/python/downloads/3aca744422de94d33f9aaa3ce99633a9/plot_convert_pipeline_vectorizer.ipynb b/docs/api/python/downloads/3aca744422de94d33f9aaa3ce99633a9/plot_convert_pipeline_vectorizer.ipynb similarity index 100% rename from python/downloads/3aca744422de94d33f9aaa3ce99633a9/plot_convert_pipeline_vectorizer.ipynb rename to docs/api/python/downloads/3aca744422de94d33f9aaa3ce99633a9/plot_convert_pipeline_vectorizer.ipynb diff --git a/python/downloads/3e23fa9ebb26f4728ee8426ed7da0f63/plot_backend.py b/docs/api/python/downloads/3e23fa9ebb26f4728ee8426ed7da0f63/plot_backend.py similarity index 100% rename from python/downloads/3e23fa9ebb26f4728ee8426ed7da0f63/plot_backend.py rename to docs/api/python/downloads/3e23fa9ebb26f4728ee8426ed7da0f63/plot_backend.py diff --git a/python/downloads/4412ae3bda7068f45094acb5373c790e/plot_load_and_predict.py b/docs/api/python/downloads/4412ae3bda7068f45094acb5373c790e/plot_load_and_predict.py similarity index 100% rename from python/downloads/4412ae3bda7068f45094acb5373c790e/plot_load_and_predict.py rename to docs/api/python/downloads/4412ae3bda7068f45094acb5373c790e/plot_load_and_predict.py diff --git a/python/downloads/500c588edb4417e84924953b39d33cc6/plot_convert_pipeline_vectorizer.py b/docs/api/python/downloads/500c588edb4417e84924953b39d33cc6/plot_convert_pipeline_vectorizer.py similarity index 100% rename from python/downloads/500c588edb4417e84924953b39d33cc6/plot_convert_pipeline_vectorizer.py rename to docs/api/python/downloads/500c588edb4417e84924953b39d33cc6/plot_convert_pipeline_vectorizer.py diff --git a/python/downloads/594159f58c2d97bee3f22ee659067d5a/plot_backend.ipynb b/docs/api/python/downloads/594159f58c2d97bee3f22ee659067d5a/plot_backend.ipynb similarity index 100% rename from python/downloads/594159f58c2d97bee3f22ee659067d5a/plot_backend.ipynb rename to docs/api/python/downloads/594159f58c2d97bee3f22ee659067d5a/plot_backend.ipynb diff --git a/python/downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip b/docs/api/python/downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip similarity index 100% rename from python/downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip rename to docs/api/python/downloads/6f1e7a639e0699d6164445b55e6c116d/auto_examples_jupyter.zip diff --git a/python/downloads/7c8424f45d0156abd4d0221c65601124/plot_load_and_predict.py b/docs/api/python/downloads/7c8424f45d0156abd4d0221c65601124/plot_load_and_predict.py similarity index 100% rename from python/downloads/7c8424f45d0156abd4d0221c65601124/plot_load_and_predict.py rename to docs/api/python/downloads/7c8424f45d0156abd4d0221c65601124/plot_load_and_predict.py diff --git a/python/downloads/7d69185b02f38811ad5d0593ec22c99d/plot_metadata.py b/docs/api/python/downloads/7d69185b02f38811ad5d0593ec22c99d/plot_metadata.py similarity index 100% rename from python/downloads/7d69185b02f38811ad5d0593ec22c99d/plot_metadata.py rename to docs/api/python/downloads/7d69185b02f38811ad5d0593ec22c99d/plot_metadata.py diff --git a/python/downloads/8547b931339c42011a7c05ff3b5f5373/plot_common_errors.py b/docs/api/python/downloads/8547b931339c42011a7c05ff3b5f5373/plot_common_errors.py similarity index 100% rename from python/downloads/8547b931339c42011a7c05ff3b5f5373/plot_common_errors.py rename to docs/api/python/downloads/8547b931339c42011a7c05ff3b5f5373/plot_common_errors.py diff --git a/python/downloads/8dd0c9d6c4ab396fa8f24f6321edc4b0/plot_common_errors.ipynb b/docs/api/python/downloads/8dd0c9d6c4ab396fa8f24f6321edc4b0/plot_common_errors.ipynb similarity index 100% rename from python/downloads/8dd0c9d6c4ab396fa8f24f6321edc4b0/plot_common_errors.ipynb rename to docs/api/python/downloads/8dd0c9d6c4ab396fa8f24f6321edc4b0/plot_common_errors.ipynb diff --git a/python/downloads/932fe1ee7f48f55a6155d2f378bc85a0/plot_metadata.py b/docs/api/python/downloads/932fe1ee7f48f55a6155d2f378bc85a0/plot_metadata.py similarity index 100% rename from python/downloads/932fe1ee7f48f55a6155d2f378bc85a0/plot_metadata.py rename to docs/api/python/downloads/932fe1ee7f48f55a6155d2f378bc85a0/plot_metadata.py diff --git a/python/downloads/940d20a5bdb46eb51fb878fbb3bd928d/plot_metadata.ipynb b/docs/api/python/downloads/940d20a5bdb46eb51fb878fbb3bd928d/plot_metadata.ipynb similarity index 100% rename from python/downloads/940d20a5bdb46eb51fb878fbb3bd928d/plot_metadata.ipynb rename to docs/api/python/downloads/940d20a5bdb46eb51fb878fbb3bd928d/plot_metadata.ipynb diff --git a/python/downloads/94ba4b1ad7abc78b59124c6a39f9a075/plot_pipeline.py b/docs/api/python/downloads/94ba4b1ad7abc78b59124c6a39f9a075/plot_pipeline.py similarity index 100% rename from python/downloads/94ba4b1ad7abc78b59124c6a39f9a075/plot_pipeline.py rename to docs/api/python/downloads/94ba4b1ad7abc78b59124c6a39f9a075/plot_pipeline.py diff --git a/python/downloads/982a1f7abbb8ffc5d5e98b671c35e5aa/plot_convert_pipeline_vectorizer.py b/docs/api/python/downloads/982a1f7abbb8ffc5d5e98b671c35e5aa/plot_convert_pipeline_vectorizer.py similarity index 100% rename from python/downloads/982a1f7abbb8ffc5d5e98b671c35e5aa/plot_convert_pipeline_vectorizer.py rename to docs/api/python/downloads/982a1f7abbb8ffc5d5e98b671c35e5aa/plot_convert_pipeline_vectorizer.py diff --git a/python/downloads/a8a3fe6bdcf0fdfbed17a5a0f2384419/plot_profiling.ipynb b/docs/api/python/downloads/a8a3fe6bdcf0fdfbed17a5a0f2384419/plot_profiling.ipynb similarity index 100% rename from python/downloads/a8a3fe6bdcf0fdfbed17a5a0f2384419/plot_profiling.ipynb rename to docs/api/python/downloads/a8a3fe6bdcf0fdfbed17a5a0f2384419/plot_profiling.ipynb diff --git a/python/downloads/ae37e1cd2f800a09b44216a88ac39d30/plot_metadata.ipynb b/docs/api/python/downloads/ae37e1cd2f800a09b44216a88ac39d30/plot_metadata.ipynb similarity index 100% rename from python/downloads/ae37e1cd2f800a09b44216a88ac39d30/plot_metadata.ipynb rename to docs/api/python/downloads/ae37e1cd2f800a09b44216a88ac39d30/plot_metadata.ipynb diff --git a/python/downloads/b81c8c31615f9400a26ee60f0641af3f/plot_dl_keras.py b/docs/api/python/downloads/b81c8c31615f9400a26ee60f0641af3f/plot_dl_keras.py similarity index 100% rename from python/downloads/b81c8c31615f9400a26ee60f0641af3f/plot_dl_keras.py rename to docs/api/python/downloads/b81c8c31615f9400a26ee60f0641af3f/plot_dl_keras.py diff --git a/python/downloads/be7aeaf8b9b95af92780b5d952019035/plot_convert_pipeline_vectorizer.ipynb b/docs/api/python/downloads/be7aeaf8b9b95af92780b5d952019035/plot_convert_pipeline_vectorizer.ipynb similarity index 100% rename from python/downloads/be7aeaf8b9b95af92780b5d952019035/plot_convert_pipeline_vectorizer.ipynb rename to docs/api/python/downloads/be7aeaf8b9b95af92780b5d952019035/plot_convert_pipeline_vectorizer.ipynb diff --git a/python/downloads/c2f3ba3f66159c615632f39a9ad32dee/plot_pipeline.ipynb b/docs/api/python/downloads/c2f3ba3f66159c615632f39a9ad32dee/plot_pipeline.ipynb similarity index 100% rename from python/downloads/c2f3ba3f66159c615632f39a9ad32dee/plot_pipeline.ipynb rename to docs/api/python/downloads/c2f3ba3f66159c615632f39a9ad32dee/plot_pipeline.ipynb diff --git a/python/downloads/c647c128e0cf2b3db04ce60b41ef1a14/plot_train_convert_predict.py b/docs/api/python/downloads/c647c128e0cf2b3db04ce60b41ef1a14/plot_train_convert_predict.py similarity index 100% rename from python/downloads/c647c128e0cf2b3db04ce60b41ef1a14/plot_train_convert_predict.py rename to docs/api/python/downloads/c647c128e0cf2b3db04ce60b41ef1a14/plot_train_convert_predict.py diff --git a/python/downloads/c9f88a9294285c733dcce209fcc939de/plot_dl_keras.ipynb b/docs/api/python/downloads/c9f88a9294285c733dcce209fcc939de/plot_dl_keras.ipynb similarity index 100% rename from python/downloads/c9f88a9294285c733dcce209fcc939de/plot_dl_keras.ipynb rename to docs/api/python/downloads/c9f88a9294285c733dcce209fcc939de/plot_dl_keras.ipynb diff --git a/python/downloads/ccbbfd4f60683438ab99a4c42d3fbbdf/plot_profiling.ipynb b/docs/api/python/downloads/ccbbfd4f60683438ab99a4c42d3fbbdf/plot_profiling.ipynb similarity index 100% rename from python/downloads/ccbbfd4f60683438ab99a4c42d3fbbdf/plot_profiling.ipynb rename to docs/api/python/downloads/ccbbfd4f60683438ab99a4c42d3fbbdf/plot_profiling.ipynb diff --git a/python/downloads/cfe61aca1f0a89486c7024466ea500fd/plot_profiling.py b/docs/api/python/downloads/cfe61aca1f0a89486c7024466ea500fd/plot_profiling.py similarity index 100% rename from python/downloads/cfe61aca1f0a89486c7024466ea500fd/plot_profiling.py rename to docs/api/python/downloads/cfe61aca1f0a89486c7024466ea500fd/plot_profiling.py diff --git a/python/downloads/d436e9922b51a71358604ec00f09e7e4/plot_pipeline.py b/docs/api/python/downloads/d436e9922b51a71358604ec00f09e7e4/plot_pipeline.py similarity index 100% rename from python/downloads/d436e9922b51a71358604ec00f09e7e4/plot_pipeline.py rename to docs/api/python/downloads/d436e9922b51a71358604ec00f09e7e4/plot_pipeline.py diff --git a/python/downloads/d83345a79a181a29892287297803aeec/plot_train_convert_predict.py b/docs/api/python/downloads/d83345a79a181a29892287297803aeec/plot_train_convert_predict.py similarity index 100% rename from python/downloads/d83345a79a181a29892287297803aeec/plot_train_convert_predict.py rename to docs/api/python/downloads/d83345a79a181a29892287297803aeec/plot_train_convert_predict.py diff --git a/python/downloads/dee2ae82948a521867a372a6b9515393/plot_load_and_predict.ipynb b/docs/api/python/downloads/dee2ae82948a521867a372a6b9515393/plot_load_and_predict.ipynb similarity index 100% rename from python/downloads/dee2ae82948a521867a372a6b9515393/plot_load_and_predict.ipynb rename to docs/api/python/downloads/dee2ae82948a521867a372a6b9515393/plot_load_and_predict.ipynb diff --git a/python/downloads/df88a32237a9b3e764a8da54c1743145/plot_backend.py b/docs/api/python/downloads/df88a32237a9b3e764a8da54c1743145/plot_backend.py similarity index 100% rename from python/downloads/df88a32237a9b3e764a8da54c1743145/plot_backend.py rename to docs/api/python/downloads/df88a32237a9b3e764a8da54c1743145/plot_backend.py diff --git a/python/downloads/e4ee07af6afb721729db3bf156693fa2/plot_profiling.py b/docs/api/python/downloads/e4ee07af6afb721729db3bf156693fa2/plot_profiling.py similarity index 100% rename from python/downloads/e4ee07af6afb721729db3bf156693fa2/plot_profiling.py rename to docs/api/python/downloads/e4ee07af6afb721729db3bf156693fa2/plot_profiling.py diff --git a/python/downloads/f8e5d8e309ca291f68bd029c26838ccc/plot_backend.ipynb b/docs/api/python/downloads/f8e5d8e309ca291f68bd029c26838ccc/plot_backend.ipynb similarity index 100% rename from python/downloads/f8e5d8e309ca291f68bd029c26838ccc/plot_backend.ipynb rename to docs/api/python/downloads/f8e5d8e309ca291f68bd029c26838ccc/plot_backend.ipynb diff --git a/python/examples_md.html b/docs/api/python/examples_md.html similarity index 100% rename from python/examples_md.html rename to docs/api/python/examples_md.html diff --git a/python/genindex.html b/docs/api/python/genindex.html similarity index 100% rename from python/genindex.html rename to docs/api/python/genindex.html diff --git a/python/images/sphx_glr_plot_backend_thumb.png b/docs/api/python/images/sphx_glr_plot_backend_thumb.png similarity index 100% rename from python/images/sphx_glr_plot_backend_thumb.png rename to docs/api/python/images/sphx_glr_plot_backend_thumb.png diff --git a/python/images/sphx_glr_plot_common_errors_thumb.png b/docs/api/python/images/sphx_glr_plot_common_errors_thumb.png similarity index 100% rename from python/images/sphx_glr_plot_common_errors_thumb.png rename to docs/api/python/images/sphx_glr_plot_common_errors_thumb.png diff --git a/python/images/sphx_glr_plot_convert_pipeline_vectorizer_thumb.png b/docs/api/python/images/sphx_glr_plot_convert_pipeline_vectorizer_thumb.png similarity index 100% rename from python/images/sphx_glr_plot_convert_pipeline_vectorizer_thumb.png rename to docs/api/python/images/sphx_glr_plot_convert_pipeline_vectorizer_thumb.png diff --git a/python/images/sphx_glr_plot_load_and_predict_thumb.png b/docs/api/python/images/sphx_glr_plot_load_and_predict_thumb.png similarity index 100% rename from python/images/sphx_glr_plot_load_and_predict_thumb.png rename to docs/api/python/images/sphx_glr_plot_load_and_predict_thumb.png diff --git a/python/images/sphx_glr_plot_metadata_thumb.png b/docs/api/python/images/sphx_glr_plot_metadata_thumb.png similarity index 100% rename from python/images/sphx_glr_plot_metadata_thumb.png rename to docs/api/python/images/sphx_glr_plot_metadata_thumb.png diff --git a/python/images/sphx_glr_plot_pipeline_001.png b/docs/api/python/images/sphx_glr_plot_pipeline_001.png similarity index 100% rename from python/images/sphx_glr_plot_pipeline_001.png rename to docs/api/python/images/sphx_glr_plot_pipeline_001.png diff --git a/python/images/sphx_glr_plot_pipeline_thumb.png b/docs/api/python/images/sphx_glr_plot_pipeline_thumb.png similarity index 100% rename from python/images/sphx_glr_plot_pipeline_thumb.png rename to docs/api/python/images/sphx_glr_plot_pipeline_thumb.png diff --git a/python/images/sphx_glr_plot_profiling_thumb.png b/docs/api/python/images/sphx_glr_plot_profiling_thumb.png similarity index 100% rename from python/images/sphx_glr_plot_profiling_thumb.png rename to docs/api/python/images/sphx_glr_plot_profiling_thumb.png diff --git a/python/images/sphx_glr_plot_train_convert_predict_001.png b/docs/api/python/images/sphx_glr_plot_train_convert_predict_001.png similarity index 100% rename from python/images/sphx_glr_plot_train_convert_predict_001.png rename to docs/api/python/images/sphx_glr_plot_train_convert_predict_001.png diff --git a/python/images/sphx_glr_plot_train_convert_predict_thumb.png b/docs/api/python/images/sphx_glr_plot_train_convert_predict_thumb.png similarity index 100% rename from python/images/sphx_glr_plot_train_convert_predict_thumb.png rename to docs/api/python/images/sphx_glr_plot_train_convert_predict_thumb.png diff --git a/python/index.html b/docs/api/python/index.html similarity index 100% rename from python/index.html rename to docs/api/python/index.html diff --git a/python/modules/index.html b/docs/api/python/modules/index.html similarity index 100% rename from python/modules/index.html rename to docs/api/python/modules/index.html diff --git a/python/modules/onnxruntime/capi/onnxruntime_inference_collection.html b/docs/api/python/modules/onnxruntime/capi/onnxruntime_inference_collection.html similarity index 100% rename from python/modules/onnxruntime/capi/onnxruntime_inference_collection.html rename to docs/api/python/modules/onnxruntime/capi/onnxruntime_inference_collection.html diff --git a/python/modules/onnxruntime/datasets.html b/docs/api/python/modules/onnxruntime/datasets.html similarity index 100% rename from python/modules/onnxruntime/datasets.html rename to docs/api/python/modules/onnxruntime/datasets.html diff --git a/python/objects.inv b/docs/api/python/objects.inv similarity index 100% rename from python/objects.inv rename to docs/api/python/objects.inv diff --git a/python/search.html b/docs/api/python/search.html similarity index 100% rename from python/search.html rename to docs/api/python/search.html diff --git a/python/searchindex.js b/docs/api/python/searchindex.js similarity index 100% rename from python/searchindex.js rename to docs/api/python/searchindex.js diff --git a/python/sources/README.rst.txt b/docs/api/python/sources/README.rst.txt similarity index 100% rename from python/sources/README.rst.txt rename to docs/api/python/sources/README.rst.txt diff --git a/python/sources/api_summary.rst.txt b/docs/api/python/sources/api_summary.rst.txt similarity index 100% rename from python/sources/api_summary.rst.txt rename to docs/api/python/sources/api_summary.rst.txt diff --git a/python/sources/auto_examples/index.rst.txt b/docs/api/python/sources/auto_examples/index.rst.txt similarity index 100% rename from python/sources/auto_examples/index.rst.txt rename to docs/api/python/sources/auto_examples/index.rst.txt diff --git a/python/sources/auto_examples/plot_backend.rst.txt b/docs/api/python/sources/auto_examples/plot_backend.rst.txt similarity index 100% rename from python/sources/auto_examples/plot_backend.rst.txt rename to docs/api/python/sources/auto_examples/plot_backend.rst.txt diff --git a/python/sources/auto_examples/plot_common_errors.rst.txt b/docs/api/python/sources/auto_examples/plot_common_errors.rst.txt similarity index 100% rename from python/sources/auto_examples/plot_common_errors.rst.txt rename to docs/api/python/sources/auto_examples/plot_common_errors.rst.txt diff --git a/python/sources/auto_examples/plot_convert_pipeline_vectorizer.rst.txt b/docs/api/python/sources/auto_examples/plot_convert_pipeline_vectorizer.rst.txt similarity index 100% rename from python/sources/auto_examples/plot_convert_pipeline_vectorizer.rst.txt rename to docs/api/python/sources/auto_examples/plot_convert_pipeline_vectorizer.rst.txt diff --git a/python/sources/auto_examples/plot_dl_keras.rst.txt b/docs/api/python/sources/auto_examples/plot_dl_keras.rst.txt similarity index 100% rename from python/sources/auto_examples/plot_dl_keras.rst.txt rename to docs/api/python/sources/auto_examples/plot_dl_keras.rst.txt diff --git a/python/sources/auto_examples/plot_load_and_predict.rst.txt b/docs/api/python/sources/auto_examples/plot_load_and_predict.rst.txt similarity index 100% rename from python/sources/auto_examples/plot_load_and_predict.rst.txt rename to docs/api/python/sources/auto_examples/plot_load_and_predict.rst.txt diff --git a/python/sources/auto_examples/plot_metadata.rst.txt b/docs/api/python/sources/auto_examples/plot_metadata.rst.txt similarity index 100% rename from python/sources/auto_examples/plot_metadata.rst.txt rename to docs/api/python/sources/auto_examples/plot_metadata.rst.txt diff --git a/python/sources/auto_examples/plot_pipeline.rst.txt b/docs/api/python/sources/auto_examples/plot_pipeline.rst.txt similarity index 100% rename from python/sources/auto_examples/plot_pipeline.rst.txt rename to docs/api/python/sources/auto_examples/plot_pipeline.rst.txt diff --git a/python/sources/auto_examples/plot_profiling.rst.txt b/docs/api/python/sources/auto_examples/plot_profiling.rst.txt similarity index 100% rename from python/sources/auto_examples/plot_profiling.rst.txt rename to docs/api/python/sources/auto_examples/plot_profiling.rst.txt diff --git a/python/sources/auto_examples/plot_train_convert_predict.rst.txt b/docs/api/python/sources/auto_examples/plot_train_convert_predict.rst.txt similarity index 100% rename from python/sources/auto_examples/plot_train_convert_predict.rst.txt rename to docs/api/python/sources/auto_examples/plot_train_convert_predict.rst.txt diff --git a/python/sources/auto_examples/sg_execution_times.rst.txt b/docs/api/python/sources/auto_examples/sg_execution_times.rst.txt similarity index 100% rename from python/sources/auto_examples/sg_execution_times.rst.txt rename to docs/api/python/sources/auto_examples/sg_execution_times.rst.txt diff --git a/python/sources/examples_md.rst.txt b/docs/api/python/sources/examples_md.rst.txt similarity index 100% rename from python/sources/examples_md.rst.txt rename to docs/api/python/sources/examples_md.rst.txt diff --git a/python/sources/index.rst.txt b/docs/api/python/sources/index.rst.txt similarity index 100% rename from python/sources/index.rst.txt rename to docs/api/python/sources/index.rst.txt diff --git a/python/sources/tutorial.rst.txt b/docs/api/python/sources/tutorial.rst.txt similarity index 100% rename from python/sources/tutorial.rst.txt rename to docs/api/python/sources/tutorial.rst.txt diff --git a/python/static/ONNX_Runtime_icon.png b/docs/api/python/static/ONNX_Runtime_icon.png similarity index 100% rename from python/static/ONNX_Runtime_icon.png rename to docs/api/python/static/ONNX_Runtime_icon.png diff --git a/python/static/alabaster.css b/docs/api/python/static/alabaster.css similarity index 100% rename from python/static/alabaster.css rename to docs/api/python/static/alabaster.css diff --git a/python/static/basic.css b/docs/api/python/static/basic.css similarity index 100% rename from python/static/basic.css rename to docs/api/python/static/basic.css diff --git a/python/static/binder_badge_logo.svg b/docs/api/python/static/binder_badge_logo.svg similarity index 100% rename from python/static/binder_badge_logo.svg rename to docs/api/python/static/binder_badge_logo.svg diff --git a/python/static/broken_example.png b/docs/api/python/static/broken_example.png similarity index 100% rename from python/static/broken_example.png rename to docs/api/python/static/broken_example.png diff --git a/python/static/custom.css b/docs/api/python/static/custom.css similarity index 100% rename from python/static/custom.css rename to docs/api/python/static/custom.css diff --git a/python/static/doctools.js b/docs/api/python/static/doctools.js similarity index 100% rename from python/static/doctools.js rename to docs/api/python/static/doctools.js diff --git a/python/static/documentation_options.js b/docs/api/python/static/documentation_options.js similarity index 100% rename from python/static/documentation_options.js rename to docs/api/python/static/documentation_options.js diff --git a/python/static/file.png b/docs/api/python/static/file.png similarity index 100% rename from python/static/file.png rename to docs/api/python/static/file.png diff --git a/python/static/gallery-binder.css b/docs/api/python/static/gallery-binder.css similarity index 100% rename from python/static/gallery-binder.css rename to docs/api/python/static/gallery-binder.css diff --git a/python/static/gallery-dataframe.css b/docs/api/python/static/gallery-dataframe.css similarity index 100% rename from python/static/gallery-dataframe.css rename to docs/api/python/static/gallery-dataframe.css diff --git a/python/static/gallery-rendered-html.css b/docs/api/python/static/gallery-rendered-html.css similarity index 100% rename from python/static/gallery-rendered-html.css rename to docs/api/python/static/gallery-rendered-html.css diff --git a/python/static/gallery.css b/docs/api/python/static/gallery.css similarity index 100% rename from python/static/gallery.css rename to docs/api/python/static/gallery.css diff --git a/python/static/graphviz.css b/docs/api/python/static/graphviz.css similarity index 100% rename from python/static/graphviz.css rename to docs/api/python/static/graphviz.css diff --git a/python/static/jquery-3.5.1.js b/docs/api/python/static/jquery-3.5.1.js similarity index 100% rename from python/static/jquery-3.5.1.js rename to docs/api/python/static/jquery-3.5.1.js diff --git a/python/static/jquery.js b/docs/api/python/static/jquery.js similarity index 100% rename from python/static/jquery.js rename to docs/api/python/static/jquery.js diff --git a/python/static/language_data.js b/docs/api/python/static/language_data.js similarity index 100% rename from python/static/language_data.js rename to docs/api/python/static/language_data.js diff --git a/python/static/minus.png b/docs/api/python/static/minus.png similarity index 100% rename from python/static/minus.png rename to docs/api/python/static/minus.png diff --git a/python/static/no_image.png b/docs/api/python/static/no_image.png similarity index 100% rename from python/static/no_image.png rename to docs/api/python/static/no_image.png diff --git a/python/static/plus.png b/docs/api/python/static/plus.png similarity index 100% rename from python/static/plus.png rename to docs/api/python/static/plus.png diff --git a/python/static/pygments.css b/docs/api/python/static/pygments.css similarity index 100% rename from python/static/pygments.css rename to docs/api/python/static/pygments.css diff --git a/python/static/searchtools.js b/docs/api/python/static/searchtools.js similarity index 100% rename from python/static/searchtools.js rename to docs/api/python/static/searchtools.js diff --git a/python/static/underscore-1.12.0.js b/docs/api/python/static/underscore-1.12.0.js similarity index 100% rename from python/static/underscore-1.12.0.js rename to docs/api/python/static/underscore-1.12.0.js diff --git a/python/static/underscore-1.3.1.js b/docs/api/python/static/underscore-1.3.1.js similarity index 100% rename from python/static/underscore-1.3.1.js rename to docs/api/python/static/underscore-1.3.1.js diff --git a/python/static/underscore.js b/docs/api/python/static/underscore.js similarity index 100% rename from python/static/underscore.js rename to docs/api/python/static/underscore.js diff --git a/python/tutorial.html b/docs/api/python/tutorial.html similarity index 100% rename from python/tutorial.html rename to docs/api/python/tutorial.html diff --git a/docs/api/winrt-api.md b/docs/api/winrt-api.md new file mode 100644 index 0000000000..4cb951bece --- /dev/null +++ b/docs/api/winrt-api.md @@ -0,0 +1,10 @@ +--- +title: WinRT API +parent: API Docs +nav_order: 5 +--- +# ORT WinRT API on Microsoft Docs +{: .no_toc } + + + [Go to the WinRT API on Microsoft Docs](https://docs.microsoft.com/windows/ai/windows-ml/api-reference){: .btn .mr-4 target="_blank"} diff --git a/docs/how-to/build/android-ios.md b/docs/build/android-ios.md similarity index 97% rename from docs/how-to/build/android-ios.md rename to docs/build/android-ios.md index 1be776ea03..5ec26070e9 100644 --- a/docs/how-to/build/android-ios.md +++ b/docs/build/android-ios.md @@ -2,9 +2,8 @@ title: Build for Android/iOS parent: Build ORT nav_order: 5 -grand_parent: How to --- - +` # Build ONNX Runtime for Android and iOS {: .no_toc } @@ -122,7 +121,7 @@ To build on Windows with `--build_java` enabled you must also: ### Android NNAPI Execution Provider -If you want to use NNAPI Execution Provider on Android, see [NNAPI Execution Provider](../../reference/execution-providers/NNAPI-ExecutionProvider). +If you want to use NNAPI Execution Provider on Android, see [NNAPI Execution Provider](../execution-providers/NNAPI-ExecutionProvider). #### Build Instructions @@ -202,7 +201,7 @@ Run one of the following build scripts from the ONNX Runtime repository root: ### CoreML Execution Provider -If you want to use CoreML Execution Provider on iOS or macOS, see [CoreML Execution Provider](../../reference/execution-providers/CoreML-ExecutionProvider). +If you want to use CoreML Execution Provider on iOS or macOS, see [CoreML Execution Provider](../execution-providers/CoreML-ExecutionProvider). #### Build Instructions diff --git a/docs/how-to/build/eps.md b/docs/build/eps.md similarity index 95% rename from docs/how-to/build/eps.md rename to docs/build/eps.md index 51576f84bc..72ef11f829 100644 --- a/docs/how-to/build/eps.md +++ b/docs/build/eps.md @@ -1,7 +1,6 @@ --- title: Build with different EPs parent: Build ORT -grand_parent: How to nav_order: 3 --- @@ -87,7 +86,7 @@ If you want to build with an earlier version, you must temporarily remove the 'C ## TensorRT -See more information on the TensorRT Execution Provider [here](../../reference/execution-providers/TensorRT-ExecutionProvider.md). +See more information on the TensorRT Execution Provider [here](../execution-providers/TensorRT-ExecutionProvider.md). ### Prerequisites {: .no_toc } @@ -189,7 +188,7 @@ These instructions are for JetPack SDK 4.6. ## oneDNN -See more information on ondDNN (formerly DNNL) [here](../../reference/execution-providers/DNNL-ExecutionProvider.md). +See more information on ondDNN (formerly DNNL) [here](../execution-providers/DNNL-ExecutionProvider.md). ### Build Instructions {: .no_toc } @@ -223,7 +222,7 @@ OneDNN EP build supports building Python wheel for both Windows and linux using ## OpenVINO -See more information on the OpenVINO Execution Provider [here](../../reference/execution-providers/OpenVINO-ExecutionProvider.md). +See more information on the OpenVINO Execution Provider [here](../execution-providers/OpenVINO-ExecutionProvider.md). ### Prerequisites {: .no_toc } @@ -279,7 +278,7 @@ See more information on the OpenVINO Execution Provider [here](../../reference/e ``` * `--use_openvino` builds the OpenVINO Execution Provider in ONNX Runtime. -* ``: Specifies the default hardware target for building OpenVINO Execution Provider. This can be overriden dynamically at runtime with another option (refer to [OpenVINO-ExecutionProvider](../../reference/execution-providers/OpenVINO-ExecutionProvider.md#summary-of-options) for more details on dynamic device selection). Below are the options for different Intel target devices. +* ``: Specifies the default hardware target for building OpenVINO Execution Provider. This can be overriden dynamically at runtime with another option (refer to [OpenVINO-ExecutionProvider](../execution-providers/OpenVINO-ExecutionProvider.md#summary-of-options) for more details on dynamic device selection). Below are the options for different Intel target devices. | Hardware Option | Target Device | | --------------- | ------------------------| @@ -303,12 +302,12 @@ A minimum of two device's should be specified for a valid HETERO or Multi-Device Example's: HETERO:MYRIAD,CPU or HETERO:HDDL,GPU,CPU or MULTI:MYRIAD,GPU,CPU ``` -For more information on OpenVINO Execution Provider's ONNX Layer support, Topology support, and Intel hardware enabled, please refer to the document [OpenVINO-ExecutionProvider](../../reference/execution-providers/OpenVINO-ExecutionProvider.md) +For more information on OpenVINO Execution Provider's ONNX Layer support, Topology support, and Intel hardware enabled, please refer to the document [OpenVINO-ExecutionProvider](../execution-providers/OpenVINO-ExecutionProvider.md) --- ## NUPHAR -See more information on the Nuphar Execution Provider [here](../../reference/execution-providers/Nuphar-ExecutionProvider.md). +See more information on the Nuphar Execution Provider [here](../execution-providers/Nuphar-ExecutionProvider.md). ### Prerequisites {: .no_toc } @@ -388,7 +387,7 @@ Dockerfile instructions are available [here](https://github.com/microsoft/onnxru --- ## DirectML -See more information on the DirectML execution provider [here](../../reference/execution-providers/DirectML-ExecutionProvider.md). +See more information on the DirectML execution provider [here](../execution-providers/DirectML-ExecutionProvider.md). ### Windows {: .no_toc } @@ -403,7 +402,7 @@ The DirectML execution provider supports building for both x64 and x86 architect --- ## ARM Compute Library -See more information on the ACL Execution Provider [here](../../reference/execution-providers/ACL-ExecutionProvider.md). +See more information on the ACL Execution Provider [here](../execution-providers/ACL-ExecutionProvider.md). ### Prerequisites {: .no_toc } @@ -470,7 +469,7 @@ onnxruntime_test_all ## ArmNN -See more information on the ArmNN Execution Provider [here](../../reference/execution-providers/ArmNN-ExecutionProvider.md). +See more information on the ArmNN Execution Provider [here](../execution-providers/ArmNN-ExecutionProvider.md). ### Prerequisites {: .no_toc } @@ -518,7 +517,7 @@ The ARM Compute Library home directory and build directory must also be availabl --- ## RKNPU -See more information on the RKNPU Execution Provider [here](../../reference/execution-providers/RKNPU-ExecutionProvider.md). +See more information on the RKNPU Execution Provider [here](../execution-providers/RKNPU-ExecutionProvider.md). ### Prerequisites {: .no_toc } @@ -557,9 +556,9 @@ set(CMAKE_C_COMPILER aarch64-linux-gnu-gcc) --- ## Vitis-AI -See more information on the Xilinx Vitis-AI execution provider [here](../../reference/execution-providers/Vitis-AI-ExecutionProvider.md). +See more information on the Xilinx Vitis-AI execution provider [here](../execution-providers/Vitis-AI-ExecutionProvider.md). -For instructions to setup the hardware environment: [Hardware setup](../../reference/execution-providers/Vitis-AI-ExecutionProvider.md#Hardware-setup) +For instructions to setup the hardware environment: [Hardware setup](../execution-providers/Vitis-AI-ExecutionProvider.md#Hardware-setup) ### Linux {: .no_toc } @@ -578,7 +577,7 @@ The Vitis-AI execution provider is only supported on Linux. ## AMD MIGraphX -See more information on the MIGraphX Execution Provider [here](../../reference/execution-providers/MIGraphX-ExecutionProvider.md). +See more information on the MIGraphX Execution Provider [here](../execution-providers/MIGraphX-ExecutionProvider.md). ### Prerequisites {: .no_toc } diff --git a/docs/how-to/build/index.md b/docs/build/index.md similarity index 89% rename from docs/how-to/build/index.md rename to docs/build/index.md index 2888a66da5..9adfcd48f5 100644 --- a/docs/how-to/build/index.md +++ b/docs/build/index.md @@ -1,8 +1,7 @@ --- title: Build ORT -parent: How to has_children: true -nav_order: 2 +nav_order: 5 --- # Build ONNX Runtime from source {: .no_toc } diff --git a/docs/how-to/build/inferencing.md b/docs/build/inferencing.md similarity index 99% rename from docs/how-to/build/inferencing.md rename to docs/build/inferencing.md index 6aed58f010..5c145aba88 100644 --- a/docs/how-to/build/inferencing.md +++ b/docs/build/inferencing.md @@ -1,7 +1,6 @@ --- title: Build for inferencing parent: Build ORT -grand_parent: How to nav_order: 1 --- diff --git a/docs/how-to/build/reduced.md b/docs/build/reduced.md similarity index 99% rename from docs/how-to/build/reduced.md rename to docs/build/reduced.md index a89aa012da..8956b9a659 100644 --- a/docs/how-to/build/reduced.md +++ b/docs/build/reduced.md @@ -1,6 +1,5 @@ --- title: Build with reduced size -grand_parent: How to parent: Build ORT nav_order: 6 --- diff --git a/docs/how-to/build/training.md b/docs/build/training.md similarity index 99% rename from docs/how-to/build/training.md rename to docs/build/training.md index b271a73deb..79e2b9edae 100644 --- a/docs/how-to/build/training.md +++ b/docs/build/training.md @@ -1,7 +1,6 @@ --- title: Build for training parent: Build ORT -grand_parent: How to nav_order: 2 --- diff --git a/docs/build/web.md b/docs/build/web.md new file mode 100644 index 0000000000..97e70b363d --- /dev/null +++ b/docs/build/web.md @@ -0,0 +1,14 @@ +--- +title: Build for web +parent: Build ORT +nav_order: 4 +--- + +# Build ONNX Runtime for Web + + + Check out the [release blog here](https://cloudblogs.microsoft.com/opensource/2021/09/02/onnx-runtime-web-running-your-machine-learning-model-in-browser/) + + + *[DOCUMENTATION COMING SOON]* + diff --git a/docs/tutorials/ecosystem.md b/docs/ecosystem/index.md similarity index 78% rename from docs/tutorials/ecosystem.md rename to docs/ecosystem/index.md index 58a500d288..7d309a2f6b 100644 --- a/docs/tutorials/ecosystem.md +++ b/docs/ecosystem/index.md @@ -1,7 +1,6 @@ --- title: ORT Ecosystem -parent: Tutorials -nav_order: 3 +nav_order: 11 --- # ORT Ecosystem {: .no_toc } @@ -16,31 +15,31 @@ ONNX Runtime functions as part of an ecosystem of tools and platforms to deliver ## Azure Machine Learning Services -* [Azure Container Instance: BERT](https://github.com/microsoft/onnxruntime/tree/master/onnxruntime/python/tools/transformers/notebooks/Inference_Bert_with_OnnxRuntime_on_AzureML.ipynb) -* [Azure Container Instance: Facial Expression Recognition](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/onnx/onnx-inference-facial-expression-recognition-deploy.ipynb) -* [Azure Container Instance: MNIST](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/onnx/onnx-inference-mnist-deploy.ipynb) -* [Azure Container Instance: Image classification (Resnet)](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/onnx/onnx-modelzoo-aml-deploy-resnet50.ipynb) -* [Azure Kubernetes Services: FER+](https://github.com/microsoft/onnxruntime/tree/master/docs/python/notebooks/onnx-inference-byoc-gpu-cpu-aks.ipynb) -* [Azure IoT Sedge (Intel UP2 device with OpenVINO)](https://github.com/Azure-Samples/onnxruntime-iot-edge/blob/master/AzureML-OpenVINO/README.md) -* [Automated Machine Learning](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/automated-machine-learning/classification-bank-marketing-all-features/auto-ml-classification-bank-marketing-all-features.ipynb) +* [Azure Container Instance: BERT](https://github.com/microsoft/onnxruntime/tree/master/onnxruntime/python/tools/transformers/notebooks/Inference_Bert_with_OnnxRuntime_on_AzureML.ipynb){:target="_blank"} +* [Azure Container Instance: Facial Expression Recognition](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/onnx/onnx-inference-facial-expression-recognition-deploy.ipynb){:target="_blank"} +* [Azure Container Instance: MNIST](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/onnx/onnx-inference-mnist-deploy.ipynb){:target="_blank"} +* [Azure Container Instance: Image classification (Resnet)](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/deployment/onnx/onnx-modelzoo-aml-deploy-resnet50.ipynb){:target="_blank"} +* [Azure Kubernetes Services: FER+](https://github.com/microsoft/onnxruntime/tree/master/docs/python/notebooks/onnx-inference-byoc-gpu-cpu-aks.ipynb){:target="_blank"} +* [Azure IoT Sedge (Intel UP2 device with OpenVINO)](https://github.com/Azure-Samples/onnxruntime-iot-edge/blob/master/AzureML-OpenVINO/README.md){:target="_blank"} +* [Automated Machine Learning](https://github.com/Azure/MachineLearningNotebooks/blob/master/how-to-use-azureml/automated-machine-learning/classification-bank-marketing-all-features/auto-ml-classification-bank-marketing-all-features.ipynb){:target="_blank"} ## Azure Custom Vision -* [Export a Custom Vision model to ONNX format](https://docs.microsoft.com/en-us/samples/azure-samples/cognitive-services-onnx-customvision-sample/cognitive-services-onnx-customvision-sample/) -* [Use a Custom Vision model with Windows Machine Learning](https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/custom-vision-onnx-windows-ml) +* [Export a Custom Vision model to ONNX format](https://docs.microsoft.com/en-us/samples/azure-samples/cognitive-services-onnx-customvision-sample/cognitive-services-onnx-customvision-sample/){:target="_blank"} +* [Use a Custom Vision model with Windows Machine Learning](https://docs.microsoft.com/en-us/azure/cognitive-services/custom-vision-service/custom-vision-onnx-windows-ml){:target="_blank"} ## Azure Live Video Analytics -* [Azure Video Analytics: YOLOv3 and TinyYOLOv3](https://github.com/Azure/live-video-analytics/tree/master/utilities/video-analysis/yolov3-onnx) +* [Azure Video Analytics: YOLOv3 and TinyYOLOv3](https://github.com/Azure/live-video-analytics/tree/master/utilities/video-analysis/yolov3-onnx){:target="_blank"} ## Azure SQL Edge -* [ML predictions in Azure SQL Edge and Azure SQL Managed Instance](https://docs.microsoft.com/en-us/azure/azure-sql-edge/deploy-onnxJ) +* [ML predictions in Azure SQL Edge and Azure SQL Managed Instance](https://docs.microsoft.com/en-us/azure/azure-sql-edge/deploy-onnxJ){:target="_blank"} ## Azure Synapse Analytics -* [ML predictions in Synapse SQL](https://docs.microsoft.com/en-us/azure/synapse-analytics/sql-data-warehouse/sql-data-warehouse-predict) +* [ML predictions in Synapse SQL](https://docs.microsoft.com/en-us/azure/synapse-analytics/sql-data-warehouse/sql-data-warehouse-predict){:target="_blank"} ## ML.NET -* [Automated Machine Learning](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-use-automl-onnx-model-dotnet?toc=/dotnet/machine-learning/how-to-guides/toc.json&bc=/dotnet/machine-learning/how-to-guides/toc.json) -* [Inference: Object detection](https://docs.microsoft.com/en-us/dotnet/machine-learning/tutorials/object-detection-onnx) +* [Automated Machine Learning](https://docs.microsoft.com/en-us/azure/machine-learning/how-to-use-automl-onnx-model-dotnet?toc=/dotnet/machine-learning/how-to-guides/toc.json&bc=/dotnet/machine-learning/how-to-guides/toc.json){:target="_blank"} +* [Inference: Object detection](https://docs.microsoft.com/en-us/dotnet/machine-learning/tutorials/object-detection-onnx){:target="_blank"} ## NVIDIA Triton Inference Server -* [ONNX Runtime backend for Triton](https://github.com/triton-inference-server/onnxruntime_backend) \ No newline at end of file +* [ONNX Runtime backend for Triton](https://github.com/triton-inference-server/onnxruntime_backend){:target="_blank"} \ No newline at end of file diff --git a/docs/reference/execution-providers/ACL-ExecutionProvider.md b/docs/execution-providers/ACL-ExecutionProvider.md similarity index 53% rename from docs/reference/execution-providers/ACL-ExecutionProvider.md rename to docs/execution-providers/ACL-ExecutionProvider.md index 46dc2ff903..65cd2eb0cc 100644 --- a/docs/reference/execution-providers/ACL-ExecutionProvider.md +++ b/docs/execution-providers/ACL-ExecutionProvider.md @@ -1,13 +1,13 @@ --- title: ARM Compute Library parent: Execution Providers -grand_parent: Reference +nav_order: 4 --- # ACL Execution Provider {: .no_toc } -[Arm Compute Library](https://github.com/ARM-software/ComputeLibrary) is an open source inference engine maintained by Arm and Linaro companies. The integration of ACL as an execution provider (EP) into ONNX Runtime accelerates performance of ONNX model workloads across Armv8 cores. +[Arm Compute Library](https://github.com/ARM-software/ComputeLibrary){:target="_blank"} is an open source inference engine maintained by Arm and Linaro companies. The integration of ACL as an execution provider (EP) into ONNX Runtime accelerates performance of ONNX model workloads across Armv8 cores. ## Contents @@ -18,7 +18,7 @@ grand_parent: Reference ## Build -For build instructions, please see the [BUILD page](../../how-to/build/eps.md#arm-compute-library). +For build instructions, please see the [BUILD page](./build/eps.md#arm-compute-library). ## Usage ### C/C++ @@ -30,9 +30,9 @@ Ort::SessionOptions sf; bool enable_cpu_mem_arena = true; Ort::ThrowOnError(OrtSessionOptionsAppendExecutionProvider_ACL(sf, enable_cpu_mem_arena)); ``` -The C API details are [here](../api/c-api.md). +The C API details are [here](../get-started/with-c.html). ## Performance Tuning -For performance tuning, please see guidance on this page: [ONNX Runtime Perf Tuning](../../how-to/tune-performance.md) +For performance tuning, please see guidance on this page: [ONNX Runtime Perf Tuning](./performance/tune-performance.md) -When/if using [onnxruntime_perf_test](https://github.com/microsoft/onnxruntime/tree/master/onnxruntime/test/perftest), use the flag -e acl +When/if using [onnxruntime_perf_test](https://github.com/microsoft/onnxruntime/tree/master/onnxruntime/test/perftest){:target="_blank"}, use the flag -e acl diff --git a/docs/reference/execution-providers/ArmNN-ExecutionProvider.md b/docs/execution-providers/ArmNN-ExecutionProvider.md similarity index 82% rename from docs/reference/execution-providers/ArmNN-ExecutionProvider.md rename to docs/execution-providers/ArmNN-ExecutionProvider.md index 7c42ab0bae..71bdd192c6 100644 --- a/docs/reference/execution-providers/ArmNN-ExecutionProvider.md +++ b/docs/execution-providers/ArmNN-ExecutionProvider.md @@ -1,7 +1,7 @@ --- title: ARM NN parent: Execution Providers -grand_parent: Reference +nav_order: 3 --- # ArmNN Execution Provider @@ -16,7 +16,7 @@ grand_parent: Reference [ArmNN](https://github.com/ARM-software/armnn) is an open source inference engine maintained by Arm and Linaro companies. The integration of ArmNN as an execution provider (EP) into ONNX Runtime accelerates performance of ONNX model workloads across Armv8 cores. ## Build -For build instructions, please see the [BUILD page](../../how-to/build/eps.md#armnn). +For build instructions, please see the [BUILD page](./build/eps.md#armnn). ## Usage ### C/C++ @@ -27,9 +27,9 @@ Ort::SessionOptions so; bool enable_cpu_mem_arena = true; Ort::ThrowOnError(OrtSessionOptionsAppendExecutionProvider_ArmNN(so, enable_cpu_mem_arena)); ``` -The C API details are [here](../api/c-api.md). +The C API details are [here](./get-started/with-c.html.md). ## Performance Tuning -For performance tuning, please see guidance on this page: [ONNX Runtime Perf Tuning](../../how-to/tune-performance.md) +For performance tuning, please see guidance on this page: [ONNX Runtime Perf Tuning](./performance/tune-performance.md) When/if using [onnxruntime_perf_test](https://github.com/microsoft/onnxruntime/tree/master/onnxruntime/test/perftest), use the flag -e armnn diff --git a/docs/reference/execution-providers/CUDA-ExecutionProvider.md b/docs/execution-providers/CUDA-ExecutionProvider.md similarity index 95% rename from docs/reference/execution-providers/CUDA-ExecutionProvider.md rename to docs/execution-providers/CUDA-ExecutionProvider.md index d1e75b805c..de142ca917 100644 --- a/docs/reference/execution-providers/CUDA-ExecutionProvider.md +++ b/docs/execution-providers/CUDA-ExecutionProvider.md @@ -1,7 +1,6 @@ --- title: CUDA parent: Execution Providers -grand_parent: Reference nav_order: 1 --- @@ -18,7 +17,7 @@ The CUDA Execution Provider enables hardware accelerated computation on Nvidia C {:toc} ## Install -Pre-built binaries of ONNX Runtime with CUDA EP are published for most language bindings. Please reference [How to - Install ORT](https://www.onnxruntime.ai/docs/how-to/install.html#inference). +Pre-built binaries of ONNX Runtime with CUDA EP are published for most language bindings. Please reference [How to - Install ORT](../install.html#inference). ## Requirements @@ -35,7 +34,7 @@ Please reference table below for official GPU packages dependencies for the ONNX For older versions, please reference the readme and build pages on the release branch. ## Build -For build instructions, please see the [BUILD page](../../how-to/build/eps.md#cuda). +For build instructions, please see the [BUILD page](../build/eps.md#cuda). ## Configuration Options The CUDA Execution Provider supports the following configuration options. diff --git a/docs/reference/execution-providers/CoreML-ExecutionProvider.md b/docs/execution-providers/CoreML-ExecutionProvider.md similarity index 96% rename from docs/reference/execution-providers/CoreML-ExecutionProvider.md rename to docs/execution-providers/CoreML-ExecutionProvider.md index f1ceaa8861..78487a7339 100644 --- a/docs/reference/execution-providers/CoreML-ExecutionProvider.md +++ b/docs/execution-providers/CoreML-ExecutionProvider.md @@ -1,7 +1,7 @@ --- title: CoreML parent: Execution Providers -grand_parent: Reference +nav_order: 2 --- {::options toc_levels="2" /} @@ -29,7 +29,7 @@ Pre-built binaries of ONNX Runtime Mobile with CoreML EP for iOS are published t ## Build -For build instructions for iOS devices, please see [How to: Build for Android/iOS](../../how-to/build/android-ios.md#coreml-execution-provider). +For build instructions for iOS devices, please see [How to: Build for Android/iOS](../build/android-ios.md#coreml-execution-provider). ## Usage diff --git a/docs/reference/execution-providers/DirectML-ExecutionProvider.md b/docs/execution-providers/DirectML-ExecutionProvider.md similarity index 94% rename from docs/reference/execution-providers/DirectML-ExecutionProvider.md rename to docs/execution-providers/DirectML-ExecutionProvider.md index cf5a55ac21..ffdec5a124 100644 --- a/docs/reference/execution-providers/DirectML-ExecutionProvider.md +++ b/docs/execution-providers/DirectML-ExecutionProvider.md @@ -1,7 +1,7 @@ --- title: Direct ML parent: Execution Providers -grand_parent: Reference +nav_order: 5 --- # DirectML Execution Provider @@ -22,7 +22,7 @@ The DirectML Execution Provider currently uses DirectML version 1.4.2. {:toc} ## Install -Pre-built packages of ORT with the DirectML EP is published on Nuget.org. See [How to: Install ORT](https://faxu.github.io/onnxruntime/docs/how-to/install.html). +Pre-built packages of ORT with the DirectML EP is published on Nuget.org. See [How to: Install ORT](./install). ## Requirements @@ -37,7 +37,7 @@ DirectML is compatible with Windows 10, version 1709 (10.0.16299; RS3, "Fall Cre ## Build Requirements for building the DirectML execution provider: -1. Visual Studio 2017 toolchain (see [cmake configuration instructions](../../how-to/build-inferencing.md)) +1. Visual Studio 2017 toolchain 2. [The Windows 10 SDK (10.0.18362.0) for Windows 10, version 1903](https://developer.microsoft.com/en-us/windows/downloads/windows-10-sdk) (or newer) To build onnxruntime with the DML EP included, supply the `--use_dml` parameter to `build.bat`. e.g. @@ -52,7 +52,7 @@ Note that building onnxruntime with the DirectML execution provider enabled caus ## Usage -When using the [C API](../api/c-api.md) with a DML-enabled build of onnxruntime, the DirectML execution provider can be enabled using one of the two factory functions included in `include/onnxruntime/core/providers/dml/dml_provider_factory.h`. +When using the [C API](../get-started/with-c.html.md) with a DML-enabled build of onnxruntime, the DirectML execution provider can be enabled using one of the two factory functions included in `include/onnxruntime/core/providers/dml/dml_provider_factory.h`. ### `OrtSessionOptionsAppendExecutionProvider_DML` function {: .no_toc } diff --git a/docs/reference/execution-providers/MIGraphX-ExecutionProvider.md b/docs/execution-providers/MIGraphX-ExecutionProvider.md similarity index 87% rename from docs/reference/execution-providers/MIGraphX-ExecutionProvider.md rename to docs/execution-providers/MIGraphX-ExecutionProvider.md index cc95b42397..cbed2a0e58 100644 --- a/docs/reference/execution-providers/MIGraphX-ExecutionProvider.md +++ b/docs/execution-providers/MIGraphX-ExecutionProvider.md @@ -1,7 +1,7 @@ --- title: AMD MI GraphX parent: Execution Providers -grand_parent: Reference +nav_order: 6 --- # MIGraphX Execution Provider @@ -16,7 +16,7 @@ The [MIGraphX](https://github.com/ROCmSoftwarePlatform/AMDMIGraphX/) execution p {:toc} ## Build -For build instructions, please see the [BUILD page](../../how-to/build/eps.md#amd-migraphx). +For build instructions, please see the [BUILD page](../build/eps.md#amd-migraphx). ## Usage @@ -31,7 +31,7 @@ Ort::ThrowOnError(OrtSessionOptionsAppendExecutionProvider_MiGraphX(sf, device_i You can check [here](https://github.com/scxiao/ort_test/tree/master/char_rnn) for a specific c/c++ program. -The C API details are [here](../api/c-api.md). +The C API details are [here](../get-started/with-c.html.md). ### Python When using the Python wheel from the ONNX Runtime build with MIGraphX execution provider, it will be automatically @@ -45,6 +45,6 @@ model on either the CPU or MIGraphX Execution Provider. MIGraphX providers an environment variable ORT_MIGRAPHX_FP16_ENABLE to enable the FP16 mode. ## Performance Tuning -For performance tuning, please see guidance on this page: [ONNX Runtime Perf Tuning](../../how-to/tune-performance.md) +For performance tuning, please see guidance on this page: [ONNX Runtime Perf Tuning](../performance/tune-performance.md) When/if using [onnxruntime_perf_test](https://github.com/microsoft/onnxruntime/tree/master/onnxruntime/test/perftest#onnxruntime-performance-test), use the flag `-e migraphx` \ No newline at end of file diff --git a/docs/reference/execution-providers/NNAPI-ExecutionProvider.md b/docs/execution-providers/NNAPI-ExecutionProvider.md similarity index 94% rename from docs/reference/execution-providers/NNAPI-ExecutionProvider.md rename to docs/execution-providers/NNAPI-ExecutionProvider.md index e64bb61426..f15343ff32 100644 --- a/docs/reference/execution-providers/NNAPI-ExecutionProvider.md +++ b/docs/execution-providers/NNAPI-ExecutionProvider.md @@ -1,7 +1,7 @@ --- title: NNAPI parent: Execution Providers -grand_parent: Reference +nav_order: 7 --- {::options toc_levels="2" /} @@ -24,7 +24,7 @@ Pre-built packages of ONNX Runtime Mobile with NNAPI EP for Android are publishe ## Build -Please see the [ONNX Runtime Mobile](../../how-to/mobile) deployment information for instructions on building or using a pre-built package that includes the NNAPI EP. +Please see the [ONNX Runtime Mobile](../tutorials/mobile/) deployment information for instructions on building or using a pre-built package that includes the NNAPI EP. ## Usage diff --git a/docs/reference/execution-providers/Nuphar-ExecutionProvider.md b/docs/execution-providers/Nuphar-ExecutionProvider.md similarity index 99% rename from docs/reference/execution-providers/Nuphar-ExecutionProvider.md rename to docs/execution-providers/Nuphar-ExecutionProvider.md index 8d91ca8023..935afaabff 100644 --- a/docs/reference/execution-providers/Nuphar-ExecutionProvider.md +++ b/docs/execution-providers/Nuphar-ExecutionProvider.md @@ -1,7 +1,7 @@ --- title: NUPHAR parent: Execution Providers -grand_parent: Reference +nav_order: 8 --- # Nuphar Execution Provider @@ -18,7 +18,7 @@ Developers can tap into the power of Nuphar through ONNX Runtime to accelerate i {:toc} ## Build -For build instructions, please see the [BUILD page](../../how-to/build/eps.md#nuphar). +For build instructions, please see the [BUILD page](../build/eps.md#nuphar). ## Usage ### C/C++ diff --git a/docs/reference/execution-providers/OpenVINO-ExecutionProvider.md b/docs/execution-providers/OpenVINO-ExecutionProvider.md similarity index 96% rename from docs/reference/execution-providers/OpenVINO-ExecutionProvider.md rename to docs/execution-providers/OpenVINO-ExecutionProvider.md index 58b4290ca8..c98e85c623 100644 --- a/docs/reference/execution-providers/OpenVINO-ExecutionProvider.md +++ b/docs/execution-providers/OpenVINO-ExecutionProvider.md @@ -1,7 +1,7 @@ --- title: OpenVINO parent: Execution Providers -grand_parent: Reference +nav_order: 10 --- # OpenVINO Execution Provider @@ -28,12 +28,12 @@ Pre-built packages and Docker images are published for ONNX Runtime with OpenVI |1.8.0|2021.3|[Details](https://github.com/intel/onnxruntime/releases/tag/2021.3)| ## Build -For build instructions, please see the [BUILD page](../../how-to/build/eps.md#openvino). +For build instructions, please see the [BUILD page](../build/eps.md#openvino). ## Usage **C#** -To use csharp api for openvino execution provider create a custom nuget package. Follow the instructions [here](../../how-to/build/inferencing.md#build-nuget-packages) to install prerequisites for nuget creation. Once prerequisites are installed follow the instructions to [build openvino](../../how-to/build/eps.md#openvino) and add an extra flag `--build_nuget` to create nuget packages. Two nuget packages will be created Microsoft.ML.OnnxRuntime.Managed and Microsoft.ML.OnnxRuntime.Openvino. +To use csharp api for openvino execution provider create a custom nuget package. Follow the instructions [here](../build/inferencing.md#build-nuget-packages) to install prerequisites for nuget creation. Once prerequisites are installed follow the instructions to [build openvino](../build/eps.md#openvino) and add an extra flag `--build_nuget` to create nuget packages. Two nuget packages will be created Microsoft.ML.OnnxRuntime.Managed and Microsoft.ML.OnnxRuntime.Openvino. ### Multi-threading for OpenVINO EP diff --git a/docs/reference/execution-providers/RKNPU-ExecutionProvider.md b/docs/execution-providers/RKNPU-ExecutionProvider.md similarity index 91% rename from docs/reference/execution-providers/RKNPU-ExecutionProvider.md rename to docs/execution-providers/RKNPU-ExecutionProvider.md index 1e3a41fa38..31efb0ed77 100644 --- a/docs/reference/execution-providers/RKNPU-ExecutionProvider.md +++ b/docs/execution-providers/RKNPU-ExecutionProvider.md @@ -1,7 +1,7 @@ --- title: RKNPU parent: Execution Providers -grand_parent: Reference +nav_order: 11 --- # RKNPU Execution Provider @@ -17,7 +17,7 @@ RKNPU DDK is an advanced interface to access Rockchip NPU. The RKNPU Execution P ## Build -For build instructions, please see the [BUILD page](../../how-to/build/eps.md#rknpu). +For build instructions, please see the [BUILD page](../build/eps.md#rknpu). ## Usage **C/C++** @@ -29,7 +29,7 @@ Ort::SessionOptions sf; Ort::ThrowOnError(OrtSessionOptionsAppendExecutionProvider_RKNPU(sf)); Ort::Session session(env, model_path, sf); ``` -The C API details are [here](../api/c-api.md). +The C API details are [here](../get-started/with-c.html.md). ## Support Coverage diff --git a/docs/reference/execution-providers/TensorRT-ExecutionProvider.md b/docs/execution-providers/TensorRT-ExecutionProvider.md similarity index 98% rename from docs/reference/execution-providers/TensorRT-ExecutionProvider.md rename to docs/execution-providers/TensorRT-ExecutionProvider.md index 0a8eccfceb..4ece654915 100644 --- a/docs/reference/execution-providers/TensorRT-ExecutionProvider.md +++ b/docs/execution-providers/TensorRT-ExecutionProvider.md @@ -1,7 +1,7 @@ --- title: TensorRT parent: Execution Providers -grand_parent: Reference +nav_order: 12 --- # TensorRT Execution Provider @@ -23,7 +23,7 @@ Pre-built packages and Docker images are available for Jetpack in the [Jetson Zo ## Build -See [Build instructions](../../how-to/build/eps.md#tensorrt). +See [Build instructions](../build/eps.md#tensorrt). The TensorRT execution provider for ONNX Runtime is built and tested with TensorRT 7.2.2. @@ -38,7 +38,7 @@ Ort::ThrowOnError(OrtSessionOptionsAppendExecutionProvider_CUDA(sf, device_id)); Ort::Session session(env, model_path, sf); ``` -The C API details are [here](../api/c-api.md). +The C API details are [here](../get-started/with-c.html.md). #### Shape Inference for TensorRT Subgraphs If some operators in the model are not supported by TensorRT, ONNX Runtime will partition the graph and only send supported subgraphs to TensorRT execution provider. Because TensorRT requires that all inputs of the subgraphs have shape specified, ONNX Runtime will throw error if there is no input shape info. In this case please run shape inference for the entire model first by running script [here](https://github.com/microsoft/onnxruntime/blob/master/onnxruntime/python/tools/symbolic_shape_infer.py). @@ -173,7 +173,7 @@ sess.set_providers(["TensorrtExecutionProvider"],[{'device_id': '1', 'trt_max_wo ``` ## Performance Tuning -For performance tuning, please see guidance on this page: [ONNX Runtime Perf Tuning](../../how-to/tune-performance.md) +For performance tuning, please see guidance on this page: [ONNX Runtime Perf Tuning](../tutorials/mobile/tune-performance.md) When/if using [onnxruntime_perf_test](https://github.com/microsoft/onnxruntime/tree/master/onnxruntime/test/perftest#onnxruntime-performance-test), use the flag `-e tensorrt` diff --git a/docs/reference/execution-providers/Vitis-AI-ExecutionProvider.md b/docs/execution-providers/Vitis-AI-ExecutionProvider.md similarity index 98% rename from docs/reference/execution-providers/Vitis-AI-ExecutionProvider.md rename to docs/execution-providers/Vitis-AI-ExecutionProvider.md index de9aa0900e..d0dd0afddf 100644 --- a/docs/reference/execution-providers/Vitis-AI-ExecutionProvider.md +++ b/docs/execution-providers/Vitis-AI-ExecutionProvider.md @@ -1,7 +1,7 @@ --- title: Vitis AI parent: Execution Providers -grand_parent: Reference +nav_order: 13 --- # Vitis-AI Execution Provider @@ -37,7 +37,7 @@ The following table lists system requirements for running docker containers as w | Docker Version | 19\.03\.1 | ## Build -See [Build instructions](../../how-to/build/eps.md#vitis-ai). +See [Build instructions](../build/eps.md#vitis-ai). **Hardware setup and docker build** diff --git a/docs/how-to/add-execution-provider.md b/docs/execution-providers/add-execution-provider.md similarity index 98% rename from docs/how-to/add-execution-provider.md rename to docs/execution-providers/add-execution-provider.md index 0aa1835d2f..70e1065b85 100644 --- a/docs/how-to/add-execution-provider.md +++ b/docs/execution-providers/add-execution-provider.md @@ -1,7 +1,7 @@ --- title: Add a new execution provider -parent: How to -nav_order: 7 +parent: Execution Providers +nav_order: 14 --- # Add a new Execution Provider to ONNX Runtime diff --git a/docs/reference/execution-providers/index.md b/docs/execution-providers/index.md similarity index 96% rename from docs/reference/execution-providers/index.md rename to docs/execution-providers/index.md index 6f5309caf4..6492cfa69a 100644 --- a/docs/reference/execution-providers/index.md +++ b/docs/execution-providers/index.md @@ -1,8 +1,7 @@ --- title: Execution Providers -parent: Reference has_children: true -nav_order: 2 +nav_order: 10 --- # ONNX Runtime Execution Providers @@ -36,11 +35,11 @@ ONNX Runtime supports many different execution providers today. Some of the EPs ### Add an Execution Provider -Developers of specialized HW acceleration solutions can integrate with ONNX Runtime to execute ONNX models on their stack. To create an EP to interface with ONNX Runtime you must first identify a unique name for the EP. Follow the steps outlined [here](../../how-to/add-execution-provider.md) to integrate your code in the repo. +Developers of specialized HW acceleration solutions can integrate with ONNX Runtime to execute ONNX models on their stack. To create an EP to interface with ONNX Runtime you must first identify a unique name for the EP. Follow the steps outlined [here](../execution-provider/add-execution-provider.md) to integrate your code in the repo. ### Build ONNX Runtime package with EPs -The ONNX Runtime package can be built with any combination of the EPs along with the default CPU execution provider. **Note** that if multiple EPs are combined into the same ONNX Runtime package then all the dependent libraries must be present in the execution environment. The steps for producing the ONNX Runtime package with different EPs is documented [here](../../how-to/build/inferencing.md#execution-providers). +The ONNX Runtime package can be built with any combination of the EPs along with the default CPU execution provider. **Note** that if multiple EPs are combined into the same ONNX Runtime package then all the dependent libraries must be present in the execution environment. The steps for producing the ONNX Runtime package with different EPs is documented [here](../build/inferencing.md#execution-providers). ### APIs for Execution Provider diff --git a/docs/reference/execution-providers/oneDNN-ExecutionProvider.md b/docs/execution-providers/oneDNN-ExecutionProvider.md similarity index 95% rename from docs/reference/execution-providers/oneDNN-ExecutionProvider.md rename to docs/execution-providers/oneDNN-ExecutionProvider.md index 9adecec5df..e0031bd6d3 100644 --- a/docs/reference/execution-providers/oneDNN-ExecutionProvider.md +++ b/docs/execution-providers/oneDNN-ExecutionProvider.md @@ -1,7 +1,7 @@ --- title: Intel oneDNN parent: Execution Providers -grand_parent: Reference +nav_order: 9 --- # oneDNN Execution Provider @@ -21,7 +21,7 @@ Intel and Microsoft have developed the DNNL Execution Provider (EP) for ONNX Run ## Build -For build instructions, please see the [BUILD page](../../how-to/build/eps.md#onednn). +For build instructions, please see the [BUILD page](../build/eps.md#onednn). ## Usage @@ -37,7 +37,7 @@ bool enable_cpu_mem_arena = true; Ort::ThrowOnError(OrtSessionOptionsAppendExecutionProvider_Dnnl(sf, enable_cpu_mem_arena)); ``` -The C API details are [here](../api/c-api.md). +The C API details are [here](../get-started/with-c.html.md). ### Python @@ -45,7 +45,7 @@ When using the python wheel from the ONNX Runtime built with DNNL execution prov ## Performance Tuning -For performance tuning, please see guidance on this page: [ONNX Runtime Perf Tuning](../../how-to/tune-performance.md) +For performance tuning, please see guidance on this page: [ONNX Runtime Perf Tuning](../performance/tune-performance.md) ### Subgraph Optimization diff --git a/docs/get-started/index.md b/docs/get-started/index.md new file mode 100644 index 0000000000..fbcf5888a2 --- /dev/null +++ b/docs/get-started/index.md @@ -0,0 +1,10 @@ +--- +title: Get Started +has_children: true +nav_order: 2 +--- +# Get Started +{: .no_toc } + + + diff --git a/docs/get-started/training-pytorch.md b/docs/get-started/training-pytorch.md new file mode 100644 index 0000000000..56d73cdb08 --- /dev/null +++ b/docs/get-started/training-pytorch.md @@ -0,0 +1,38 @@ +--- +title: ORT Training with PyTorch +parent: Get Started +nav_order: 10 +--- + +# Get started with ORT for Training API (PyTorch) +{: .no_toc } +The ORT Training API is a PyTorch frontend that implements the torch.nn.Module interface. + + +## ORT Training Example +In this example we will go over how to use ORT for Training a model with PyTorch. + +``` +pip install torch-ort +python -m torch_ort.configure +``` + +**Note**: This installs the default version of the `torch-ort` and `onnxruntime-training` packages that are mapped to specific versions of the CUDA libraries. Refer to the install options in [ONNXRUNTIME.ai](https://onnxruntime.ai). + + - Add ORTModule in the `train.py` +```python + from torch_ort import ORTModule + . + . + . + model = ORTModule(model) +``` + +## Contents +{: .no_toc } + +* TOC placeholder +{:toc} + +## Samples +[ONNX Runtime Training Examples](../tutorials/training) \ No newline at end of file diff --git a/docs/reference/api/c-api.md b/docs/get-started/with-c.md similarity index 97% rename from docs/reference/api/c-api.md rename to docs/get-started/with-c.md index 3f96593f96..caf8687546 100644 --- a/docs/reference/api/c-api.md +++ b/docs/get-started/with-c.md @@ -1,11 +1,10 @@ --- -title: C API -parent: API docs -grand_parent: Reference -nav_order: 1 +title: C +parent: Get Started +nav_exclude: true --- -# ONNX Runtime C API +# Get started with ORT for C {: .no_toc } ## Contents @@ -18,8 +17,8 @@ nav_order: 1 | Artifact | Description | Supported Platforms | |-----------|-------------|---------------------| -| [Microsoft.ML.OnnxRuntime](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime) | CPU (Release) |Windows, Linux, Mac, X64, X86 (Windows-only), ARM64 (Windows-only)...more details: [compatibility](../../resources/compatibility.md) | -| [Microsoft.ML.OnnxRuntime.Gpu](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.gpu) | GPU - CUDA (Release) | Windows, Linux, Mac, X64...more details: [compatibility](../../resources/compatibility.md) | +| [Microsoft.ML.OnnxRuntime](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime) | CPU (Release) |Windows, Linux, Mac, X64, X86 (Windows-only), ARM64 (Windows-only)...more details: [compatibility](../references/compatibility) | +| [Microsoft.ML.OnnxRuntime.Gpu](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.gpu) | GPU - CUDA (Release) | Windows, Linux, Mac, X64...more details: [compatibility](../references/compatibility) | | [Microsoft.ML.OnnxRuntime.DirectML](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.directml) | GPU - DirectML (Release) | Windows 10 1709+ | | [ort-nightly](https://aiinfra.visualstudio.com/PublicPackages/_packaging?_a=feed&feed=ORT-Nightly) | CPU, GPU (Dev) | Same as Release versions | @@ -48,7 +47,7 @@ Refer to [onnxruntime_c_api.h](https://github.com/microsoft/onnxruntime/blob/mas * Converting an in-memory ONNX Tensor encoded in protobuf format to a pointer that can be used as model input. * Setting the thread pool size for each session. * Setting graph optimization level for each session. -* Dynamically loading custom ops. [Instructions](../../how-to/add-custom-op.md) +* Dynamically loading custom ops. [Instructions](../tutorials/mobile/add-custom-op.md) * Ability to load a model from a byte array. See ```OrtCreateSessionFromArray``` in [onnxruntime_c_api.h](https://github.com/microsoft/onnxruntime/blob/master/include/onnxruntime/core/session/onnxruntime_c_api.h). * **Global/shared threadpools:** By default each session creates its own set of threadpools. In situations where multiple sessions need to be created (to infer different models) in the same process, you end up with several threadpools created @@ -111,4 +110,4 @@ To turn on/off telemetry collection on official Windows builds, please use Enabl ## Samples -See [Tutorials: API Basics - C](../../tutorials/inferencing/api-basics.md#c-1) +See [Tutorials: API Basics - C](../tutorials/api-basics) diff --git a/docs/reference/api/cpp-api.md b/docs/get-started/with-cpp.md similarity index 76% rename from docs/reference/api/cpp-api.md rename to docs/get-started/with-cpp.md index a28f845062..169c257696 100644 --- a/docs/reference/api/cpp-api.md +++ b/docs/get-started/with-cpp.md @@ -1,11 +1,10 @@ --- -title: C++ API -parent: API docs -grand_parent: Reference +title: C++ +parent: Get Started nav_order: 2 --- -# ONNX Runtime C++ API +# Get started with ORT for C++ {: .no_toc } ## Contents @@ -18,15 +17,15 @@ nav_order: 2 | Artifact | Description | Supported Platforms | |-----------|-------------|---------------------| -| [Microsoft.ML.OnnxRuntime](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime) | CPU (Release) |Windows, Linux, Mac, X64, X86 (Windows-only), ARM64 (Windows-only)...more details: [compatibility](../../resources/compatibility.md) | -| [Microsoft.ML.OnnxRuntime.Gpu](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.gpu) | GPU - CUDA (Release) | Windows, Linux, Mac, X64...more details: [compatibility](../../resources/compatibility.md) | +| [Microsoft.ML.OnnxRuntime](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime) | CPU (Release) |Windows, Linux, Mac, X64, X86 (Windows-only), ARM64 (Windows-only)...more details: [compatibility](../references/compatibility) | +| [Microsoft.ML.OnnxRuntime.Gpu](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.gpu) | GPU - CUDA (Release) | Windows, Linux, Mac, X64...more details: [compatibility](../references/compatibility) | | [Microsoft.ML.OnnxRuntime.DirectML](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.directml) | GPU - DirectML (Release) | Windows 10 1709+ | | [ort-nightly](https://aiinfra.visualstudio.com/PublicPackages/_packaging?_a=feed&feed=ORT-Nightly) | CPU, GPU (Dev) | Same as Release versions | .zip and .tgz files are also included as assets in each [Github release](https://github.com/microsoft/onnxruntime/releases). ## API Reference -The C++ API is a thin wrapper of the C API. Please refer to [C API](./c-api.html) for more details. +The C++ API is a thin wrapper of the C API. Please refer to [C API](./with-c.html) for more details. ## Samples -See [Tutorials: API Basics - C++](../../tutorials/inferencing/api-basics.md#c) \ No newline at end of file +See [Tutorials: API Basics - C++](../tutorials/api-basics) \ No newline at end of file diff --git a/docs/reference/api/csharp-api.md b/docs/get-started/with-csharp.md similarity index 54% rename from docs/reference/api/csharp-api.md rename to docs/get-started/with-csharp.md index 1e00ce2898..008d2038ac 100644 --- a/docs/reference/api/csharp-api.md +++ b/docs/get-started/with-csharp.md @@ -1,37 +1,71 @@ --- -title: C# API -parent: API docs -grand_parent: Reference -nav_order: 3 +title: C# +parent: Get Started +toc: true +nav_order: 2 --- - -# ONNX Runtime C# API +# Get started with ORT for C# {: .no_toc } -The ONNX runtime provides a C# .NET binding for running inference on ONNX models in any of the .NET standard platforms. - ## Contents {: .no_toc } * TOC placeholder {:toc} -## Supported Versions -.NET standard 1.1 +## Install the Nuget Packages with the .NET CLI -## Builds +```bash +dotnet add package Microsoft.ML.OnnxRuntime --version 1.2.0 +dotnet add package System.Numerics.Tensors --version 0.1.0 +``` -| Artifact | Description | Supported Platforms | -|-----------|-------------|---------------------| -| [Microsoft.ML.OnnxRuntime](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime) | CPU (Release) |Windows, Linux, Mac, X64, X86 (Windows-only), ARM64 (Windows-only)...more details: [compatibility](../../resources/compatibility.md) | -| [Microsoft.ML.OnnxRuntime.Gpu](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.gpu) | GPU - CUDA (Release) | Windows, Linux, Mac, X64...more details: [compatibility](../../resources/compatibility.md) | -| [Microsoft.ML.OnnxRuntime.DirectML](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.directml) | GPU - DirectML (Release) | Windows 10 1709+ | -| [ort-nightly](https://aiinfra.visualstudio.com/PublicPackages/_packaging?_a=feed&feed=ORT-Nightly) | CPU, GPU (Dev) | Same as Release versions | +## Import the libraries +```csharp +using Microsoft.ML.OnnxRuntime; +using System.Numerics.Tensors; +``` -## API Reference -[C# API Reference](./csharp-api-reference.html) +## Create method for inference +This is an [Azure Function](https://azure.microsoft.com/services/functions/) example that uses ORT with C# for inference on an NLP model created with SciKit Learn. + +```csharp + public static async Task Run( + [HttpTrigger(AuthorizationLevel.Function, "get", "post", Route = null)] HttpRequest req, + ILogger log, ExecutionContext context) + { + log.LogInformation("C# HTTP trigger function processed a request."); + + string review = req.Query["review"]; + + string requestBody = await new StreamReader(req.Body).ReadToEndAsync(); + dynamic data = JsonConvert.DeserializeObject(requestBody); + review = review ?? data?.review; + + // Get path to model to create inference session. + var modelPath = "./model.onnx"; + + // create input tensor (nlp example) + var inputTensor = new DenseTensor(new string[] { review }, new int[] { 1, 1 }); + + // Create input data for session. + var input = new List { NamedOnnxValue.CreateFromTensor("input", inputTensor) }; + + // Create an InferenceSession from the Model Path. + var session = new InferenceSession(modelPath); + + // Run session and send input data in to get inference output. Call ToList then get the Last item. Then use the AsEnumerable extension method to return the Value result as an Enumerable of NamedOnnxValue. + var output = session.Run(input).ToList().Last().AsEnumerable(); + + // From the Enumerable output create the inferenceResult by getting the First value and using the AsDictionary extension method of the NamedOnnxValue. + var inferenceResult = output.First().AsDictionary(); + + // Return the inference result as json. + return new JsonResult(inferenceResult); + } +``` ## Reuse input/output tensor buffers In some scenarios, you may want to reuse input/output tensors. This often happens when you want to chain 2 models (ie. feed one's output as input to another), or want to accelerate inference speed during multiple inference runs. @@ -65,7 +99,6 @@ using (var outputs1 = session1.Run(inputs1)) } } ``` - ### Multiple inference runs with fixed sized input(s) and output(s) If the model have fixed sized inputs and outputs of numeric tensors, you can use "FixedBufferOnnxValue" to accelerate the inference speed. By using "FixedBufferOnnxValue", the container objects only need to be allocated/disposed one time during multiple InferenceSession.Run() calls. This avoids some overhead which may be beneficial for smaller models where the time is noticeable in the overall running time. @@ -80,6 +113,32 @@ If using the GPU package, simply use the appropriate SessionOptions when creatin int gpuDeviceId = 0; // The GPU device ID to execute on var session = new InferenceSession("model.onnx", SessionOptions.MakeSessionOptionWithCudaProvider(gpuDeviceId)); ``` +# ONNX Runtime C# API +{: .no_toc } + +The ONNX runtime provides a C# .NET binding for running inference on ONNX models in any of the .NET standard platforms. + +## Supported Versions +.NET standard 1.1 + +## Builds + +| Artifact | Description | Supported Platforms | +|-----------|-------------|---------------------| +| [Microsoft.ML.OnnxRuntime](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime) | CPU (Release) |Windows, Linux, Mac, X64, X86 (Windows-only), ARM64 (Windows-only)...more details: [compatibility](../references/compatibility) | +| [Microsoft.ML.OnnxRuntime.Gpu](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.gpu) | GPU - CUDA (Release) | Windows, Linux, Mac, X64...more details: [compatibility](../references/compatibility) | +| [Microsoft.ML.OnnxRuntime.DirectML](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.directml) | GPU - DirectML (Release) | Windows 10 1709+ | +| [ort-nightly](https://aiinfra.visualstudio.com/PublicPackages/_packaging?_a=feed&feed=ORT-Nightly) | CPU, GPU (Dev) | Same as Release versions | + + +## API Reference +[C# API Reference](../api/csharp-api) + ## Samples -See [Tutorials: Basics - C#](../../tutorials/inferencing/api-basics.md#c-2) +See [Tutorials: Basics - C#](../tutorials/api-basics) + + +## Learn More +- [C# Tutorials](../tutorials/) +- [C# API Reference](../api/csharp-api.html) \ No newline at end of file diff --git a/docs/get-started/with-iot.md b/docs/get-started/with-iot.md new file mode 100644 index 0000000000..943d04863d --- /dev/null +++ b/docs/get-started/with-iot.md @@ -0,0 +1,11 @@ +--- +title: IoT and Edge +parent: Get Started +toc: true +nav_order: 8 +--- +# Get Started with ORT for IoT +{: .no_toc } + + * [Jetson Nano embedded device: Fast model inferencing](https://github.com/Azure-Samples/onnxruntime-iot-edge/blob/master/README-ONNXRUNTIME-arm64.md) +* [Intel VPU edge device with OpenVINO: Deploy small quantized model](https://github.com/Azure-Samples/onnxruntime-iot-edge/blob/master/README-ONNXRUNTIME-OpenVINO.md) \ No newline at end of file diff --git a/docs/reference/api/java-api.md b/docs/get-started/with-java.md similarity index 98% rename from docs/reference/api/java-api.md rename to docs/get-started/with-java.md index 8a830f095f..acdaa521ea 100644 --- a/docs/reference/api/java-api.md +++ b/docs/get-started/with-java.md @@ -1,11 +1,10 @@ --- -title: Java API -parent: API docs -grand_parent: Reference +title: Java +parent: Get Started +toc: true nav_order: 4 ---- - -# ONNX Runtime Java API +--- +# Get Started with ORT for Java {: .no_toc } The ONNX runtime provides a Java binding for running inference on ONNX models on a JVM. diff --git a/docs/get-started/with-javascript.md b/docs/get-started/with-javascript.md new file mode 100644 index 0000000000..0ed8b30090 --- /dev/null +++ b/docs/get-started/with-javascript.md @@ -0,0 +1,104 @@ +--- +title: JavaScript +parent: Get Started +toc: true +nav_order: 3 +--- + +# Get started with ORT for JavaScript +{: .no_toc } + +ONNX Runtime JavaScript API is the unified interface used by [ONNX Runtime Node.js binding](https://github.com/microsoft/onnxruntime/tree/master/js/node), [ONNX Runtime Web](https://github.com/microsoft/onnxruntime/tree/master/js/web) and [ONNX Runtime for React Native](https://github.com/microsoft/onnxruntime/tree/master/js/react_native). + +## Contents +{: .no_toc } + +* TOC placeholder +{:toc} + +## JavaScript Examples (Install and import) + +### Web ORT (client) + +```bash +npm install onnxruntime-web +``` +```javascript +const ort = require('onnxruntime-web'); +``` + +### Node ORT (server) + +```bash +npm install onnxruntime-node +``` +```javascript +const ort = require('onnxruntime-node'); +``` + +### React Native ORT + +```bash +npm install onnxruntime-react-native +``` +```javascript +const ort = require('onnxruntime-react-native'); +``` + +### JavaScript Usage Example +```javascript +// use an async context to call onnxruntime functions. +async function main() { + try { + // create a new session and load the specific model. + // + // the model in this example contains a single MatMul node + // it has 2 inputs: 'a'(float32, 3x4) and 'b'(float32, 4x3) + // it has 1 output: 'c'(float32, 3x3) + const session = await ort.InferenceSession.create('./model.onnx'); + + // prepare inputs. a tensor need its corresponding TypedArray as data + const dataA = Float32Array.from([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]); + const dataB = Float32Array.from([10, 20, 30, 40, 50, 60, 70, 80, 90, 100, 110, 120]); + const tensorA = new ort.Tensor('float32', dataA, [3, 4]); + const tensorB = new ort.Tensor('float32', dataB, [4, 3]); + + // prepare feeds. use model input names as keys. + const feeds = { a: tensorA, b: tensorB }; + + // feed inputs and run + const results = await session.run(feeds); + + // read from results + const dataC = results.c.data; + document.write(`data of result tensor 'c': ${dataC}`); + + } catch (e) { + document.write(`failed to inference ONNX model: ${e}.`); + } +} + +``` + +## Supported Versions + +- ONNX Runtime Node.js binding: Node.js v12.x+ or Electron v5.x+ +- ONNX Runtime Web: mainstream modern browsers on Windows, macOS, Android and iOS. +- ONNX Runtime for React Native: same as [ORT Mobile](./with-mobile) (Android/iOS) + +## Builds + +Builds are published to **npm** and can be installed using `npm install` + +| Package | Artifact | Description | Supported Platforms | +|---------|-----------|-------------|---------------------| +|Node.js binding|[onnxruntime-node](https://www.npmjs.com/package/onnxruntime-node)|CPU (Release)| Windows x64 CPU NAPI_v3, Linux x64 CPU NAPI_v3, MacOS x64 CPU NAPI_v3| +|Web|[onnxruntime-web](https://www.npmjs.com/package/onnxruntime-web)|CPU and GPU|Browsers (wasm, webgl), Node.js (wasm)| +|React Native|[onnxruntime-react-native](https://www.npmjs.com/package/onnxruntime-react-native)|CPU|Android, iOS| + +For Node.js binding, to use on platforms without pre-built binaries, you can [build Node.js binding from source](../build/inferencing.md#apis-and-language-bindings) and consume using `npm install /js/node/`. + +## API Reference +See Typescript declarations for [Inference Session](https://github.com/microsoft/onnxruntime/blob/master/js/common/lib/inference-session.ts), [Tensor](https://github.com/microsoft/onnxruntime/blob/master/js/common/lib/tensor.ts) and [Environment Flags](https://github.com/microsoft/onnxruntime/blob/master/js/common/lib/env.ts) for reference. + +See also [ONNX Runtime JavaScript examples](https://github.com/microsoft/onnxruntime-inference-examples/tree/main/js). diff --git a/docs/get-started/with-mobile.md b/docs/get-started/with-mobile.md new file mode 100644 index 0000000000..ddc1af21e5 --- /dev/null +++ b/docs/get-started/with-mobile.md @@ -0,0 +1,49 @@ +--- +title: Mobile +parent: Get Started +toc: true +nav_order: 7 +--- +# Get Started with ORT for Mobile +{: .no_toc } + +The API for executing ORT format models is the same as for ONNX models. + +See the [ONNX Runtime API documentation](../api) for details on individual API usage. + +## APIs by platform + + +| Platform | Available APIs | +|----------|----------------| +| Android | C, C++, Java | +| iOS | C, C++, Objective-C (Swift via bridge) | + +## ORT format model loading + +If you provide a filename for the ORT format model, a file extension of '.ort' will be inferred to be an ORT format model. + +If you provide in-memory bytes for the ORT format model, a marker in those bytes will be checked to infer if it's an ORT format model. + +If you wish to explicitly say that the InferenceSession input is an ORT format model you can do so via SessionOptions, although this generally should not be necessary. + +C++ API +```c++ +Ort::SessionOptions session_options; +session_options.AddConfigEntry('session.load_model_format', 'ORT'); + +Ort::Env env; +Ort::Session session(env, , session_options); +``` + +Java API +```java +SessionOptions session_options = new SessionOptions(); +session_options.addConfigEntry("session.load_model_format", "ORT"); + +OrtEnvironment env = OrtEnvironment.getEnvironment(); +OrtSession session = env.createSession(, opsession_optionstions); +``` + +## Learn More +- [Mobile Tutorial](./Tutorials/Mobile/) \ No newline at end of file diff --git a/docs/reference/api/objectivec-api.md b/docs/get-started/with-obj-c.md similarity index 73% rename from docs/reference/api/objectivec-api.md rename to docs/get-started/with-obj-c.md index 5ff1d30e37..e991697fba 100644 --- a/docs/reference/api/objectivec-api.md +++ b/docs/get-started/with-obj-c.md @@ -1,11 +1,9 @@ --- -title: Objective-C API -parent: API docs -grand_parent: Reference -nav_order: 6 +title: Objective-C +parent: Get Started +nav_exclude: true --- - -# ONNX Runtime Objective-C API +# Get started with ORT for Objective-C {: .no_toc } ONNX Runtime provides an Objective-C API for running ONNX models on iOS devices. @@ -28,7 +26,7 @@ The artifacts are published to CocoaPods. |-|-|-| | onnxruntime-mobile-objc | CPU and CoreML | iOS | -Refer to the [installation instructions](../../how-to/mobile/initial-setup.md#iOS). +Refer to the [installation instructions](../tutorials/mobile/mobile/initial-setup.md#iOS). ## Swift Usage @@ -42,8 +40,8 @@ To enable this, use a bridging header (more info [here](https://developer.apple. ## API Reference -[Objective-C API Reference](../../../objectivec/index.html) +[Objective-C API Reference](../api/objectivec/index.html) ## Samples -See the iOS examples [here](https://github.com/microsoft/onnxruntime-inference-examples/tree/main/mobile). +See the iOS examples [here](https://github.com/microsoft/onnxruntime-inference-examples/tree/main/mobile). \ No newline at end of file diff --git a/docs/get-started/with-python.md b/docs/get-started/with-python.md new file mode 100644 index 0000000000..a9d201ba3f --- /dev/null +++ b/docs/get-started/with-python.md @@ -0,0 +1,255 @@ +--- +title: Python +parent: Get Started +toc: true +nav_order: 1 +--- +# Get started with ORT for Python +{: .no_toc } + +Below is a quick guide to get the packages installed to use ONNX for model serialization and infernece with ORT. + +## Contents +{: .no_toc } + +* TOC placeholder +{:toc} + + +## Install ONNX Runtime (ORT) + +```python +pip install onnxruntime +``` + +## Install ONNX for model export + + +```python +## ONNX is built into PyTorch +pip install torch +``` +```python +## tensorflow +pip install tf2onnx +``` +```python +## sklearn +pip install skl2onnx +``` + +## Quickstart Examples for PyTorch, TensorFlow, and SciKit Learn +Train a model using your favorite framework, export to ONNX format and inference in any supported ONNX Runtime language! + +### PyTorch CV +{: .no_toc } +In this example we will go over how to export a PyTorch CV model into ONNX format and then inference with ORT. The code to create the model is from the [PyTorch Fundamentals learning path on Microsoft Learn](https://aka.ms/learnpytorch). + +- Export the model using `torch.onnx.export` + +```python +torch.onnx.export(model, # model being run + torch.randn(1, 28, 28).to(device), # model input (or a tuple for multiple inputs) + "fashion_mnist_model.onnx", # where to save the model (can be a file or file-like object) + input_names = ['input'], # the model's input names + output_names = ['output']) # the model's output names +``` +- Load the onnx model with `onnx.load` +```python +import onnx +onnx_model = onnx.load("fashion_mnist_model.onnx") +onnx.checker.check_model(onnx_model) +``` +- Create inference session using `ort.InferenceSession` + +```python +import onnxruntime as ort +import numpy as np +x, y = test_data[0][0], test_data[0][1] +ort_sess = ort.InferenceSession('fashion_mnist_model.onnx') +outputs = ort_sess.run(None, {'input': x.numpy()}) + +# Print Result +predicted, actual = classes[outputs[0][0].argmax(0)], classes[y] +print(f'Predicted: "{predicted}", Actual: "{actual}"') +``` + +### PyTorch NLP +{: .no_toc } +In this example we will go over how to export a PyTorch NLP model into ONNX format and then inference with ORT. The code to create the AG News model is from [this PyTorch tutorial](https://pytorch.org/tutorials/beginner/text_sentiment_ngrams_tutorial.html). + +- Process text and create the sample data input and offsets for export. +```python +import torch +text = "Text from the news article" +text = torch.tensor(text_pipeline(text)) +offsets = torch.tensor([0]) +``` +- Export Model +```python +# Export the model +torch.onnx.export(model, # model being run + (text, offsets), # model input (or a tuple for multiple inputs) + "ag_news_model.onnx", # where to save the model (can be a file or file-like object) + export_params=True, # store the trained parameter weights inside the model file + opset_version=10, # the ONNX version to export the model to + do_constant_folding=True, # whether to execute constant folding for optimization + input_names = ['input', 'offsets'], # the model's input names + output_names = ['output'], # the model's output names + dynamic_axes={'input' : {0 : 'batch_size'}, # variable length axes + 'output' : {0 : 'batch_size'}}) +``` +- Load the model using `onnx.load` +```python +import onnx +onnx_model = onnx.load("ag_news_model.onnx") +onnx.checker.check_model(onnx_model) +``` + +- Create inference session with `ort.infernnce` +```python +import onnxruntime as ort +import numpy as np +ort_sess = ort.InferenceSession('ag_news_model.onnx') +outputs = ort_sess.run(None, {'input': text.numpy(), + 'offsets': torch.tensor([0]).numpy()}) +# Print Result +result = outputs[0].argmax(axis=1)+1 +print("This is a %s news" %ag_news_label[result[0]]) +``` + +### TensorFlow CV +{: .no_toc } +In this example we will go over how to export a TensorFlow CV model into ONNX format and then inference with ORT. The model used is from this [GitHub Notebook for Keras resnet50](https://github.com/onnx/tensorflow-onnx/blob/master/tutorials/keras-resnet50.ipynb). + +- Get the pretrained model + +```python +import os +import tensorflow as tf +from tensorflow.keras.applications.resnet50 import ResNet50 +import onnxruntime + +model = ResNet50(weights='imagenet') + +preds = model.predict(x) +print('Keras Predicted:', decode_predictions(preds, top=3)[0]) +model.save(os.path.join("/tmp", model.name)) +``` +- Convert the model to onnx and export + +```python +import tf2onnx +import onnxruntime as rt + +spec = (tf.TensorSpec((None, 224, 224, 3), tf.float32, name="input"),) +output_path = model.name + ".onnx" + +model_proto, _ = tf2onnx.convert.from_keras(model, input_signature=spec, opset=13, output_path=output_path) +output_names = [n.name for n in model_proto.graph.output] +``` +- Create inference session with `rt.infernnce` + +```python +providers = ['CPUExecutionProvider'] +m = rt.InferenceSession(output_path, providers=providers) +onnx_pred = m.run(output_names, {"input": x}) + +print('ONNX Predicted:', decode_predictions(onnx_pred[0], top=3)[0]) +``` + +### SciKit Learn CV +{: .no_toc } +In this example we will go over how to export a SciKit Learn CV model into ONNX format and then inference with ORT. We’ll use the famous iris datasets. + +```python +from sklearn.datasets import load_iris +from sklearn.model_selection import train_test_split +iris = load_iris() +X, y = iris.data, iris.target +X_train, X_test, y_train, y_test = train_test_split(X, y) + +from sklearn.linear_model import LogisticRegression +clr = LogisticRegression() +clr.fit(X_train, y_train) +print(clr) + +LogisticRegression() +``` + +- Convert or export the model into ONNX format + +```python + +from skl2onnx import convert_sklearn +from skl2onnx.common.data_types import FloatTensorType + +initial_type = [('float_input', FloatTensorType([None, 4]))] +onx = convert_sklearn(clr, initial_types=initial_type) +with open("logreg_iris.onnx", "wb") as f: + f.write(onx.SerializeToString()) +``` + + +- Load and run the model using ONNX Runtime +We will use ONNX Runtime to compute the predictions for this machine learning model. + +```python + +import numpy +import onnxruntime as rt + +sess = rt.InferenceSession("logreg_iris.onnx") +input_name = sess.get_inputs()[0].name +pred_onx = sess.run(None, {input_name: X_test.astype(numpy.float32)})[0] +print(pred_onx) + +OUTPUT: + [0 1 0 0 1 2 2 0 0 2 1 0 2 2 1 1 2 2 2 0 2 2 1 2 1 1 1 0 2 1 1 1 1 0 1 0 0 + 1] +``` + +- Get predicted class + +The code can be changed to get one specific output by specifying its name into a list. + +```python +import numpy +import onnxruntime as rt + +sess = rt.InferenceSession("logreg_iris.onnx") +input_name = sess.get_inputs()[0].name +label_name = sess.get_outputs()[0].name +pred_onx = sess.run( + [label_name], {input_name: X_test.astype(numpy.float32)})[0] +print(pred_onx) + +``` + +## Python API Reference Docs + + [Go to the ORT Python API Docs](../api/python/api_summary.html){: .btn .mr-4 target="_blank"} + +## Builds +If using pip, run pip install `--upgrade pip` prior to downloading. + +| Artifact | Description | Supported Platforms | +|----------- |-------------|---------------------| +|[onnxruntime](https://pypi.org/project/onnxruntime)|CPU (Release)| Windows (x64), Linux (x64, ARM64), Mac (X64), | +|[ort-nightly](https://test.pypi.org/project/ort-nightly)|CPU (Dev) | Same as above | +|[onnxruntime-gpu](https://pypi.org/project/onnxruntime-gpu)|GPU (Release)| Windows (x64), Linux (x64, ARM64) | +|[ort-gpu-nightly](https://test.pypi.org/project/ort-gpu-nightly)|GPU (Dev) | Same as above | + + +For Python compiler version notes, see [this page](https://github.com/microsoft/onnxruntime/tree/master/docs/Python_Dev_Notes.md) + + +## Supported Versions +Python 3.6 - 3.9 + +## Learn More +- [Python Tutorials](../tutorials/api-basics) +* [TensorFlow with ONNX Runtime](../tutorials/tf-get-started.md) +* [PyTorch with ONNX Runtime](https://pytorch.org/tutorials/advanced/super_resolution_with_onnxruntime.html) +* [scikit-learn with ONNX Runtime](https://www.onnxruntime.ai/python/tutorial.html) + \ No newline at end of file diff --git a/docs/reference/api/winrt-api.md b/docs/get-started/with-winrt.md similarity index 91% rename from docs/reference/api/winrt-api.md rename to docs/get-started/with-winrt.md index 276dd69a8a..67651a44ac 100644 --- a/docs/reference/api/winrt-api.md +++ b/docs/get-started/with-winrt.md @@ -1,11 +1,12 @@ --- -title: WinRT API -parent: API docs -grand_parent: Reference -nav_order: 8 +title: WinRT +parent: Get Started +toc: true +nav_order: 10 --- -# Windows Machine Learning WinRT API + +# Get started with ORT for Windows Machine Learning WinRT {: .no_toc } The ONNX Runtime Nuget package provides the ability to use the full [WinML API](https://docs.microsoft.com/en-us/windows/ai/windows-ml/api-reference). @@ -13,7 +14,7 @@ This allows scenarios such as passing a [Windows.Media.VideoFrame](https://docs. The WinML API is a WinRT API that shipped inside the Windows OS starting with build 1809 (RS5) in the Windows.AI.MachineLearning namespace. It embedded a version of the ONNX Runtime. -In addition to using the in-box version of WinML, WinML can also be installed as an application redistributable package (see [layered architecture](../../resources/high-level-design.md#the-onnx-runtime-and-windows-os-integration) for technical details). +In addition to using the in-box version of WinML, WinML can also be installed as an application redistributable package (see [layered architecture](../references/high-level-design.md#the-onnx-runtime-and-windows-os-integration) for technical details). ## Contents {: .no_toc } diff --git a/docs/how-to/build/web.md b/docs/how-to/build/web.md deleted file mode 100644 index c5e3f73d46..0000000000 --- a/docs/how-to/build/web.md +++ /dev/null @@ -1,10 +0,0 @@ ---- -title: Build for web -parent: Build ORT -nav_order: 4 -grand_parent: How to ---- - -# Build ONNX Runtime for Web - - *[COMING SOON]* diff --git a/docs/how-to/index.md b/docs/how-to/index.md deleted file mode 100644 index f7b4f1f79e..0000000000 --- a/docs/how-to/index.md +++ /dev/null @@ -1,8 +0,0 @@ ---- -title: How to -has_children: true -nav_order: 3 ---- - -# ONNX Runtime how-to guides -{: .no_toc } \ No newline at end of file diff --git a/docs/index.md b/docs/index.md index ea95d80900..772188bee0 100644 --- a/docs/index.md +++ b/docs/index.md @@ -1,25 +1,31 @@ --- -title: ONNX Runtime +title: ONNX Runtime (ORT) has_children: false -nav_order: 1 +nav_order: 0 --- -# Welcome to ONNX Runtime +# Welcome to ONNX Runtime (ORT) {: .no_toc } ONNX Runtime is an accelerator for machine learning models with multi platform support and a flexible interface to integrate with hardware-specific libraries. ONNX Runtime can be used with models from PyTorch, Tensorflow/Keras, TFLite, scikit-learn, and other frameworks. -## Contents -{: .no_toc } + -* TOC placeholder -{:toc} +## How to use ONNX Runtime (ORT) +|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| +| [Get started with ORT](./get-started){: .btn .mr-4 target="_blank"} | [API Docs](./api){: .btn target="_blank"} | +| [Tutorials](./tutorials){: .btn target="_blank"} | [Ecosystem](./ecosystem){: .btn target="_blank"} | + +## Contribute and Customize + +|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| +| [Build ORT Packages](./build){: .btn .mr-4 target="_blank"} | [ORT GitHub](https://github.com/microsoft/onnxruntime){: .btn target="_blank"} | + + +--- ## ONNX Runtime for Inferencing - -**>> [Get started with ORT for inferencing](./tutorials/inferencing) <<** - ONNX Runtime Inference powers machine learning models in key Microsoft products and services across Office, Azure, Bing, as well as dozens of community projects. Examples use cases for ONNX Runtime Inferencing include: @@ -33,20 +39,19 @@ Examples use cases for ONNX Runtime Inferencing include: {: .no_toc } The premise is simple. -1. **Get a model.** This can be trained from any framework that supports export/conversion to ONNX format. See the [tutorials](./tutorials/inferencing) for some of the popular frameworks/libraries. -2. **Load and run the model with ONNX Runtime.** See the [basic tutorials](./tutorials/inferencing/api-basics.md) for running models in different languages. -3. ***(Optional)* Tune performance using various runtime configurations or hardware accelerators.** There are lots of options here - see [How to: Tune Performance](./how-to/tune-performance.md) as a starting point. +1. **Get a model.** This can be trained from any framework that supports export/conversion to ONNX format. See the [tutorials](./tutorials) for some of the popular frameworks/libraries. +2. **Load and run the model with ONNX Runtime.** See the [basic tutorials](./tutorials/api-basics) for running models in different languages. +3. ***(Optional)* Tune performance using various runtime configurations or hardware accelerators.** There are lots of options here - see [How to: Tune Performance](./performance/tune-performance.md) as a starting point. Even without step 3, ONNX Runtime will often provide performance improvements compared to the original framework. -ONNX Runtime applies a number of graph optimizations on the model graph then partitions it into subgraphs based on available hardware-specific accelerators. Optimized computation kernels in core ONNX Runtime provide performance improvements and assigned subgraphs benefit from further acceleration from each [Execution Provider](./reference/execution-providers). +ONNX Runtime applies a number of graph optimizations on the model graph then partitions it into subgraphs based on available hardware-specific accelerators. Optimized computation kernels in core ONNX Runtime provide performance improvements and assigned subgraphs benefit from further acceleration from each [Execution Provider](./execution-providers). --- ## ONNX Runtime for Training -**>> [Get started with ORT for training](./tutorials/training) <<** Released in April 2021, ONNX Runtime Training provides a one-line addition for existing PyTorch training scripts to accelerate training times. The current support is focused on large transformer models on multi-node NVIDIA GPUs, with more to come. @@ -57,30 +62,3 @@ Using the ORTModule class wrapper, ONNX Runtime for PyTorch runs the forward an The ORTModule is instantiated from [`torch-ort`](https://github.com/pytorch/ort) backend in PyTorch. This new interface enables a seamless integration for ONNX Runtime training in a PyTorch training code with minimal changes to the existing code. -### Install ONNX Runtime Training package - -``` -pip install torch-ort -python -m torch_ort.configure -``` - -**Note**: This installs the default version of the `torch-ort` and `onnxruntime-training` packages that are mapped to specific versions of the CUDA libraries. Refer to the install options in [ONNXRUNTIME.ai](https://onnxruntime.ai). - -### Add ORTModule in the `train.py` - -```python - from torch_ort import ORTModule - . - . - . - model = ORTModule(model) -``` - -**Note**: the `model` where ORTModule is wrapped needs to be a derived from the `torch.nn.Module` class. - - - - - - - diff --git a/docs/how-to/install.md b/docs/install/index.md similarity index 66% rename from docs/how-to/install.md rename to docs/install/index.md index 1fd53e4e4c..e97acc7f75 100644 --- a/docs/how-to/install.md +++ b/docs/install/index.md @@ -1,15 +1,16 @@ --- title: Install ORT -parent: How to +has_children: false nav_order: 1 --- -# Install ONNX Runtime +# Install ONNX Runtime (ORT) {: .no_toc } See the [installation matrix](https://onnxruntime.ai) for recommended instructions for desired combinations of target operating system, hardware, accelerator, and language. -Details on OS versions, compilers, language versions, dependent libraries, etc can be found under [Compatibility](../resources/compatibility.md#Environment-compatibility). +Details on OS versions, compilers, language versions, dependent libraries, etc can be found under [Compatibility](../reference/compatibility). + ## Contents {: .no_toc } @@ -17,9 +18,105 @@ Details on OS versions, compilers, language versions, dependent libraries, etc c * TOC placeholder {:toc} -## Inference +## Python Installs -The table below lists the build variants available as officially supported packages. Others can be [built from source](../how-to/build/inferencing.md) from each release branch. +### Install ONNX Runtime (ORT) +{: .no_toc } + +```bash +pip install onnxruntime +``` + +```bash +pip install onnxruntime-gpu +``` + +### Install ONNX to export the model +{: .no_toc } + +```bash +## ONNX is built into PyTorch +pip install torch +``` +```python +## tensorflow +pip install tf2onnx +``` + +```bash +## sklearn +pip install skl2onnx +``` + +## C#/C/C++/WinML Installs + +### Install ONNX Runtime (ORT) +{: .no_toc } + +```bash +# CPU +dotnet add package Microsoft.ML.OnnxRuntime --version 1.8.1 +``` +```bash +# GPU +dotnet add package Microsoft.ML.OnnxRuntime.Gpu --version 1.8.1 +``` +```bash +# DirectML +dotnet add package Microsoft.ML.OnnxRuntime.DirectML --version 1.8.1 +``` + +```bash +# WinML +dotnet add package Microsoft.AI.MachineLearning --version 1.8.1 +``` +## JavaScript Installs + +### Web ORT (client) +{: .no_toc } + +```bash +npm install onnxruntime-web +``` + +### Node ORT (server) +{: .no_toc } + +```bash +npm install onnxruntime-node +``` + +### React Native ORT +{: .no_toc } + +```bash +npm install onnxruntime-react-native +``` + +## ORT Training package + +``` +pip install torch-ort +python -m torch_ort.configure +``` + +**Note**: This installs the default version of the `torch-ort` and `onnxruntime-training` packages that are mapped to specific versions of the CUDA libraries. Refer to the install options in [ONNXRUNTIME.ai](https://onnxruntime.ai). + +### Add ORTModule in the `train.py` + +```python + from torch_ort import ORTModule + . + . + . + model = ORTModule(model) +``` + +**Note**: the `model` where ORTModule is wrapped needs to be a derived from the `torch.nn.Module` class. + +## Inference install table for all languages + +The table below lists the build variants available as officially supported packages. Others can be [built from source](../build/inferencing) from each release branch. ### Requirements {: .no_toc } @@ -35,21 +132,21 @@ by running `locale-gen en_US.UTF-8` and `update-locale LANG=en_US.UTF-8` |---|---|---|---| |Python|If using pip, run `pip install --upgrade pip` prior to downloading.||| ||CPU: [**onnxruntime**](https://pypi.org/project/onnxruntime)| [ort-nightly (dev)](https://test.pypi.org/project/ort-nightly)|| -||GPU - CUDA: [**onnxruntime-gpu**](https://pypi.org/project/onnxruntime-gpu) | [ort-nightly-gpu (dev)](https://test.pypi.org/project/ort-nightly-gpu)|[View](../reference/execution-providers/CUDA-ExecutionProvider.md#requirements)| -||OpenVINO: [**intel/onnxruntime**](https://github.com/intel/onnxruntime/releases/latest) - *Intel managed*||[View](../how-to/build/eps.md#openvino)| +||GPU - CUDA: [**onnxruntime-gpu**](https://pypi.org/project/onnxruntime-gpu) | [ort-nightly-gpu (dev)](https://test.pypi.org/project/ort-nightly-gpu)|[View](../execution-providers/CUDA-ExecutionProvider.md#requirements)| +||OpenVINO: [**intel/onnxruntime**](https://github.com/intel/onnxruntime/releases/latest) - *Intel managed*||[View](build/eps.md#openvino)| ||TensorRT (Jetson): [**Jetson Zoo**](https://elinux.org/Jetson_Zoo#ONNX_Runtime) - *NVIDIA managed*||| |C#/C/C++|CPU: [**Microsoft.ML.OnnxRuntime**](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime) |[ort-nightly (dev)](https://aiinfra.visualstudio.com/PublicPackages/_packaging?_a=feed&feed=ORT-Nightly)|| -||GPU - CUDA: [**Microsoft.ML.OnnxRuntime.Gpu**](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.gpu)|[ort-nightly (dev)](https://aiinfra.visualstudio.com/PublicPackages/_packaging?_a=feed&feed=ORT-Nightly)|[View](../reference/execution-providers/CUDA-ExecutionProvider.md#requirements)| -||GPU - DirectML: [**Microsoft.ML.OnnxRuntime.DirectML**](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.DirectML)|[ort-nightly (dev)](https://aiinfra.visualstudio.com/PublicPackages/_packaging?_a=feed&feed=ORT-Nightly)|[View](../reference/execution-providers/DirectML-ExecutionProvider.md#requirements)| +||GPU - CUDA: [**Microsoft.ML.OnnxRuntime.Gpu**](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.gpu)|[ort-nightly (dev)](https://aiinfra.visualstudio.com/PublicPackages/_packaging?_a=feed&feed=ORT-Nightly)|[View](../execution-providers/CUDA-ExecutionProvider)| +||GPU - DirectML: [**Microsoft.ML.OnnxRuntime.DirectML**](https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.DirectML)|[ort-nightly (dev)](https://aiinfra.visualstudio.com/PublicPackages/_packaging?_a=feed&feed=ORT-Nightly)|[View](../execution-providers/DirectML-ExecutionProvider)| |WinML|[**Microsoft.AI.MachineLearning**](https://www.nuget.org/packages/Microsoft.AI.MachineLearning)||[View](https://docs.microsoft.com/en-us/windows/ai/windows-ml/port-app-to-nuget#prerequisites)| -|Java|CPU: [**com.microsoft.onnxruntime:onnxruntime**](https://search.maven.org/artifact/com.microsoft.onnxruntime/onnxruntime)||[View](../reference/api/java-api.md)| -||GPU - CUDA: [**com.microsoft.onnxruntime:onnxruntime_gpu**](https://search.maven.org/artifact/com.microsoft.onnxruntime/onnxruntime_gpu)||[View](../reference/api/java-api.md)| -|Android|[**com.microsoft.onnxruntime:onnxruntime-mobile**](https://search.maven.org/artifact/com.microsoft.onnxruntime/onnxruntime-mobile) ||[View](../how-to/mobile/initial-setup.md#android)| -|iOS (C/C++)|CocoaPods: **onnxruntime-mobile-c**||[View](../how-to/mobile/initial-setup.md#ios)| -|Objective-C|CocoaPods: **onnxruntime-mobile-objc**||[View](../how-to/mobile/initial-setup.md#ios)| -|React Native|[**onnxruntime-react-native**](https://www.npmjs.com/package/onnxruntime-react-native)||[View](../reference/api/js-api.md)| -|Node.js|[**onnxruntime-node**](https://www.npmjs.com/package/onnxruntime-node)||[View](../reference/api/js-api.md)| -|Web|[**onnxruntime-web**](https://www.npmjs.com/package/onnxruntime-web)||[View](../reference/api/js-api.md)| +|Java|CPU: [**com.microsoft.onnxruntime:onnxruntime**](https://search.maven.org/artifact/com.microsoft.onnxruntime/onnxruntime)||[View](../api/java-api.md)| +||GPU - CUDA: [**com.microsoft.onnxruntime:onnxruntime_gpu**](https://search.maven.org/artifact/com.microsoft.onnxruntime/onnxruntime_gpu)||[View](../api/java-api.md)| +|Android|[**com.microsoft.onnxruntime:onnxruntime-mobile**](https://search.maven.org/artifact/com.microsoft.onnxruntime/onnxruntime-mobile) ||[View](tutorials/mobile/mobile/initial-setup)| +|iOS (C/C++)|CocoaPods: **onnxruntime-mobile-c**||[View](tutorials/mobile/mobile/initial-setup)| +|Objective-C|CocoaPods: **onnxruntime-mobile-objc**||[View](tutorials/mobile/mobile/initial-setup)| +|React Native|[**onnxruntime-react-native**](https://www.npmjs.com/package/onnxruntime-react-native)||[View](../api/js-api.md)| +|Node.js|[**onnxruntime-node**](https://www.npmjs.com/package/onnxruntime-node)||[View](../api/js-api.md)| +|Web|[**onnxruntime-web**](https://www.npmjs.com/package/onnxruntime-web)||[View](../api/js-api.md)| @@ -58,7 +155,7 @@ by running `locale-gen en_US.UTF-8` and `update-locale LANG=en_US.UTF-8` -## Training +## Training install table for all languages ONNX Runtime Training packages are available for different versions of PyTorch, CUDA and ROCm versions. diff --git a/docs/resources/graph-optimizations.md b/docs/performance/graph-optimizations.md similarity index 99% rename from docs/resources/graph-optimizations.md rename to docs/performance/graph-optimizations.md index 83a2507406..86b1a02067 100644 --- a/docs/resources/graph-optimizations.md +++ b/docs/performance/graph-optimizations.md @@ -1,7 +1,7 @@ --- title: Graph optimizations -parent: Resources -nav_order: 3 +parent: Performance +nav_order: 2 --- # Graph Optimizations in ONNX Runtime diff --git a/docs/performance/index.md b/docs/performance/index.md new file mode 100644 index 0000000000..b78221dea9 --- /dev/null +++ b/docs/performance/index.md @@ -0,0 +1,7 @@ +--- +title: Performance +has_children: true +nav_order: 11 +--- + +# ONNX Runtime Reference diff --git a/docs/resources/mobile-performance-tuning.md b/docs/performance/mobile-performance-tuning.md similarity index 94% rename from docs/resources/mobile-performance-tuning.md rename to docs/performance/mobile-performance-tuning.md index 2e0baa48a4..1937f3c2ed 100644 --- a/docs/resources/mobile-performance-tuning.md +++ b/docs/performance/mobile-performance-tuning.md @@ -1,7 +1,7 @@ --- title: ONNX Runtime Mobile Performance Tuning -parent: Resources -nav_order: 4 +parent: Performance +nav_order: 1 --- {::options toc_levels="2" /} @@ -9,7 +9,7 @@ nav_order: 4 ONNX Runtime Mobile can be used to execute ORT format models using NNAPI (via the NNAPI Execution Provider (EP)) on Android platforms, and CoreML (via the CoreML EP) on iOS platforms. This section explains the details of how different optimizations affect performance, and provides some suggestions for performance testing with ORT format models. -First, please review the introductory details in [using NNAPI and CoreML with ONNX Runtime Mobile](../how-to/mobile/using-nnapi-coreml-with-ort-mobile). +First, please review the introductory details in [using NNAPI and CoreML with ONNX Runtime Mobile](tutorials/mobile/mobile/using-nnapi-coreml-with-ort-mobile). **IMPORTANT NOTE:** The examples on this page refer to the NNAPI EP for brevity. The information equally applies to the CoreML EP, so any reference to 'NNAPI' below can be substituted with 'CoreML'.
    The exception is [creating an NNAPI-aware ORT format model](#3-creating-an-nnapi-aware-ort-format-model), as that functionality is currently unsupported by the CoreML EP. @@ -45,7 +45,7 @@ _Layout_ optimizations may be hardware specific and involve internal conversions ### Outcome of optimizations when creating an optimized ORT format model -Below is an example of the changes that occur in _basic_ and _extended_ optimizations when applied to the MNIST model with only the CPU EP enabled. The optimization level is specified when [creating the ORT format model](../how-to/mobile/model-conversion#optimization-level). +Below is an example of the changes that occur in _basic_ and _extended_ optimizations when applied to the MNIST model with only the CPU EP enabled. The optimization level is specified when [creating the ORT format model](tutorials/mobile/mobile/model-conversion#optimization-level). - At the _basic_ level we combine the Conv and Add nodes (the addition is done via the 'B' input to Conv), we combine the MatMul and Add into a single Gemm node (the addition is done via the 'C' input to Gemm), and constant fold to remove one of the Reshape nodes. - `python /tools/python/convert_onnx_models_to_ort.py --optimization_level basic /dir_with_mnist_onnx_model` @@ -93,7 +93,7 @@ For our MNIST model that would mean that after the _basic_ optimizations are app To create an NNAPI-aware ORT format model please follow these steps. -1. Create a 'full' build of ONNX Runtime with the NNAPI EP by [building ONNX Runtime from source](../how-to/build/inferencing.md#cpu). +1. Create a 'full' build of ONNX Runtime with the NNAPI EP by [building ONNX Runtime from source](build/inferencing.md#cpu). This build can be done on any platform, as the NNAPI EP can be used to create the ORT format model without the Android NNAPI library as there is no model execution in this process. When building add `--use_nnapi --build_shared_lib --build_wheel` to the build flags if any of those are missing. @@ -118,7 +118,7 @@ To create an NNAPI-aware ORT format model please follow these steps. pip install -U build\Windows\RelWithDebIfo\RelWithDebIfo\dist\onnxruntime_noopenmp-1.7.0-cp37-cp37m-win_amd64.whl ``` -3. Create an NNAPI-aware ORT format model by running `convert_onnx_models_to_ort.py` as per the [standard instructions](../how-to/mobile/model-conversion), with NNAPI enabled (`--use_nnapi`), and the optimization level set to _extended_ or _all_ (e.g. `--optimization_level extended`). This will allow higher level optimizations to run on any nodes that NNAPI can not handle. +3. Create an NNAPI-aware ORT format model by running `convert_onnx_models_to_ort.py` as per the [standard instructions](tutorials/mobile/mobile/model-conversion), with NNAPI enabled (`--use_nnapi`), and the optimization level set to _extended_ or _all_ (e.g. `--optimization_level extended`). This will allow higher level optimizations to run on any nodes that NNAPI can not handle. ``` python /tools/python/convert_onnx_models_to_ort.py --use_nnapi --optimization_level extended /models ``` diff --git a/docs/how-to/quantization.md b/docs/performance/quantization.md similarity index 99% rename from docs/how-to/quantization.md rename to docs/performance/quantization.md index 1715b1d562..a33b7ddfe8 100644 --- a/docs/how-to/quantization.md +++ b/docs/performance/quantization.md @@ -1,6 +1,6 @@ --- title: Quantize ONNX Models -parent: How to +parent: Performance nav_order: 4 --- # Quantize ONNX Models @@ -69,6 +69,7 @@ Please refer to [quantize.py](https://github.com/microsoft/onnxruntime/blob/mast {: .no_toc } - Dynamic quantization + ```python import onnx from onnxruntime.quantization import quantize_dynamic, QuantType @@ -79,6 +80,7 @@ quantized_model = quantize_dynamic(model_fp32, model_quant, weight_type=QuantTyp ``` - QAT quantization + ```python import onnx from onnxruntime.quantization import quantize_qat, QuantType diff --git a/docs/how-to/tune-performance.md b/docs/performance/tune-performance.md similarity index 97% rename from docs/how-to/tune-performance.md rename to docs/performance/tune-performance.md index 18ee2f7ff5..a8951fef13 100644 --- a/docs/how-to/tune-performance.md +++ b/docs/performance/tune-performance.md @@ -1,13 +1,13 @@ --- title: Tune performance -parent: How to +parent: Performance nav_order: 3 --- # ONNX Runtime Performance Tuning {: .no_toc } -ONNX Runtime provides high performance across a range of hardware options through its [Execution Providers interface](../reference/execution-providers) for different execution environments. +ONNX Runtime provides high performance across a range of hardware options through its [Execution Providers interface](../execution-providers) for different execution environments. Along with this flexibility comes decisions for tuning and usage. For each model running with each execution provider, there are settings that can be tuned (e.g. thread number, wait policy, etc) to improve performance. @@ -52,14 +52,14 @@ In both cases, you will get a JSON file which contains the detailed performance ## Using different Execution Providers -To learn more about different Execution Providers, see [Reference: Execution Providers](../reference/execution-providers). +To learn more about different Execution Providers, see [Reference: Execution Providers](../execution-providers). ### Build the EP {: .no_toc } **Python** -Official Python packages on Pypi only support the default CPU (MLAS) and default GPU (CUDA) execution providers. For other execution providers, you need to [build from source](../how-to/build/eps.md). The recommended instructions build the wheel with debug info in parallel. +Official Python packages on Pypi only support the default CPU (MLAS) and default GPU (CUDA) execution providers. For other execution providers, you need to [build from source](build/eps.md). The recommended instructions build the wheel with debug info in parallel. For example: @@ -132,13 +132,13 @@ TensorRT and CUDA are separate execution providers for ONNX Runtime. On the same ### TensorRT/CUDA or DirectML? {: .no_toc } -DirectML is the hardware-accelerated DirectX 12 library for machine learning on Windows and supports all DirectX 12 capable devices (Nvidia, Intel, AMD). This means that if you are targeting Windows GPUs, using the DirectML Execution Provider is likely your best bet. This can be used with both the ONNX Runtime as well as [WinML APIs](../reference/api/winrt-api.md). +DirectML is the hardware-accelerated DirectX 12 library for machine learning on Windows and supports all DirectX 12 capable devices (Nvidia, Intel, AMD). This means that if you are targeting Windows GPUs, using the DirectML Execution Provider is likely your best bet. This can be used with both the ONNX Runtime as well as [WinML APIs](../api/winrt-api.md). ## Tuning performance Below are some suggestions for things to try for various EPs for tuning performance. ### Shared arena based allocator -Memory consumption can be reduced between multiple sessions by configuring the shared arena based allocation. See the `Share allocator(s) between sessions` section in the [C API documentation](../reference/api/c-api). +Memory consumption can be reduced between multiple sessions by configuring the shared arena based allocation. See the `Share allocator(s) between sessions` section in the [C API documentation](../get-started/with-c.html). ### Thread management diff --git a/docs/reference/api/index.md b/docs/reference/api/index.md deleted file mode 100644 index 582a9ee330..0000000000 --- a/docs/reference/api/index.md +++ /dev/null @@ -1,7 +0,0 @@ ---- -title: API docs -parent: Reference -has_children: true -nav_order: 1 ---- -# API docs diff --git a/docs/reference/api/js-api.md b/docs/reference/api/js-api.md deleted file mode 100644 index 553bd1dc86..0000000000 --- a/docs/reference/api/js-api.md +++ /dev/null @@ -1,41 +0,0 @@ ---- -title: JavaScript API -parent: API docs -grand_parent: Reference -nav_order: 5 ---- - -# ONNX Runtime JavaScript API -{: .no_toc } - -ONNX Runtime JavaScript API is the unified interface used by [ONNX Runtime Node.js binding](https://github.com/microsoft/onnxruntime/tree/master/js/node), [ONNX Runtime Web](https://github.com/microsoft/onnxruntime/tree/master/js/web) and [ONNX Runtime for React Native](https://github.com/microsoft/onnxruntime/tree/master/js/react_native). - -## Contents -{: .no_toc } - -* TOC placeholder -{:toc} - - -## Supported Versions - -- ONNX Runtime Node.js binding: Node.js v12.x+ or Electron v5.x+ -- ONNX Runtime Web: mainstream modern browsers on Windows, macOS, Android and iOS. -- ONNX Runtime for React Native: same as [ORT Mobile](../mobile/prebuilt-package) (Android/iOS) - -## Builds - -Builds are published to **npm** and can be installed using `npm install` - -| Package | Artifact | Description | Supported Platforms | -|---------|-----------|-------------|---------------------| -|Node.js binding|[onnxruntime-node](https://www.npmjs.com/package/onnxruntime-node)|CPU (Release)| Windows x64 CPU NAPI_v3, Linux x64 CPU NAPI_v3, MacOS x64 CPU NAPI_v3| -|Web|[onnxruntime-web](https://www.npmjs.com/package/onnxruntime-web)|CPU and GPU|Browsers (wasm, webgl), Node.js (wasm)| -|React Native|[onnxruntime-react-native](https://www.npmjs.com/package/onnxruntime-react-native)|CPU|Android, iOS| - -For Node.js binding, to use on platforms without pre-built binaries, you can [build Node.js binding from source](../../how-to/build/inferencing.md#apis-and-language-bindings) and consume using `npm install /js/node/`. - -## API Reference -See Typescript declarations for [Inference Session](https://github.com/microsoft/onnxruntime/blob/master/js/common/lib/inference-session.ts), [Tensor](https://github.com/microsoft/onnxruntime/blob/master/js/common/lib/tensor.ts) and [Environment Flags](https://github.com/microsoft/onnxruntime/blob/master/js/common/lib/env.ts) for reference. - -See also [ONNX Runtime JavaScript examples](https://github.com/microsoft/onnxruntime-inference-examples/tree/main/js). diff --git a/docs/reference/api/python-api.md b/docs/reference/api/python-api.md deleted file mode 100644 index 5dd674e9e2..0000000000 --- a/docs/reference/api/python-api.md +++ /dev/null @@ -1,38 +0,0 @@ ---- -title: Python API -parent: API docs -grand_parent: Reference -nav_order: 7 ---- - -# ONNX Runtime Python API -{: .no_toc } - -## Contents -{: .no_toc } - -* TOC placeholder -{:toc} - -## Supported Versions -Python 3.6 - 3.9 - -## Builds -If using pip, run pip install `--upgrade pip` prior to downloading. - -| Artifact | Description | Supported Platforms | -|----------- |-------------|---------------------| -|[onnxruntime](https://pypi.org/project/onnxruntime)|CPU (Release)| Windows (x64), Linux (x64, ARM64), Mac (X64), | -|[ort-nightly](https://test.pypi.org/project/ort-nightly)|CPU (Dev) | Same as above | -|[onnxruntime-gpu](https://pypi.org/project/onnxruntime-gpu)|GPU (Release)| Windows (x64), Linux (x64, ARM64) | -|[ort-gpu-nightly](https://test.pypi.org/project/ort-gpu-nightly)|GPU (Dev) | Same as above | - - -For Python compiler version notes, see [this page](https://github.com/microsoft/onnxruntime/tree/master/docs/Python_Dev_Notes.md) - -## API Reference - -[https://www.onnxruntime.ai/python](https://www.onnxruntime.ai/python/) - -## Samples -See [Tutorials: API Basics - Python](../../tutorials/inferencing/api-basics.md#python) \ No newline at end of file diff --git a/docs/reference/api/training-pytorch.md b/docs/reference/api/training-pytorch.md deleted file mode 100644 index 6d9be0299e..0000000000 --- a/docs/reference/api/training-pytorch.md +++ /dev/null @@ -1,19 +0,0 @@ ---- -title: Training API -parent: API docs -grand_parent: Reference -nav_order: 10 ---- - -# Training API (PyTorch) -{: .no_toc } -The ORT Training API is a PyTorch frontend that implements the torch.nn.Module interface. - -## Contents -{: .no_toc } - -* TOC placeholder -{:toc} - -## Samples -[ONNX Runtime Training Examples](../../tutorials/training) \ No newline at end of file diff --git a/docs/resources/compatibility.md b/docs/reference/compatibility.md similarity index 97% rename from docs/resources/compatibility.md rename to docs/reference/compatibility.md index 2fb81af79f..324003ab78 100644 --- a/docs/resources/compatibility.md +++ b/docs/reference/compatibility.md @@ -1,8 +1,8 @@ --- title: Compatibility -parent: Resources +parent: Reference toc: true -nav_order: 1 +nav_order: 12 --- # ONNX Runtime compatibility @@ -64,7 +64,7 @@ ONNX Runtime supports all opsets from the latest released version of the [ONNX]( * [Supported Operator Data Types](https://github.com/microsoft/onnxruntime/blob/master/docs/OperatorKernels.md) * *Operators not supported in the current ONNX spec may be available as a [Contrib Operator](https://github.com/microsoft/onnxruntime/blob/master/docs/ContribOperators.md)* - * [How to add a custom operator/kernel](../how-to/add-custom-op.md) + * [How to add a custom operator/kernel](tutorials/mobile/add-custom-op.md) | ONNX Runtime version | [ONNX version](https://github.com/onnx/onnx/blob/master/docs/Versioning.md) | ONNX opset version | ONNX ML opset version | ONNX IR version | [Windows ML Availability](https://docs.microsoft.com/en-us/windows/ai/windows-ml/release-notes/)| |------------------------------|--------------------|--------------------|----------------------|------------------|------------------| diff --git a/docs/resources/high-level-design.md b/docs/reference/high-level-design.md similarity index 96% rename from docs/resources/high-level-design.md rename to docs/reference/high-level-design.md index d9aa3a4d1e..413d8095be 100644 --- a/docs/resources/high-level-design.md +++ b/docs/reference/high-level-design.md @@ -1,7 +1,7 @@ --- title: Technical design -parent: Resources -nav_order: 2 +parent: Reference +nav_order: 13 --- # ONNX Runtime High Level Design @@ -58,7 +58,7 @@ Conceptually, each partition is reduced to a single fused operator. It is create ## Key design decisions * Multiple threads can invoke the Run() method on the same -inference session object. See [API doc](../reference/api/c-api.md) for more details. +inference session object. See [API doc](../get-started/with-c.html.md) for more details. * To facilitate this, the Compute() function of all kernels is const implying the kernels are stateless. * Implementations of the operators by execution providers are called @@ -72,8 +72,8 @@ different representation if they choose to, but it is their responsibility to co ## Extensibility Options -* [Add a custom operator/kernel](../how-to/add-custom-op.md) -* [Add an execution provider](../how-to/add-execution-provider.md) +* [Add a custom operator/kernel](tutorials/mobile/add-custom-op.md) +* [Add an execution provider](tutorials/mobile/add-execution-provider.md) * [Add a new graphtransform](https://github.com/microsoft/onnxruntime/tree/master/include//onnxruntime/core/optimizer/graph_transformer.h) * [Add a new rewrite rule](https://github.com/microsoft/onnxruntime/tree/master/include//onnxruntime/core/optimizer/rewrite_rule.h) diff --git a/docs/reference/index.md b/docs/reference/index.md index 7a910ba0d1..f1901cdcfa 100644 --- a/docs/reference/index.md +++ b/docs/reference/index.md @@ -1,7 +1,7 @@ --- title: Reference has_children: true -nav_order: 4 +nav_order: 7 --- # ONNX Runtime Reference diff --git a/docs/how-to/add-custom-op.md b/docs/reference/operators/add-custom-op.md similarity index 99% rename from docs/how-to/add-custom-op.md rename to docs/reference/operators/add-custom-op.md index c2d4cfee00..cdb00099ca 100644 --- a/docs/how-to/add-custom-op.md +++ b/docs/reference/operators/add-custom-op.md @@ -1,7 +1,8 @@ --- title: Use custom operators -parent: How to -nav_order: 6 +parent: Operators +grand_parent: Reference +nav_order: 3 --- # Custom operators {: .no_toc } diff --git a/docs/how-to/custom-python-operator.md b/docs/reference/operators/custom-python-operator.md similarity index 99% rename from docs/how-to/custom-python-operator.md rename to docs/reference/operators/custom-python-operator.md index 2aa96d3b5b..296794c84d 100644 --- a/docs/how-to/custom-python-operator.md +++ b/docs/reference/operators/custom-python-operator.md @@ -1,6 +1,8 @@ --- title: Use the PyOp operator nav_exclude: true +parent: Operators +grand_parent: Reference --- # How to use the Python Operator (PyOp) diff --git a/docs/resources/index.md b/docs/resources/index.md deleted file mode 100644 index dc4b165430..0000000000 --- a/docs/resources/index.md +++ /dev/null @@ -1,7 +0,0 @@ ---- -title: Resources -has_children: true -nav_order: 5 ---- - -# ONNX Runtime Resources diff --git a/docs/tutorials/tutorials/OpenVINO_EP_samples/squeezenet_classification_cpp.md b/docs/tutorials/OpenVINO_EP_samples/squeezenet_classification_cpp.md similarity index 100% rename from docs/tutorials/tutorials/OpenVINO_EP_samples/squeezenet_classification_cpp.md rename to docs/tutorials/OpenVINO_EP_samples/squeezenet_classification_cpp.md diff --git a/docs/tutorials/tutorials/OpenVINO_EP_samples/tiny_yolo_v2_object_detection_python.md b/docs/tutorials/OpenVINO_EP_samples/tiny_yolo_v2_object_detection_python.md similarity index 100% rename from docs/tutorials/tutorials/OpenVINO_EP_samples/tiny_yolo_v2_object_detection_python.md rename to docs/tutorials/OpenVINO_EP_samples/tiny_yolo_v2_object_detection_python.md diff --git a/docs/tutorials/tutorials/OpenVINO_EP_samples/yolov3_object_detection_csharp.md b/docs/tutorials/OpenVINO_EP_samples/yolov3_object_detection_csharp.md similarity index 100% rename from docs/tutorials/tutorials/OpenVINO_EP_samples/yolov3_object_detection_csharp.md rename to docs/tutorials/OpenVINO_EP_samples/yolov3_object_detection_csharp.md diff --git a/docs/tutorials/accelerate-pytorch/index.md b/docs/tutorials/accelerate-pytorch/index.md new file mode 100644 index 0000000000..b7f49211e4 --- /dev/null +++ b/docs/tutorials/accelerate-pytorch/index.md @@ -0,0 +1,8 @@ +--- +title: Accelerate PyTorch +has_children: true +nav_order: 3 +parent: Tutorials +--- + +# Accelerate PyTorch diff --git a/docs/tutorials/training/ort-training.md b/docs/tutorials/accelerate-pytorch/ort-training.md similarity index 90% rename from docs/tutorials/training/ort-training.md rename to docs/tutorials/accelerate-pytorch/ort-training.md index 5e7f0b5277..b85ec358f6 100644 --- a/docs/tutorials/training/ort-training.md +++ b/docs/tutorials/accelerate-pytorch/ort-training.md @@ -1,8 +1,8 @@ --- -title: Accelerate PyTorch training +title: Accelerate PyTorch Training +parent: Accelerate PyTorch grand_parent: Tutorials -parent: Training -nav_order: 1 +nav_order: 2 --- # ORTModule Examples * [Use ORTModule with HuggingFace Models](https://github.com/microsoft/onnxruntime-training-examples/tree/master/huggingface) diff --git a/docs/tutorials/inferencing/pytorch.md b/docs/tutorials/accelerate-pytorch/pytorch.md similarity index 88% rename from docs/tutorials/inferencing/pytorch.md rename to docs/tutorials/accelerate-pytorch/pytorch.md index 14c91b089a..459c9f78df 100644 --- a/docs/tutorials/inferencing/pytorch.md +++ b/docs/tutorials/accelerate-pytorch/pytorch.md @@ -1,26 +1,22 @@ --- -title: Accelerate PyTorch +title: Accelerate PyTorch Inference +parent: Accelerate PyTorch grand_parent: Tutorials -parent: Inferencing -nav_order: 2 +nav_order: 1 --- # Accelerate PyTorch model inferencing {: .no_toc } ONNX Runtime can be used to accelerate PyTorch models inferencing. -## Contents -{: .no_toc } - -* TOC placeholder -{:toc} - ## Convert model to ONNX +{: .no_toc } * [Basic PyTorch export through torch.onnx](https://pytorch.org/docs/stable/onnx.html) * [Super-resolution with ONNX Runtime](https://pytorch.org/tutorials/advanced/super_resolution_with_onnxruntime.html) * [Export PyTorch model with custom ops](../tutorials/export-pytorch-model.md) ## Accelerate PyTorch model inferencing +{: .no_toc } * [Accelerate reduced size BERT model through quantization](https://github.com/microsoft/onnxruntime/blob/master/onnxruntime/python/tools/quantization/notebooks/bert/Bert-GLUE_OnnxRuntime_quantization.ipynb) diff --git a/docs/tutorials/inferencing/api-basics.md b/docs/tutorials/api-basics.md similarity index 96% rename from docs/tutorials/inferencing/api-basics.md rename to docs/tutorials/api-basics.md index 73f8cecb11..2759523d27 100644 --- a/docs/tutorials/inferencing/api-basics.md +++ b/docs/tutorials/api-basics.md @@ -1,7 +1,6 @@ --- title: API Basics -grand_parent: Tutorials -parent: Inferencing +parent: Tutorials nav_order: 1 --- # ONNX Runtime Inferencing: API Basics diff --git a/docs/tutorials/tutorials/basic_csharp.md b/docs/tutorials/basic_csharp.md similarity index 100% rename from docs/tutorials/tutorials/basic_csharp.md rename to docs/tutorials/basic_csharp.md diff --git a/docs/tutorials/tutorials/export-pytorch-model.md b/docs/tutorials/export-pytorch-model.md similarity index 100% rename from docs/tutorials/tutorials/export-pytorch-model.md rename to docs/tutorials/export-pytorch-model.md diff --git a/docs/tutorials/tutorials/fasterrcnn_csharp.md b/docs/tutorials/fasterrcnn_csharp.md similarity index 100% rename from docs/tutorials/tutorials/fasterrcnn_csharp.md rename to docs/tutorials/fasterrcnn_csharp.md diff --git a/docs/tutorials/inferencing/huggingface.md b/docs/tutorials/huggingface.md similarity index 96% rename from docs/tutorials/inferencing/huggingface.md rename to docs/tutorials/huggingface.md index 167d3627d6..1b4f11fa2e 100644 --- a/docs/tutorials/inferencing/huggingface.md +++ b/docs/tutorials/huggingface.md @@ -1,7 +1,6 @@ --- title: Accelerate Hugging Face -grand_parent: Tutorials -parent: Inferencing +parent: Tutorials nav_order: 4 --- # Accelerate Hugging Face models diff --git a/docs/tutorials/index.md b/docs/tutorials/index.md index 67a35aec74..931d11874b 100644 --- a/docs/tutorials/index.md +++ b/docs/tutorials/index.md @@ -1,7 +1,7 @@ --- title: Tutorials has_children: true -nav_order: 2 +nav_order: 4 --- # ONNX Runtime Tutorials diff --git a/docs/tutorials/inferencing/index.md b/docs/tutorials/inferencing/index.md deleted file mode 100644 index 7e1c1db442..0000000000 --- a/docs/tutorials/inferencing/index.md +++ /dev/null @@ -1,14 +0,0 @@ ---- -title: Inferencing -parent: Tutorials -has_children: true -nav_order: 1 ---- -# Tutorials: ORT Inferencing - -## Quickstarts -* [TensorFlow with ONNX Runtime](../tutorials/tf-get-started.md) -* [PyTorch with ONNX Runtime](https://pytorch.org/tutorials/advanced/super_resolution_with_onnxruntime.html) -* [scikit-learn with ONNX Runtime](https://www.onnxruntime.ai/python/tutorial.html) - - diff --git a/docs/tutorials/inferencing/web.md b/docs/tutorials/inferencing/web.md deleted file mode 100644 index 65e78af4a0..0000000000 --- a/docs/tutorials/inferencing/web.md +++ /dev/null @@ -1,11 +0,0 @@ ---- -title: Deploy on web -grand_parent: Tutorials -parent: Inferencing -has_children: false -nav_order: 7 ---- - -# Deploy ML models on the web - - *[COMING SOON]* \ No newline at end of file diff --git a/docs/tutorials/inferencing/iot-edge.md b/docs/tutorials/iot-edge.md similarity index 90% rename from docs/tutorials/inferencing/iot-edge.md rename to docs/tutorials/iot-edge.md index 0bd39ce1fd..aec5747a31 100644 --- a/docs/tutorials/inferencing/iot-edge.md +++ b/docs/tutorials/iot-edge.md @@ -1,7 +1,6 @@ --- title: Deploy on IoT and edge -grand_parent: Tutorials -parent: Inferencing +parent: Tutorials has_children: false nav_order: 6 --- diff --git a/docs/tutorials/tutorials/mnist_cpp.md b/docs/tutorials/mnist_cpp.md similarity index 100% rename from docs/tutorials/tutorials/mnist_cpp.md rename to docs/tutorials/mnist_cpp.md diff --git a/docs/tutorials/tutorials/mnist_java.md b/docs/tutorials/mnist_java.md similarity index 100% rename from docs/tutorials/tutorials/mnist_java.md rename to docs/tutorials/mnist_java.md diff --git a/docs/tutorials/inferencing/mobile.md b/docs/tutorials/mobile.md similarity index 74% rename from docs/tutorials/inferencing/mobile.md rename to docs/tutorials/mobile.md index 296b25170f..81f4bfd4d8 100644 --- a/docs/tutorials/inferencing/mobile.md +++ b/docs/tutorials/mobile.md @@ -1,11 +1,10 @@ --- title: Deploy on mobile -grand_parent: Tutorials -parent: Inferencing +parent: Tutorials nav_order: 5 --- # Deploy ML models on mobile devices -ONNX Runtime can be used to performantly deploy models on mobile devices. Learn more about the mobile build and optimizations under [How to: Build for mobile](../../how-to/mobile). +ONNX Runtime can be used to performantly deploy models on mobile devices. Learn more about the mobile build and optimizations under [How to: Build for mobile](../tutorials/mobile/mobile). * *[COMING SOON]* Deploy ORT on Android * *[COMING SOON]* Deploy ORT on iOS diff --git a/docs/how-to/mobile/custom-build.md b/docs/tutorials/mobile/custom-build.md similarity index 99% rename from docs/how-to/mobile/custom-build.md rename to docs/tutorials/mobile/custom-build.md index 736192d59d..ddd8f3dfcb 100644 --- a/docs/how-to/mobile/custom-build.md +++ b/docs/tutorials/mobile/custom-build.md @@ -1,7 +1,7 @@ --- title: Custom Build parent: Deploy ONNX Runtime Mobile -grand_parent: How to +grand_parent: Tutorials has_children: false nav_order: 4 --- diff --git a/docs/how-to/mobile/index.md b/docs/tutorials/mobile/index.md similarity index 86% rename from docs/how-to/mobile/index.md rename to docs/tutorials/mobile/index.md index 0c92dcb5fa..242be2183a 100644 --- a/docs/how-to/mobile/index.md +++ b/docs/tutorials/mobile/index.md @@ -1,8 +1,8 @@ --- title: Deploy ONNX Runtime Mobile -parent: How to +parent: Tutorials has_children: true -nav_order: 5 +nav_order: 4 --- # How To: Deploy ONNX Runtime on Mobile/Edge devices diff --git a/docs/how-to/mobile/initial-setup.md b/docs/tutorials/mobile/initial-setup.md similarity index 99% rename from docs/how-to/mobile/initial-setup.md rename to docs/tutorials/mobile/initial-setup.md index 0206a1049f..72342c63a9 100644 --- a/docs/how-to/mobile/initial-setup.md +++ b/docs/tutorials/mobile/initial-setup.md @@ -1,7 +1,7 @@ --- title: Initial setup parent: Deploy ONNX Runtime Mobile -grand_parent: How to +grand_parent: Tutorials has_children: false nav_order: 2 --- diff --git a/docs/how-to/mobile/limitations.md b/docs/tutorials/mobile/limitations.md similarity index 98% rename from docs/how-to/mobile/limitations.md rename to docs/tutorials/mobile/limitations.md index 5ca396f1c4..60210fe05b 100644 --- a/docs/how-to/mobile/limitations.md +++ b/docs/tutorials/mobile/limitations.md @@ -1,7 +1,7 @@ --- title: Limitations parent: Deploy ONNX Runtime Mobile -grand_parent: How to +grand_parent: Tutorials nav_order: 7 --- diff --git a/docs/how-to/mobile/model-conversion.md b/docs/tutorials/mobile/model-conversion.md similarity index 98% rename from docs/how-to/mobile/model-conversion.md rename to docs/tutorials/mobile/model-conversion.md index 4dedb355dc..c9ecb305c1 100644 --- a/docs/how-to/mobile/model-conversion.md +++ b/docs/tutorials/mobile/model-conversion.md @@ -1,7 +1,7 @@ --- title: ONNX Model Conversion parent: Deploy ONNX Runtime Mobile -grand_parent: How to +grand_parent: Tutorials has_children: false nav_order: 3 --- @@ -86,7 +86,7 @@ For earlier versions, *extended* is recommended, as the *all* level previously i If the model will potentially be run with the NNAPI EP or CoreML EP, it is recommended to create an ORT format model using the *basic* optimization level. Performance testing should be done to compare running this model with the NNAPI or CoreML EP enabled vs. running the model optimized to a higher level using the CPU EP to determine the optimal setup. -See the documentation on [performance tuning mobile scenarios](../../resources/mobile-performance-tuning) for in-depth information. +See the documentation on [performance tuning mobile scenarios](../references/mobile-performance-tuning) for in-depth information. ##### Enable type reduction diff --git a/docs/how-to/mobile/model-execution.md b/docs/tutorials/mobile/model-execution.md similarity index 92% rename from docs/how-to/mobile/model-execution.md rename to docs/tutorials/mobile/model-execution.md index 9b3ef0162c..fc71694a39 100644 --- a/docs/how-to/mobile/model-execution.md +++ b/docs/tutorials/mobile/model-execution.md @@ -1,7 +1,7 @@ --- title: Model Execution parent: Deploy ONNX Runtime Mobile -grand_parent: How to +grand_parent: Tutorials has_children: false nav_order: 5 --- @@ -11,7 +11,7 @@ nav_order: 5 The API for executing ORT format models is the same as for ONNX models. -See the [ONNX Runtime API documentation](../../reference/api) for details on individual API usage. +See the [ONNX Runtime API documentation](../api) for details on individual API usage. ## APIs by platform diff --git a/docs/how-to/mobile/overview.md b/docs/tutorials/mobile/overview.md similarity index 94% rename from docs/how-to/mobile/overview.md rename to docs/tutorials/mobile/overview.md index de3bf25d00..a67df31da0 100644 --- a/docs/how-to/mobile/overview.md +++ b/docs/tutorials/mobile/overview.md @@ -1,7 +1,7 @@ --- title: Overview parent: Deploy ONNX Runtime Mobile -grand_parent: How to +grand_parent: Tutorials has_children: false nav_order: 1 --- @@ -35,7 +35,7 @@ The pre-built package includes support for selected operators and ONNX opset ver ### Operators and Types supported -ONNX operator and types supported by the pre-built package for each ONNX Runtime release are documented [here](../../reference/mobile/prebuilt-package). +ONNX operator and types supported by the pre-built package for each ONNX Runtime release are documented [here](../tutorials/mobile/prebuilt-package). ## Custom build diff --git a/docs/how-to/mobile/using-nnapi-coreml-with-ort-mobile.md b/docs/tutorials/mobile/using-nnapi-coreml-with-ort-mobile.md similarity index 88% rename from docs/how-to/mobile/using-nnapi-coreml-with-ort-mobile.md rename to docs/tutorials/mobile/using-nnapi-coreml-with-ort-mobile.md index e22871c299..918c9e9882 100644 --- a/docs/how-to/mobile/using-nnapi-coreml-with-ort-mobile.md +++ b/docs/tutorials/mobile/using-nnapi-coreml-with-ort-mobile.md @@ -1,16 +1,16 @@ --- title: Enabling NNAPI or CoreML Execution Providers parent: Deploy ONNX Runtime Mobile -grand_parent: How to +grand_parent: Tutorials nav_order: 6 --- ## Using NNAPI and CoreML with ONNX Runtime Mobile - Usage of NNAPI on Android platforms is via the NNAPI Execution Provider (EP). - - See the [NNAPI Execution Provider](../../reference/execution-providers/NNAPI-ExecutionProvider) documentation for more details. + - See the [NNAPI Execution Provider](../execution-providers/NNAPI-ExecutionProvider) documentation for more details. - Usage of CoreML on iOS and macOS platforms is via the CoreML EP. - - See the [CoreML Execution Provider](../../reference/execution-providers/CoreML-ExecutionProvider) documentation for more details. + - See the [CoreML Execution Provider](../execution-providers/CoreML-ExecutionProvider) documentation for more details. The pre-built ONNX Runtime Mobile package includes the NNAPI EP on Android, and the CoreML EP on iOS. diff --git a/docs/tutorials/tutorials/resnet50_csharp.md b/docs/tutorials/resnet50_csharp.md similarity index 100% rename from docs/tutorials/tutorials/resnet50_csharp.md rename to docs/tutorials/resnet50_csharp.md diff --git a/docs/tutorials/inferencing/tensorflow.md b/docs/tutorials/tensorflow.md similarity index 95% rename from docs/tutorials/inferencing/tensorflow.md rename to docs/tutorials/tensorflow.md index 151b1c0ce5..2ffc5f70bf 100644 --- a/docs/tutorials/inferencing/tensorflow.md +++ b/docs/tutorials/tensorflow.md @@ -1,27 +1,21 @@ --- title: Accelerate TensorFlow nav_order: 3 -grand_parent: Tutorials -parent: Inferencing +parent: Tutorials --- # Accelerate TensorFlow model inferencing {: .no_toc } ONNX Runtime can accelerate inferencing times for TensorFlow, TFLite, and Keras models. -## Contents -{: .no_toc } - -* TOC placeholder -{:toc} - ## Get Started +{: .no_toc } * [End to end: Run TensorFlow models in ONNX Runtime](../tutorials/tf-get-started.md) ## Export model to ONNX - +{: .no_toc } ### TensorFlow/Keras - +{: .no_toc } These examples use the [TensorFlow-ONNX converter](https://github.com/onnx/tensorflow-onnx), which supports TensorFlow 1, 2, Keras, and TFLite model formats. * [TensorFlow: Object detection (efficentdet)](https://github.com/onnx/tensorflow-onnx/blob/master/tutorials/efficientdet.ipynb) @@ -32,8 +26,10 @@ These examples use the [TensorFlow-ONNX converter](https://github.com/onnx/tenso * [Keras: Image classification (Resnet 50)](https://github.com/onnx/tensorflow-onnx/blob/master/tutorials/keras-resnet50.ipynb) ### TFLite +{: .no_toc } * [TFLite: Image classifciation (mobiledet)](https://github.com/onnx/tensorflow-onnx/blob/master/tutorials/mobiledet-tflite.ipynb) ## Accelerate TensorFlow model inferencing +{: .no_toc } * [Accelerate BERT model on CPU](https://github.com/microsoft/onnxruntime/blob/master/onnxruntime/python/tools/transformers/notebooks/PyTorch_Bert-Squad_OnnxRuntime_CPU.ipynb) * [Accelerate BERT model on GPU](https://github.com/microsoft/onnxruntime/blob/master/onnxruntime/python/tools/transformers/notebooks/PyTorch_Bert-Squad_OnnxRuntime_GPU.ipynb) \ No newline at end of file diff --git a/docs/tutorials/tutorials/tf-get-started.md b/docs/tutorials/tf-get-started.md similarity index 96% rename from docs/tutorials/tutorials/tf-get-started.md rename to docs/tutorials/tf-get-started.md index 54672eaf00..0ece8ebd29 100644 --- a/docs/tutorials/tutorials/tf-get-started.md +++ b/docs/tutorials/tf-get-started.md @@ -100,4 +100,4 @@ If your model fails to convert please read our [README](https://github.com/onnx/ ## Next Steps -- [More tutorials: accelerate Tensorflow models](../inferencing/tensorflow.md#accelerate-tensorflow-model-inferencing-1) +- [More tutorials: accelerate Tensorflow models](../tensorflow) diff --git a/docs/tutorials/inferencing/traditional-ml.md b/docs/tutorials/traditional-ml.md similarity index 95% rename from docs/tutorials/inferencing/traditional-ml.md rename to docs/tutorials/traditional-ml.md index aa2641eb34..d01b3e9b69 100644 --- a/docs/tutorials/inferencing/traditional-ml.md +++ b/docs/tutorials/traditional-ml.md @@ -1,7 +1,6 @@ --- title: Deploy traditional ML -grand_parent: Tutorials -parent: Inferencing +parent: Tutorials has_children: false nav_order: 8 --- diff --git a/docs/tutorials/training/docs - Shortcut.lnk b/docs/tutorials/training/docs - Shortcut.lnk deleted file mode 100644 index a9c90de3ec..0000000000 Binary files a/docs/tutorials/training/docs - Shortcut.lnk and /dev/null differ diff --git a/docs/tutorials/training/index.md b/docs/tutorials/training/index.md deleted file mode 100644 index 0b2e7a5f47..0000000000 --- a/docs/tutorials/training/index.md +++ /dev/null @@ -1,9 +0,0 @@ ---- -title: Training -parent: Tutorials -has_children: true -nav_order: 2 ---- -# Tutorials: ORT Training - -## [Finetuning acceleration for Hugging Face Transformers with ONNX Runtime](https://github.com/microsoft/onnxruntime-training-examples/tree/master/huggingface). \ No newline at end of file diff --git a/docs/tutorials/web.md b/docs/tutorials/web.md new file mode 100644 index 0000000000..624e9f9b3d --- /dev/null +++ b/docs/tutorials/web.md @@ -0,0 +1,14 @@ +--- +title: Deploy on web +parent: Tutorials +has_children: false +nav_order: 7 +--- + +# Deploy ML models on the web + + Check out the [release blog here](https://cloudblogs.microsoft.com/opensource/2021/09/02/onnx-runtime-web-running-your-machine-learning-model-in-browser/) + + + *[DOCUMENTATION COMING SOON]* + diff --git a/index.html b/index.html index 66e9b82a17..65087b6f7a 100644 --- a/index.html +++ b/index.html @@ -730,7 +730,7 @@ Tutorials
  • - + APIs