| |
| |
| <!DOCTYPE html> |
| <html class="writer-html5" lang="en" data-content_root="./"> |
| <head> |
| <meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" /> |
| |
| <meta name="viewport" content="width=device-width, initial-scale=1.0" /> |
| <title>apache_beam.ml.inference.tensorrt_inference module — Apache Beam 2.68.0 documentation</title> |
| <link rel="stylesheet" type="text/css" href="_static/pygments.css?v=b86133f3" /> |
| <link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=e59714d7" /> |
| |
| |
| <script src="_static/jquery.js?v=5d32c60e"></script> |
| <script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script> |
| <script src="_static/documentation_options.js?v=2388e03a"></script> |
| <script src="_static/doctools.js?v=9a2dae69"></script> |
| <script src="_static/sphinx_highlight.js?v=dc90522c"></script> |
| <script src="_static/js/theme.js"></script> |
| <link rel="index" title="Index" href="genindex.html" /> |
| <link rel="search" title="Search" href="search.html" /> |
| <link rel="next" title="apache_beam.ml.inference.utils module" href="apache_beam.ml.inference.utils.html" /> |
| <link rel="prev" title="apache_beam.ml.inference.tensorflow_inference module" href="apache_beam.ml.inference.tensorflow_inference.html" /> |
| </head> |
| |
| <body class="wy-body-for-nav"> |
| <div class="wy-grid-for-nav"> |
| <nav data-toggle="wy-nav-shift" class="wy-nav-side"> |
| <div class="wy-side-scroll"> |
| <div class="wy-side-nav-search" > |
| |
| |
| |
| <a href="index.html" class="icon icon-home"> |
| Apache Beam |
| </a> |
| <div role="search"> |
| <form id="rtd-search-form" class="wy-form" action="search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" aria-label="Search docs" /> |
| <input type="hidden" name="check_keywords" value="yes" /> |
| <input type="hidden" name="area" value="default" /> |
| </form> |
| </div> |
| </div><div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="Navigation menu"> |
| <ul class="current"> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.coders.html">apache_beam.coders package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.dataframe.html">apache_beam.dataframe package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.io.html">apache_beam.io package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.metrics.html">apache_beam.metrics package</a></li> |
| <li class="toctree-l1 current"><a class="reference internal" href="apache_beam.ml.html">apache_beam.ml package</a><ul class="current"> |
| <li class="toctree-l2 current"><a class="reference internal" href="apache_beam.ml.html#subpackages">Subpackages</a><ul class="current"> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.ml.anomaly.html">apache_beam.ml.anomaly package</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.ml.gcp.html">apache_beam.ml.gcp package</a></li> |
| <li class="toctree-l3 current"><a class="reference internal" href="apache_beam.ml.inference.html">apache_beam.ml.inference package</a><ul class="current"> |
| <li class="toctree-l4 current"><a class="reference internal" href="apache_beam.ml.inference.html#submodules">Submodules</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.ml.rag.html">apache_beam.ml.rag package</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.ml.transforms.html">apache_beam.ml.transforms package</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.ml.ts.html">apache_beam.ml.ts package</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.options.html">apache_beam.options package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.portability.html">apache_beam.portability package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.runners.html">apache_beam.runners package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.testing.html">apache_beam.testing package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.transforms.html">apache_beam.transforms package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.typehints.html">apache_beam.typehints package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.utils.html">apache_beam.utils package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.yaml.html">apache_beam.yaml package</a></li> |
| </ul> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.error.html">apache_beam.error module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.pipeline.html">apache_beam.pipeline module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.pvalue.html">apache_beam.pvalue module</a></li> |
| </ul> |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"><nav class="wy-nav-top" aria-label="Mobile navigation menu" > |
| <i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
| <a href="index.html">Apache Beam</a> |
| </nav> |
| |
| <div class="wy-nav-content"> |
| <div class="rst-content"> |
| <div role="navigation" aria-label="Page navigation"> |
| <ul class="wy-breadcrumbs"> |
| <li><a href="index.html" class="icon icon-home" aria-label="Home"></a></li> |
| <li class="breadcrumb-item"><a href="apache_beam.ml.html">apache_beam.ml package</a></li> |
| <li class="breadcrumb-item"><a href="apache_beam.ml.inference.html">apache_beam.ml.inference package</a></li> |
| <li class="breadcrumb-item active">apache_beam.ml.inference.tensorrt_inference module</li> |
| <li class="wy-breadcrumbs-aside"> |
| <a href="_sources/apache_beam.ml.inference.tensorrt_inference.rst.txt" rel="nofollow"> View page source</a> |
| </li> |
| </ul> |
| <hr/> |
| </div> |
| <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
| <div itemprop="articleBody"> |
| |
| <section id="module-apache_beam.ml.inference.tensorrt_inference"> |
| <span id="apache-beam-ml-inference-tensorrt-inference-module"></span><h1>apache_beam.ml.inference.tensorrt_inference module<a class="headerlink" href="#module-apache_beam.ml.inference.tensorrt_inference" title="Link to this heading"></a></h1> |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="apache_beam.ml.inference.tensorrt_inference.TensorRTEngine"> |
| <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.ml.inference.tensorrt_inference.</span></span><span class="sig-name descname"><span class="pre">TensorRTEngine</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">engine</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">tensorrt.ICudaEngine</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/inference/tensorrt_inference.html#TensorRTEngine"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.inference.tensorrt_inference.TensorRTEngine" title="Link to this definition"></a></dt> |
| <dd><p>Bases: <a class="reference external" href="https://docs.python.org/3/library/functions.html#object" title="(in Python v3.13)"><code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></a></p> |
| <p>Implementation of the TensorRTEngine class which handles |
| allocations associated with TensorRT engine.</p> |
| <p>Example Usage:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">TensorRTEngine</span><span class="p">(</span><span class="n">engine</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><p><strong>engine</strong> – trt.ICudaEngine object that contains TensorRT engine</p> |
| </dd> |
| </dl> |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.inference.tensorrt_inference.TensorRTEngine.get_engine_attrs"> |
| <span class="sig-name descname"><span class="pre">get_engine_attrs</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/inference/tensorrt_inference.html#TensorRTEngine.get_engine_attrs"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.inference.tensorrt_inference.TensorRTEngine.get_engine_attrs" title="Link to this definition"></a></dt> |
| <dd><p>Returns TensorRT engine attributes.</p> |
| </dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="apache_beam.ml.inference.tensorrt_inference.TensorRTEngineHandlerNumPy"> |
| <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.ml.inference.tensorrt_inference.</span></span><span class="sig-name descname"><span class="pre">TensorRTEngineHandlerNumPy</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="pre">min_batch_size:</span> <span class="pre">int,</span> <span class="pre">max_batch_size:</span> <span class="pre">int,</span> <span class="pre">*,</span> <span class="pre">inference_fn:</span> <span class="pre">~collections.abc.Callable[[~collections.abc.Sequence[~numpy.ndarray],</span> <span class="pre">~apache_beam.ml.inference.tensorrt_inference.TensorRTEngine,</span> <span class="pre">dict[str,</span> <span class="pre">~typing.Any]</span> <span class="pre">|</span> <span class="pre">None],</span> <span class="pre">~collections.abc.Iterable[~apache_beam.ml.inference.base.PredictionResult]]</span> <span class="pre">=</span> <span class="pre"><function</span> <span class="pre">_default_tensorRT_inference_fn>,</span> <span class="pre">large_model:</span> <span class="pre">bool</span> <span class="pre">=</span> <span class="pre">False,</span> <span class="pre">model_copies:</span> <span class="pre">int</span> <span class="pre">|</span> <span class="pre">None</span> <span class="pre">=</span> <span class="pre">None,</span> <span class="pre">max_batch_duration_secs:</span> <span class="pre">int</span> <span class="pre">|</span> <span class="pre">None</span> <span class="pre">=</span> <span class="pre">None,</span> <span class="pre">**kwargs</span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/inference/tensorrt_inference.html#TensorRTEngineHandlerNumPy"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.inference.tensorrt_inference.TensorRTEngineHandlerNumPy" title="Link to this definition"></a></dt> |
| <dd><p>Bases: <a class="reference internal" href="apache_beam.ml.inference.base.html#apache_beam.ml.inference.base.ModelHandler" title="apache_beam.ml.inference.base.ModelHandler"><code class="xref py py-class docutils literal notranslate"><span class="pre">ModelHandler</span></code></a>[<a class="reference external" href="https://numpy.org/doc/stable/reference/generated/numpy.ndarray.html#numpy.ndarray" title="(in NumPy v2.3)"><code class="xref py py-class docutils literal notranslate"><span class="pre">ndarray</span></code></a>, <a class="reference internal" href="apache_beam.ml.inference.base.html#apache_beam.ml.inference.base.PredictionResult" title="apache_beam.ml.inference.base.PredictionResult"><code class="xref py py-class docutils literal notranslate"><span class="pre">PredictionResult</span></code></a>, <a class="reference internal" href="#apache_beam.ml.inference.tensorrt_inference.TensorRTEngine" title="apache_beam.ml.inference.tensorrt_inference.TensorRTEngine"><code class="xref py py-class docutils literal notranslate"><span class="pre">TensorRTEngine</span></code></a>]</p> |
| <p>Implementation of the ModelHandler interface for TensorRT.</p> |
| <p>Example Usage:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">pcoll</span> <span class="o">|</span> <span class="n">RunInference</span><span class="p">(</span> |
| <span class="n">TensorRTEngineHandlerNumPy</span><span class="p">(</span> |
| <span class="n">min_batch_size</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> |
| <span class="n">max_batch_size</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> |
| <span class="n">engine_path</span><span class="o">=</span><span class="s2">"my_uri"</span><span class="p">))</span> |
| </pre></div> |
| </div> |
| <p><strong>NOTE:</strong> This API and its implementation are under development and |
| do not provide backward compatibility guarantees.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>min_batch_size</strong> – minimum accepted batch size.</p></li> |
| <li><p><strong>max_batch_size</strong> – maximum accepted batch size.</p></li> |
| <li><p><strong>inference_fn</strong> – the inference function to use on RunInference calls. |
| default: _default_tensorRT_inference_fn</p></li> |
| <li><p><strong>large_model</strong> – set to true if your model is large enough to run into |
| memory pressure if you load multiple copies. Given a model that |
| consumes N memory and a machine with W cores and M memory, you should |
| set this to True if N*W > M.</p></li> |
| <li><p><strong>model_copies</strong> – The exact number of models that you would like loaded |
| onto your machine. This can be useful if you exactly know your CPU or |
| GPU capacity and want to maximize resource utilization.</p></li> |
| <li><p><strong>max_batch_duration_secs</strong> – the maximum amount of time to buffer |
| a batch before emitting; used in streaming contexts.</p></li> |
| <li><p><strong>kwargs</strong> – Additional arguments like ‘engine_path’ and ‘onnx_path’ are |
| currently supported. ‘env_vars’ can be used to set environment variables |
| before loading the model.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p>See <a class="reference external" href="https://docs.nvidia.com/deeplearning/tensorrt/api/python_api/">https://docs.nvidia.com/deeplearning/tensorrt/api/python_api/</a> |
| for details</p> |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.inference.tensorrt_inference.TensorRTEngineHandlerNumPy.batch_elements_kwargs"> |
| <span class="sig-name descname"><span class="pre">batch_elements_kwargs</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/inference/tensorrt_inference.html#TensorRTEngineHandlerNumPy.batch_elements_kwargs"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.inference.tensorrt_inference.TensorRTEngineHandlerNumPy.batch_elements_kwargs" title="Link to this definition"></a></dt> |
| <dd><p>Sets min_batch_size and max_batch_size of a TensorRT engine.</p> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.inference.tensorrt_inference.TensorRTEngineHandlerNumPy.load_model"> |
| <span class="sig-name descname"><span class="pre">load_model</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="#apache_beam.ml.inference.tensorrt_inference.TensorRTEngine" title="apache_beam.ml.inference.tensorrt_inference.TensorRTEngine"><span class="pre">TensorRTEngine</span></a></span></span><a class="reference internal" href="_modules/apache_beam/ml/inference/tensorrt_inference.html#TensorRTEngineHandlerNumPy.load_model"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.inference.tensorrt_inference.TensorRTEngineHandlerNumPy.load_model" title="Link to this definition"></a></dt> |
| <dd><p>Loads and initializes a TensorRT engine for processing.</p> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.inference.tensorrt_inference.TensorRTEngineHandlerNumPy.load_onnx"> |
| <span class="sig-name descname"><span class="pre">load_onnx</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.13)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><span class="pre">tensorrt.INetworkDefinition</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">tensorrt.Builder</span><span class="p"><span class="pre">]</span></span></span></span><a class="reference internal" href="_modules/apache_beam/ml/inference/tensorrt_inference.html#TensorRTEngineHandlerNumPy.load_onnx"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.inference.tensorrt_inference.TensorRTEngineHandlerNumPy.load_onnx" title="Link to this definition"></a></dt> |
| <dd><p>Loads and parses an onnx model for processing.</p> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.inference.tensorrt_inference.TensorRTEngineHandlerNumPy.build_engine"> |
| <span class="sig-name descname"><span class="pre">build_engine</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">network</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">tensorrt.INetworkDefinition</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">builder</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">tensorrt.Builder</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="#apache_beam.ml.inference.tensorrt_inference.TensorRTEngine" title="apache_beam.ml.inference.tensorrt_inference.TensorRTEngine"><span class="pre">TensorRTEngine</span></a></span></span><a class="reference internal" href="_modules/apache_beam/ml/inference/tensorrt_inference.html#TensorRTEngineHandlerNumPy.build_engine"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.inference.tensorrt_inference.TensorRTEngineHandlerNumPy.build_engine" title="Link to this definition"></a></dt> |
| <dd><p>Build an engine according to parsed/created network.</p> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.inference.tensorrt_inference.TensorRTEngineHandlerNumPy.run_inference"> |
| <span class="sig-name descname"><span class="pre">run_inference</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/collections.abc.html#collections.abc.Sequence" title="(in Python v3.13)"><span class="pre">Sequence</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://numpy.org/doc/stable/reference/generated/numpy.ndarray.html#numpy.ndarray" title="(in NumPy v2.3)"><span class="pre">ndarray</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">engine</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#apache_beam.ml.inference.tensorrt_inference.TensorRTEngine" title="apache_beam.ml.inference.tensorrt_inference.TensorRTEngine"><span class="pre">TensorRTEngine</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">inference_args</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.13)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Any" title="(in Python v3.13)"><span class="pre">Any</span></a><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/collections.abc.html#collections.abc.Iterable" title="(in Python v3.13)"><span class="pre">Iterable</span></a><span class="p"><span class="pre">[</span></span><a class="reference internal" href="apache_beam.ml.inference.base.html#apache_beam.ml.inference.base.PredictionResult" title="apache_beam.ml.inference.base.PredictionResult"><span class="pre">PredictionResult</span></a><span class="p"><span class="pre">]</span></span></span></span><a class="reference internal" href="_modules/apache_beam/ml/inference/tensorrt_inference.html#TensorRTEngineHandlerNumPy.run_inference"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.inference.tensorrt_inference.TensorRTEngineHandlerNumPy.run_inference" title="Link to this definition"></a></dt> |
| <dd><p>Runs inferences on a batch of Tensors and returns an Iterable of |
| TensorRT Predictions.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>batch</strong> – A np.ndarray or a np.ndarray that represents a concatenation |
| of multiple arrays as a batch.</p></li> |
| <li><p><strong>engine</strong> – A TensorRT engine.</p></li> |
| <li><p><strong>inference_args</strong> – Any additional arguments for an inference |
| that are not applicable to TensorRT.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Returns<span class="colon">:</span></dt> |
| <dd class="field-even"><p>An Iterable of type PredictionResult.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.inference.tensorrt_inference.TensorRTEngineHandlerNumPy.get_num_bytes"> |
| <span class="sig-name descname"><span class="pre">get_num_bytes</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/collections.abc.html#collections.abc.Sequence" title="(in Python v3.13)"><span class="pre">Sequence</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://numpy.org/doc/stable/reference/generated/numpy.ndarray.html#numpy.ndarray" title="(in NumPy v2.3)"><span class="pre">ndarray</span></a><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a></span></span><a class="reference internal" href="_modules/apache_beam/ml/inference/tensorrt_inference.html#TensorRTEngineHandlerNumPy.get_num_bytes"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.inference.tensorrt_inference.TensorRTEngineHandlerNumPy.get_num_bytes" title="Link to this definition"></a></dt> |
| <dd><dl class="field-list simple"> |
| <dt class="field-odd">Returns<span class="colon">:</span></dt> |
| <dd class="field-odd"><p>The number of bytes of data for a batch of Tensors.</p> |
| </dd> |
| </dl> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.inference.tensorrt_inference.TensorRTEngineHandlerNumPy.get_metrics_namespace"> |
| <span class="sig-name descname"><span class="pre">get_metrics_namespace</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></span><a class="reference internal" href="_modules/apache_beam/ml/inference/tensorrt_inference.html#TensorRTEngineHandlerNumPy.get_metrics_namespace"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.inference.tensorrt_inference.TensorRTEngineHandlerNumPy.get_metrics_namespace" title="Link to this definition"></a></dt> |
| <dd><p>Returns a namespace for metrics collected by the RunInference transform.</p> |
| </dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.inference.tensorrt_inference.TensorRTEngineHandlerNumPy.share_model_across_processes"> |
| <span class="sig-name descname"><span class="pre">share_model_across_processes</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.13)"><span class="pre">bool</span></a></span></span><a class="reference internal" href="_modules/apache_beam/ml/inference/tensorrt_inference.html#TensorRTEngineHandlerNumPy.share_model_across_processes"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.inference.tensorrt_inference.TensorRTEngineHandlerNumPy.share_model_across_processes" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.inference.tensorrt_inference.TensorRTEngineHandlerNumPy.model_copies"> |
| <span class="sig-name descname"><span class="pre">model_copies</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a></span></span><a class="reference internal" href="_modules/apache_beam/ml/inference/tensorrt_inference.html#TensorRTEngineHandlerNumPy.model_copies"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.inference.tensorrt_inference.TensorRTEngineHandlerNumPy.model_copies" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| </section> |
| |
| |
| </div> |
| </div> |
| <footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer"> |
| <a href="apache_beam.ml.inference.tensorflow_inference.html" class="btn btn-neutral float-left" title="apache_beam.ml.inference.tensorflow_inference module" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a> |
| <a href="apache_beam.ml.inference.utils.html" class="btn btn-neutral float-right" title="apache_beam.ml.inference.utils module" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a> |
| </div> |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p>© Copyright %Y, Apache Beam.</p> |
| </div> |
| |
| Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a |
| <a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a> |
| provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| |
| |
| </footer> |
| </div> |
| </div> |
| </section> |
| </div> |
| <script> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| </body> |
| </html> |
