saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-14 18:12:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/docs/api/csharp/api/Microsoft.ML.OnnxRuntime.html
github-actions[bot] a507c0c6a5
[Automated]: Update C# API docs (#14672)
2023-02-14 11:16:35 -08:00

281 lines
15 KiB
HTML
Raw Blame History

<!DOCTYPE html>
<!--[if IE]><![endif]-->
<html>
<head>
<meta charset="utf-8">
<meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1">
<title>Namespace Microsoft.ML.OnnxRuntime
</title>
<meta name="viewport" content="width=device-width">
<meta name="title" content="Namespace Microsoft.ML.OnnxRuntime
">
<meta name="generator" content="docfx 2.59.3.0">
<link rel="shortcut icon" href="../favicon.ico">
<link rel="stylesheet" href="../styles/docfx.vendor.css">
<link rel="stylesheet" href="../styles/docfx.css">
<link rel="stylesheet" href="../styles/main.css">
<meta property="docfx:navrel" content="../toc.html">
<meta property="docfx:tocrel" content="toc.html">
</head>
<body data-spy="scroll" data-target="#affix" data-offset="120">
<div id="wrapper">
<header>
<nav id="autocollapse" class="navbar navbar-inverse ng-scope" role="navigation">
<div class="container">
<div class="navbar-header">
<button type="button" class="navbar-toggle" data-toggle="collapse" data-target="#navbar">
<span class="sr-only">Toggle navigation</span>
<span class="icon-bar"></span>
<span class="icon-bar"></span>
<span class="icon-bar"></span>
</button>
<a class="navbar-brand" href="../index.html">
<img id="logo" class="svg" src="../logo.svg" alt="">
</a>
</div>
<div class="collapse navbar-collapse" id="navbar">
<form class="navbar-form navbar-right" role="search" id="search">
<div class="form-group">
<input type="text" class="form-control" id="search-query" placeholder="Search" autocomplete="off">
</div>
</form>
</div>
</div>
</nav>
<div class="subnav navbar navbar-default">
<div class="container hide-when-search" id="breadcrumb">
<ul class="breadcrumb">
<li></li>
</ul>
</div>
</div>
</header>
<div role="main" class="container body-content hide-when-search">
<div class="sidenav hide-when-search">
<a class="btn toc-toggle collapse" data-toggle="collapse" href="#sidetoggle" aria-expanded="false" aria-controls="sidetoggle">Show / Hide Table of Contents</a>
<div class="sidetoggle collapse" id="sidetoggle">
<div id="sidetoc"></div>
</div>
</div>
<div class="article row grid-right">
<div class="col-md-10">
<article class="content wrap" id="_content" data-uid="Microsoft.ML.OnnxRuntime">
<h1 id="Microsoft_ML_OnnxRuntime" data-uid="Microsoft.ML.OnnxRuntime" class="text-break">Namespace Microsoft.ML.OnnxRuntime
</h1>
<div class="markdown level0 summary"></div>
<div class="markdown level0 conceptual"></div>
<div class="markdown level0 remarks"></div>
<h3 id="classes">Classes
</h3>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.DisposableNamedOnnxValue.html">DisposableNamedOnnxValue</a></h4>
<section><p>This class serves as a container for model run output values including
tensors, sequences of tensors, sequences and maps.
It extends NamedOnnxValue, exposes the OnnxValueType and Tensor type
The class must be disposed of.
It disposes of _ortValueHolder that owns the underlying Ort output value and
anything else that would need to be disposed by the instance of the class.
Use factory method CreateFromOrtValue to obtain an instance of the class.</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.FixedBufferOnnxValue.html">FixedBufferOnnxValue</a></h4>
<section><p>Represents an OrtValue with its underlying buffer pinned</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.InferenceSession.html">InferenceSession</a></h4>
<section><p>Represents an Inference Session on an ONNX Model.
This is a IDisposable class and it must be disposed of
using either a explicit call to Dispose() method or
a pattern of using() block. If this is a member of another
class that class must also become IDisposable and it must
dispose of InferfenceSession in its Dispose() method.</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.ModelMetadata.html">ModelMetadata</a></h4>
<section><p>A class that queries and caches model metadata and exposes
it as properties</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.NamedOnnxValue.html">NamedOnnxValue</a></h4>
<section></section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.NodeMetadata.html">NodeMetadata</a></h4>
<section><p>Resembles type and shape information of session-graph nodes, used for communicating the shape/type of input/output nodes</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.OnnxRuntimeException.html">OnnxRuntimeException</a></h4>
<section><p>The Exception that is thrown for errors related ton OnnxRuntime</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.OrtAllocator.html">OrtAllocator</a></h4>
<section><p>The class exposes native internal allocator for Onnxruntime.
This allocator enables you to allocate memory from the internal
memory pools including device allocations. Useful for binding.</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.OrtArenaCfg.html">OrtArenaCfg</a></h4>
<section><p>This class encapsulates arena configuration information that will be used to define the behavior
of an arena based allocator
See docs/C_API.md for more details</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.OrtCUDAProviderOptions.html">OrtCUDAProviderOptions</a></h4>
<section><p>Holds the options for configuring a CUDA Execution Provider instance</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.OrtEnv.html">OrtEnv</a></h4>
<section><p>This class initializes the process-global ONNX Runtime environment instance (OrtEnv).
The singleton class OrtEnv contains the process-global ONNX Runtime environment.
It sets up logging, creates system wide thread-pools (if Thread Pool options are provided)
and other necessary things for OnnxRuntime to function. Create or access OrtEnv by calling
the Instance() method. Call this method before doing anything else in your application.</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.OrtExternalAllocation.html">OrtExternalAllocation</a></h4>
<section><p>This class represents an arbitrary buffer of memory
allocated and owned by the user. It can be either a CPU, GPU or other device memory
that can be suitably represented by IntPtr.
This is just a composite of the buffer related information.
The memory is assumed to be pinned if necessary and usable immediately
in the native code.</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.OrtIoBinding.html">OrtIoBinding</a></h4>
<section><p>This class enables binding of inputs and/or outputs to pre-allocated
memory. This enables interesting scenarios. For example, if your input
already resides in some pre-allocated memory like GPU, you can bind
that piece of memory to an input name and shape and onnxruntime will use that as input.
Other traditional inputs can also be bound that already exists as Tensors.</p>
<p>Note, that this arrangement is designed to minimize data copies and to that effect
your memory allocations must match what is expected by the model, whether you run on
CPU or GPU. Data copy will still be made, if your pre-allocated memory location does not
match the one expected by the model. However, copies with OrtIoBindings are only done once,
at the time of the binding, not at run time. This means, that if your input data required a copy,
your further input modifications would not be seen by onnxruntime unless you rebind it, even if it is
the same buffer. If you require the scenario where data is copied, OrtIOBinding may not be the best match
for your use case.</p>
<p>The fact that data copy is not made during runtime also has performance implications.</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.OrtMemoryAllocation.html">OrtMemoryAllocation</a></h4>
<section><p>This class represents memory allocation made by a specific onnxruntime
allocator. Use OrtAllocator.Allocate() to obtain an instance of this class.
It implements IDisposable and makes use of the original allocator
used to allocate the memory. The lifespan of the allocator instance must eclipse the
lifespan of the allocation. Or, if you prefer, all OrtMemoryAllocation instances must be
disposed of before the corresponding allocator instances are disposed of.</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.OrtMemoryInfo.html">OrtMemoryInfo</a></h4>
<section><p>This class encapsulates and most of the time owns the underlying native OrtMemoryInfo instance.
Instance returned from OrtAllocator will not own OrtMemoryInfo, the class must be disposed
regardless.</p>
<p>Use this class to query and create OrtAllocator instances so you can pre-allocate memory for model
inputs/outputs and use it for binding. Instances of the class can also used to created OrtValues bound
to pre-allocated memory. In that case, the instance of OrtMemoryInfo contains the information about the allocator
used to allocate the underlying memory.</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.OrtTensorRTProviderOptions.html">OrtTensorRTProviderOptions</a></h4>
<section><p>Holds the options for configuring a TensorRT Execution Provider instance</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.OrtValue.html">OrtValue</a></h4>
<section><p>Represents a disposable OrtValue.
This class exposes a native instance of OrtValue.
The class implements IDisposable via SafeHandle and must
be disposed.</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.PrePackedWeightsContainer.html">PrePackedWeightsContainer</a></h4>
<section><p>This class holds pre-packed weights of shared initializers to be shared across sessions using these initializers
and thereby provide memory savings by sharing the same pre-packed versions of these shared initializers</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.ProviderOptionsValueHelper.html">ProviderOptionsValueHelper</a></h4>
<section><p>This helper class contains methods to handle values of provider options</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.RunOptions.html">RunOptions</a></h4>
<section><p>Sets various runtime options.</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.SessionOptions.html">SessionOptions</a></h4>
<section><p>Holds the options for creating an InferenceSession</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.SessionOptionsContainer.html">SessionOptionsContainer</a></h4>
<section><p>Helper to allow the creation/addition of session options based on pre-defined named entries.</p>
</section>
<h3 id="structs">Structs
</h3>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.OrtApi.html">OrtApi</a></h4>
<section></section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.OrtApiBase.html">OrtApiBase</a></h4>
<section></section>
<h3 id="interfaces">Interfaces
</h3>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.IDisposableReadOnlyCollection-1.html">IDisposableReadOnlyCollection&lt;T&gt;</a></h4>
<section></section>
<h3 id="enums">Enums
</h3>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.CoreMLFlags.html">CoreMLFlags</a></h4>
<section><p>CoreML flags for use with SessionOptions</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.ExecutionMode.html">ExecutionMode</a></h4>
<section><p>Controls whether you want to execute operators in the graph sequentially or in parallel.
Usually when the model has many branches, setting this option to ExecutionMode.ORT_PARALLEL
will give you better performance.
See [ONNX_Runtime_Perf_Tuning.md] for more details.</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.GraphOptimizationLevel.html">GraphOptimizationLevel</a></h4>
<section><p>Graph optimization level to use with SessionOptions
[https://github.com/microsoft/onnxruntime/blob/main/docs/ONNX_Runtime_Graph_Optimizations.md]</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.LogLevel.html">LogLevel</a></h4>
<section><p>Logging level used to specify amount of logging when
creating environment. The lower the value is the more logging
will be output. A specific value output includes everything
that higher values output.</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.NnapiFlags.html">NnapiFlags</a></h4>
<section><p>NNAPI flags for use with SessionOptions</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.OnnxValueType.html">OnnxValueType</a></h4>
<section><p>A type of data that OrtValue encapsulates.</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.OrtAllocatorType.html">OrtAllocatorType</a></h4>
<section><p>See documentation for OrtAllocatorType in C API</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.OrtLanguageProjection.html">OrtLanguageProjection</a></h4>
<section><p>Language projection property for telemetry event for tracking the source usage of ONNXRUNTIME</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.OrtLoggingLevel.html">OrtLoggingLevel</a></h4>
<section><p>Log severity levels</p>
</section>
<h4><a class="xref" href="Microsoft.ML.OnnxRuntime.OrtMemType.html">OrtMemType</a></h4>
<section><p>See documentation for OrtMemType in C API</p>
</section>
</article>
</div>
<div class="hidden-sm col-md-2" role="complementary">
<div class="sideaffix">
<div class="contribution">
<ul class="nav">
</ul>
</div>
<nav class="bs-docs-sidebar hidden-print hidden-xs hidden-sm affix" id="affix">
<h5>In This Article</h5>
<div></div>
</nav>
</div>
</div>
</div>
</div>
<footer>
<div class="grad-bottom"></div>
<div class="footer">
<div class="container">
<span class="pull-right">
<a href="#top">Back to top</a>
</span>
</div>
</div>
</footer>
</div>
<script type="text/javascript" src="../styles/docfx.vendor.js"></script>
<script type="text/javascript" src="../styles/docfx.js"></script>
<script type="text/javascript" src="../styles/main.js"></script>
</body>
</html>
Reference in a new issue View git blame Copy permalink