mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-07-15 18:23:41 +00:00
249 lines
No EOL
19 KiB
HTML
249 lines
No EOL
19 KiB
HTML
|
||
<!DOCTYPE html>
|
||
|
||
<html lang="en">
|
||
<head>
|
||
<meta charset="utf-8" />
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
||
<title>Train, convert and predict with ONNX Runtime — ONNX Runtime 1.7.0 documentation</title>
|
||
<link rel="stylesheet" href="../static/pygments.css" type="text/css" />
|
||
<link rel="stylesheet" href="../static/alabaster.css" type="text/css" />
|
||
<link rel="stylesheet" type="text/css" href="../static/graphviz.css" />
|
||
<link rel="stylesheet" type="text/css" href="../static/gallery.css" />
|
||
<link rel="stylesheet" type="text/css" href="../static/gallery-binder.css" />
|
||
<link rel="stylesheet" type="text/css" href="../static/gallery-dataframe.css" />
|
||
<link rel="stylesheet" type="text/css" href="../static/gallery-rendered-html.css" />
|
||
<script id="documentation_options" data-url_root="../" src="../static/documentation_options.js"></script>
|
||
<script src="../static/jquery.js"></script>
|
||
<script src="../static/underscore.js"></script>
|
||
<script src="../static/doctools.js"></script>
|
||
<link rel="index" title="Index" href="../genindex.html" />
|
||
<link rel="search" title="Search" href="../search.html" />
|
||
<link rel="next" title="Common errors with onnxruntime" href="plot_common_errors.html" />
|
||
<link rel="prev" title="Profile the execution of a simple model" href="plot_profiling.html" />
|
||
|
||
<link rel="stylesheet" href="../static/custom.css" type="text/css" />
|
||
|
||
|
||
<meta name="viewport" content="width=device-width, initial-scale=0.9, maximum-scale=0.9" />
|
||
|
||
</head><body>
|
||
|
||
|
||
<div class="document">
|
||
<div class="documentwrapper">
|
||
<div class="bodywrapper">
|
||
|
||
|
||
<div class="body" role="main">
|
||
|
||
<div class="sphx-glr-download-link-note admonition note">
|
||
<p class="admonition-title">Note</p>
|
||
<p>Click <a class="reference internal" href="#sphx-glr-download-auto-examples-plot-convert-pipeline-vectorizer-py"><span class="std std-ref">here</span></a>
|
||
to download the full example code</p>
|
||
</div>
|
||
<div class="sphx-glr-example-title section" id="train-convert-and-predict-with-onnx-runtime">
|
||
<span id="sphx-glr-auto-examples-plot-convert-pipeline-vectorizer-py"></span><h1>Train, convert and predict with ONNX Runtime<a class="headerlink" href="#train-convert-and-predict-with-onnx-runtime" title="Permalink to this headline">¶</a></h1>
|
||
<p>This example demonstrates an end to end scenario
|
||
starting with the training of a scikit-learn pipeline
|
||
which takes as inputs not a regular vector but a
|
||
dictionary <code class="docutils literal notranslate"><span class="pre">{</span> <span class="pre">int:</span> <span class="pre">float</span> <span class="pre">}</span></code> as its first step is a
|
||
<a class="reference external" href="http://scikit-learn.org/stable/modules/generated/sklearn.feature_extraction.DictVectorizer.html">DictVectorizer</a>.</p>
|
||
<div class="contents local topic" id="contents">
|
||
<ul class="simple">
|
||
<li><p><a class="reference internal" href="#train-a-pipeline" id="id1">Train a pipeline</a></p></li>
|
||
<li><p><a class="reference internal" href="#conversion-to-onnx-format" id="id2">Conversion to ONNX format</a></p></li>
|
||
</ul>
|
||
</div>
|
||
<div class="section" id="train-a-pipeline">
|
||
<h2><a class="toc-backref" href="#id1">Train a pipeline</a><a class="headerlink" href="#train-a-pipeline" title="Permalink to this headline">¶</a></h2>
|
||
<p>The first step consists in retrieving the boston datset.</p>
|
||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">pandas</span>
|
||
<span class="kn">from</span> <span class="nn">sklearn.datasets</span> <span class="kn">import</span> <span class="n">load_boston</span>
|
||
<span class="n">boston</span> <span class="o">=</span> <span class="n">load_boston</span><span class="p">()</span>
|
||
<span class="n">X</span><span class="p">,</span> <span class="n">y</span> <span class="o">=</span> <span class="n">boston</span><span class="o">.</span><span class="n">data</span><span class="p">,</span> <span class="n">boston</span><span class="o">.</span><span class="n">target</span>
|
||
|
||
<span class="kn">from</span> <span class="nn">sklearn.model_selection</span> <span class="kn">import</span> <span class="n">train_test_split</span>
|
||
<span class="n">X_train</span><span class="p">,</span> <span class="n">X_test</span><span class="p">,</span> <span class="n">y_train</span><span class="p">,</span> <span class="n">y_test</span> <span class="o">=</span> <span class="n">train_test_split</span><span class="p">(</span><span class="n">X</span><span class="p">,</span> <span class="n">y</span><span class="p">)</span>
|
||
<span class="n">X_train_dict</span> <span class="o">=</span> <span class="n">pandas</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">X_train</span><span class="p">[:,</span><span class="mi">1</span><span class="p">:])</span><span class="o">.</span><span class="n">T</span><span class="o">.</span><span class="n">to_dict</span><span class="p">()</span><span class="o">.</span><span class="n">values</span><span class="p">()</span>
|
||
<span class="n">X_test_dict</span> <span class="o">=</span> <span class="n">pandas</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">X_test</span><span class="p">[:,</span><span class="mi">1</span><span class="p">:])</span><span class="o">.</span><span class="n">T</span><span class="o">.</span><span class="n">to_dict</span><span class="p">()</span><span class="o">.</span><span class="n">values</span><span class="p">()</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>We create a pipeline.</p>
|
||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">sklearn.pipeline</span> <span class="kn">import</span> <span class="n">make_pipeline</span>
|
||
<span class="kn">from</span> <span class="nn">sklearn.ensemble</span> <span class="kn">import</span> <span class="n">GradientBoostingRegressor</span>
|
||
<span class="kn">from</span> <span class="nn">sklearn.feature_extraction</span> <span class="kn">import</span> <span class="n">DictVectorizer</span>
|
||
<span class="n">pipe</span> <span class="o">=</span> <span class="n">make_pipeline</span><span class="p">(</span>
|
||
<span class="n">DictVectorizer</span><span class="p">(</span><span class="n">sparse</span><span class="o">=</span><span class="kc">False</span><span class="p">),</span>
|
||
<span class="n">GradientBoostingRegressor</span><span class="p">())</span>
|
||
|
||
<span class="n">pipe</span><span class="o">.</span><span class="n">fit</span><span class="p">(</span><span class="n">X_train_dict</span><span class="p">,</span> <span class="n">y_train</span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
<p class="sphx-glr-script-out">Out:</p>
|
||
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Pipeline(steps=[('dictvectorizer', DictVectorizer(sparse=False)),
|
||
('gradientboostingregressor', GradientBoostingRegressor())])
|
||
</pre></div>
|
||
</div>
|
||
<p>We compute the prediction on the test set
|
||
and we show the confusion matrix.</p>
|
||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">sklearn.metrics</span> <span class="kn">import</span> <span class="n">r2_score</span>
|
||
|
||
<span class="n">pred</span> <span class="o">=</span> <span class="n">pipe</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">X_test_dict</span><span class="p">)</span>
|
||
<span class="nb">print</span><span class="p">(</span><span class="n">r2_score</span><span class="p">(</span><span class="n">y_test</span><span class="p">,</span> <span class="n">pred</span><span class="p">))</span>
|
||
</pre></div>
|
||
</div>
|
||
<p class="sphx-glr-script-out">Out:</p>
|
||
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>0.848444978558249
|
||
</pre></div>
|
||
</div>
|
||
</div>
|
||
<div class="section" id="conversion-to-onnx-format">
|
||
<h2><a class="toc-backref" href="#id2">Conversion to ONNX format</a><a class="headerlink" href="#conversion-to-onnx-format" title="Permalink to this headline">¶</a></h2>
|
||
<p>We use module
|
||
<a class="reference external" href="https://github.com/onnx/sklearn-onnx">sklearn-onnx</a>
|
||
to convert the model into ONNX format.</p>
|
||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">skl2onnx</span> <span class="kn">import</span> <span class="n">convert_sklearn</span>
|
||
<span class="kn">from</span> <span class="nn">skl2onnx.common.data_types</span> <span class="kn">import</span> <span class="n">FloatTensorType</span><span class="p">,</span> <span class="n">Int64TensorType</span><span class="p">,</span> <span class="n">DictionaryType</span><span class="p">,</span> <span class="n">SequenceType</span>
|
||
|
||
<span class="c1"># initial_type = [('float_input', DictionaryType(Int64TensorType([1]), FloatTensorType([])))]</span>
|
||
<span class="n">initial_type</span> <span class="o">=</span> <span class="p">[(</span><span class="s1">'float_input'</span><span class="p">,</span> <span class="n">DictionaryType</span><span class="p">(</span><span class="n">Int64TensorType</span><span class="p">([</span><span class="mi">1</span><span class="p">]),</span> <span class="n">FloatTensorType</span><span class="p">([])))]</span>
|
||
<span class="n">onx</span> <span class="o">=</span> <span class="n">convert_sklearn</span><span class="p">(</span><span class="n">pipe</span><span class="p">,</span> <span class="n">initial_types</span><span class="o">=</span><span class="n">initial_type</span><span class="p">)</span>
|
||
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="s2">"pipeline_vectorize.onnx"</span><span class="p">,</span> <span class="s2">"wb"</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
|
||
<span class="n">f</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="n">onx</span><span class="o">.</span><span class="n">SerializeToString</span><span class="p">())</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>We load the model with ONNX Runtime and look at
|
||
its input and output.</p>
|
||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">import</span> <span class="nn">onnxruntime</span> <span class="k">as</span> <span class="nn">rt</span>
|
||
<span class="kn">from</span> <span class="nn">onnxruntime.capi.onnxruntime_pybind11_state</span> <span class="kn">import</span> <span class="n">InvalidArgument</span>
|
||
|
||
<span class="n">sess</span> <span class="o">=</span> <span class="n">rt</span><span class="o">.</span><span class="n">InferenceSession</span><span class="p">(</span><span class="s2">"pipeline_vectorize.onnx"</span><span class="p">)</span>
|
||
|
||
<span class="kn">import</span> <span class="nn">numpy</span>
|
||
<span class="n">inp</span><span class="p">,</span> <span class="n">out</span> <span class="o">=</span> <span class="n">sess</span><span class="o">.</span><span class="n">get_inputs</span><span class="p">()[</span><span class="mi">0</span><span class="p">],</span> <span class="n">sess</span><span class="o">.</span><span class="n">get_outputs</span><span class="p">()[</span><span class="mi">0</span><span class="p">]</span>
|
||
<span class="nb">print</span><span class="p">(</span><span class="s2">"input name='</span><span class="si">{}</span><span class="s2">' and shape=</span><span class="si">{}</span><span class="s2"> and type=</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">inp</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="n">inp</span><span class="o">.</span><span class="n">shape</span><span class="p">,</span> <span class="n">inp</span><span class="o">.</span><span class="n">type</span><span class="p">))</span>
|
||
<span class="nb">print</span><span class="p">(</span><span class="s2">"output name='</span><span class="si">{}</span><span class="s2">' and shape=</span><span class="si">{}</span><span class="s2"> and type=</span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">out</span><span class="o">.</span><span class="n">name</span><span class="p">,</span> <span class="n">out</span><span class="o">.</span><span class="n">shape</span><span class="p">,</span> <span class="n">out</span><span class="o">.</span><span class="n">type</span><span class="p">))</span>
|
||
</pre></div>
|
||
</div>
|
||
<p class="sphx-glr-script-out">Out:</p>
|
||
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>input name='float_input' and shape=[] and type=map(int64,tensor(float))
|
||
output name='variable' and shape=[None, 1] and type=tensor(float)
|
||
</pre></div>
|
||
</div>
|
||
<p>We compute the predictions.
|
||
We could do that in one call:</p>
|
||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="k">try</span><span class="p">:</span>
|
||
<span class="n">pred_onx</span> <span class="o">=</span> <span class="n">sess</span><span class="o">.</span><span class="n">run</span><span class="p">([</span><span class="n">out</span><span class="o">.</span><span class="n">name</span><span class="p">],</span> <span class="p">{</span><span class="n">inp</span><span class="o">.</span><span class="n">name</span><span class="p">:</span> <span class="n">X_test_dict</span><span class="p">})[</span><span class="mi">0</span><span class="p">]</span>
|
||
<span class="k">except</span> <span class="p">(</span><span class="ne">RuntimeError</span><span class="p">,</span> <span class="n">InvalidArgument</span><span class="p">)</span> <span class="k">as</span> <span class="n">e</span><span class="p">:</span>
|
||
<span class="nb">print</span><span class="p">(</span><span class="n">e</span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
<p class="sphx-glr-script-out">Out:</p>
|
||
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[ONNXRuntimeError] : 2 : INVALID_ARGUMENT : Unexpected input data type. Actual: ((seq(map(int64,tensor(float))))) , expected: ((map(int64,tensor(float))))
|
||
</pre></div>
|
||
</div>
|
||
<p>But it fails because, in case of a DictVectorizer,
|
||
ONNX Runtime expects one observation at a time.</p>
|
||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">pred_onx</span> <span class="o">=</span> <span class="p">[</span><span class="n">sess</span><span class="o">.</span><span class="n">run</span><span class="p">([</span><span class="n">out</span><span class="o">.</span><span class="n">name</span><span class="p">],</span> <span class="p">{</span><span class="n">inp</span><span class="o">.</span><span class="n">name</span><span class="p">:</span> <span class="n">row</span><span class="p">})[</span><span class="mi">0</span><span class="p">][</span><span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">]</span> <span class="k">for</span> <span class="n">row</span> <span class="ow">in</span> <span class="n">X_test_dict</span><span class="p">]</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>We compare them to the model’s ones.</p>
|
||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="nb">print</span><span class="p">(</span><span class="n">r2_score</span><span class="p">(</span><span class="n">pred</span><span class="p">,</span> <span class="n">pred_onx</span><span class="p">))</span>
|
||
</pre></div>
|
||
</div>
|
||
<p class="sphx-glr-script-out">Out:</p>
|
||
<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>0.9999999999999528
|
||
</pre></div>
|
||
</div>
|
||
<p>Very similar. <em>ONNX Runtime</em> uses floats instead of doubles,
|
||
that explains the small discrepencies.</p>
|
||
<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes 1.592 seconds)</p>
|
||
<div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-plot-convert-pipeline-vectorizer-py">
|
||
<div class="sphx-glr-download sphx-glr-download-python docutils container">
|
||
<p><a class="reference download internal" download="" href="../downloads/982a1f7abbb8ffc5d5e98b671c35e5aa/plot_convert_pipeline_vectorizer.py"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Python</span> <span class="pre">source</span> <span class="pre">code:</span> <span class="pre">plot_convert_pipeline_vectorizer.py</span></code></a></p>
|
||
</div>
|
||
<div class="sphx-glr-download sphx-glr-download-jupyter docutils container">
|
||
<p><a class="reference download internal" download="" href="../downloads/3aca744422de94d33f9aaa3ce99633a9/plot_convert_pipeline_vectorizer.ipynb"><code class="xref download docutils literal notranslate"><span class="pre">Download</span> <span class="pre">Jupyter</span> <span class="pre">notebook:</span> <span class="pre">plot_convert_pipeline_vectorizer.ipynb</span></code></a></p>
|
||
</div>
|
||
</div>
|
||
<p class="sphx-glr-signature"><a class="reference external" href="https://sphinx-gallery.github.io">Gallery generated by Sphinx-Gallery</a></p>
|
||
</div>
|
||
</div>
|
||
|
||
|
||
</div>
|
||
|
||
</div>
|
||
</div>
|
||
<div class="sphinxsidebar" role="navigation" aria-label="main navigation">
|
||
<div class="sphinxsidebarwrapper">
|
||
<p class="logo"><a href="../index.html">
|
||
<img class="logo" src="../static/ONNX_Runtime_icon.png" alt="Logo"/>
|
||
</a></p>
|
||
<h1 class="logo"><a href="../index.html">ONNX Runtime</a></h1>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<h3>Navigation</h3>
|
||
<ul>
|
||
<li class="toctree-l1"><a class="reference internal" href="../tutorial.html">Tutorial</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="../api_summary.html">API Summary</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="index.html">Gallery of examples</a></li>
|
||
</ul>
|
||
|
||
<div class="relations">
|
||
<h3>Related Topics</h3>
|
||
<ul>
|
||
<li><a href="../index.html">Documentation overview</a><ul>
|
||
<li><a href="index.html">Gallery of examples</a><ul>
|
||
<li>Previous: <a href="plot_profiling.html" title="previous chapter">Profile the execution of a simple model</a></li>
|
||
<li>Next: <a href="plot_common_errors.html" title="next chapter">Common errors with onnxruntime</a></li>
|
||
</ul></li>
|
||
</ul></li>
|
||
</ul>
|
||
</div>
|
||
<div id="searchbox" style="display: none" role="search">
|
||
<h3 id="searchlabel">Quick search</h3>
|
||
<div class="searchformwrapper">
|
||
<form class="search" action="../search.html" method="get">
|
||
<input type="text" name="q" aria-labelledby="searchlabel" />
|
||
<input type="submit" value="Go" />
|
||
</form>
|
||
</div>
|
||
</div>
|
||
<script>$('#searchbox').show(0);</script>
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
</div>
|
||
</div>
|
||
<div class="clearer"></div>
|
||
</div>
|
||
<div class="footer">
|
||
©2018-2021, Microsoft.
|
||
|
||
|
|
||
Powered by <a href="http://sphinx-doc.org/">Sphinx 3.5.1</a>
|
||
& <a href="https://github.com/bitprophet/alabaster">Alabaster 0.7.12</a>
|
||
|
||
|
|
||
<a href="../sources/auto_examples/plot_convert_pipeline_vectorizer.rst.txt"
|
||
rel="nofollow">Page source</a>
|
||
</div>
|
||
|
||
|
||
|
||
|
||
</body>
|
||
</html> |