[Automated]: Update Python API docs

docs/api/python/auto_examples/plot_backend.html

@@ -102,7 +102,7 @@
 <p>The backend API is implemented by other frameworks
 and makes it easier to switch between multiple runtimes
 with the same API.</p>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.015 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.017 seconds)</p>
 <div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-plot-backend-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../downloads/3e23fa9ebb26f4728ee8426ed7da0f63/plot_backend.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_backend.py</span></code></a></p>

docs/api/python/auto_examples/plot_common_errors.html

@@ -203,7 +203,7 @@
 ERROR with Shape=(2, 1, 2) - [ONNXRuntimeError] : 2 : INVALID_ARGUMENT : Invalid rank for input: float_input Got: 3 Expected: 2 Please fix either the inputs or the model.
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.008 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.012 seconds)</p>
 <div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-plot-common-errors-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../downloads/3a2955e44bf8f95a0eee6e71695ad788/plot_common_errors.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_common_errors.py</span></code></a></p>

docs/api/python/auto_examples/plot_convert_pipeline_vectorizer.html

@@ -134,7 +134,7 @@ <h2><a class="toc-backref" href="#id1">Train a pipeline</a><a class="headerlink"
 </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>0.8875422353009019
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>0.8427444349522607
 </pre></div>
 </div>
 </section>
@@ -193,12 +193,12 @@ <h2><a class="toc-backref" href="#id2">Conversion to ONNX format</a><a class="he
 </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>0.9999999999999098
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>0.9999999999999056
 </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  0.977 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  1.181 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>

docs/api/python/auto_examples/plot_load_and_predict.html

@@ -98,24 +98,24 @@
 </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>[array([[[0.6510769 , 0.53574014, 0.5246311 , 0.7076354 , 0.62458384],
-        [0.6178043 , 0.6118449 , 0.55362356, 0.530993  , 0.51342654],
-        [0.51229876, 0.63369405, 0.53360677, 0.6799468 , 0.6856118 ],
-        [0.61446375, 0.5756609 , 0.58993536, 0.52939814, 0.5155214 ]],
-
-       [[0.5833087 , 0.5912285 , 0.5129974 , 0.52104723, 0.5589873 ],
-        [0.6912771 , 0.67039084, 0.6275468 , 0.6388816 , 0.7219965 ],
-        [0.7254892 , 0.5989482 , 0.55460036, 0.5609656 , 0.5783487 ],
-        [0.7270879 , 0.6662836 , 0.6403104 , 0.59592724, 0.5243805 ]],
-
-       [[0.6805607 , 0.5933663 , 0.7285657 , 0.54098815, 0.607139  ],
-        [0.6130347 , 0.72747064, 0.65980005, 0.57267225, 0.62237465],
-        [0.69912946, 0.58575433, 0.7252008 , 0.5705788 , 0.5725795 ],
-        [0.6403949 , 0.64117014, 0.6178422 , 0.55547553, 0.6336622 ]]],
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[array([[[0.62922037, 0.561156  , 0.5080795 , 0.6244578 , 0.5731013 ],
+        [0.70947427, 0.6941823 , 0.62022245, 0.62342674, 0.6543724 ],
+        [0.5332583 , 0.6587574 , 0.59361964, 0.62477636, 0.6500683 ],
+        [0.6214162 , 0.60647833, 0.6681156 , 0.7199558 , 0.5032289 ]],
+
+       [[0.536524  , 0.6299298 , 0.6306909 , 0.6419255 , 0.68945134],
+        [0.67906946, 0.71493363, 0.6613402 , 0.61385757, 0.5439159 ],
+        [0.64069986, 0.6363738 , 0.541755  , 0.58712244, 0.5134371 ],
+        [0.69225496, 0.5437989 , 0.66372246, 0.7143415 , 0.57663304]],
+
+       [[0.68010736, 0.50777453, 0.5135236 , 0.6203964 , 0.7076469 ],
+        [0.715078  , 0.63704497, 0.6765113 , 0.52124536, 0.5760229 ],
+        [0.50323224, 0.69429994, 0.574678  , 0.58742845, 0.631329  ],
+        [0.6279564 , 0.536385  , 0.5186675 , 0.64032906, 0.5367126 ]]],
       dtype=float32)]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.008 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.012 seconds)</p>
 <div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-plot-load-and-predict-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../downloads/7c8424f45d0156abd4d0221c65601124/plot_load_and_predict.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_load_and_predict.py</span></code></a></p>

docs/api/python/auto_examples/plot_metadata.html

@@ -99,7 +99,7 @@
 version=0
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.003 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.004 seconds)</p>
 <div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-plot-metadata-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../downloads/932fe1ee7f48f55a6155d2f378bc85a0/plot_metadata.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_metadata.py</span></code></a></p>

docs/api/python/auto_examples/plot_pipeline.html

@@ -168,10 +168,10 @@ <h2><a class="toc-backref" href="#id2">Draw a model with ONNX</a><a class="heade
 </pre></div>
 </div>
 <img src="../images/sphx_glr_plot_pipeline_001.png" srcset="../images/sphx_glr_plot_pipeline_001.png" alt="plot pipeline" class = "sphx-glr-single-img"/><p class="sphx-glr-script-out">Out:</p>
-<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;matplotlib.image.AxesImage object at 0x7f5f54bbbb20&gt;
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>&lt;matplotlib.image.AxesImage object at 0x7fd449283c10&gt;
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.284 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.221 seconds)</p>
 <div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-plot-pipeline-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../downloads/d436e9922b51a71358604ec00f09e7e4/plot_pipeline.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_pipeline.py</span></code></a></p>

docs/api/python/auto_examples/plot_profiling.html

@@ -96,7 +96,7 @@
 </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>onnxruntime_profile__2022-03-12_01-42-14.json
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>onnxruntime_profile__2022-03-14_22-35-38.json
 </pre></div>
 </div>
 <p>The results are stored un a file in JSON format.
@@ -111,23 +111,23 @@
 <p class="sphx-glr-script-out">Out:</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[{&#39;args&#39;: {},
   &#39;cat&#39;: &#39;Session&#39;,
-  &#39;dur&#39;: 71,
+  &#39;dur&#39;: 60,
   &#39;name&#39;: &#39;model_loading_array&#39;,
   &#39;ph&#39;: &#39;X&#39;,
-  &#39;pid&#39;: 3179,
-  &#39;tid&#39;: 3179,
-  &#39;ts&#39;: 2},
+  &#39;pid&#39;: 2949,
+  &#39;tid&#39;: 2949,
+  &#39;ts&#39;: 1},
  {&#39;args&#39;: {},
   &#39;cat&#39;: &#39;Session&#39;,
-  &#39;dur&#39;: 258,
+  &#39;dur&#39;: 240,
   &#39;name&#39;: &#39;session_initialization&#39;,
   &#39;ph&#39;: &#39;X&#39;,
-  &#39;pid&#39;: 3179,
-  &#39;tid&#39;: 3179,
-  &#39;ts&#39;: 90}]
+  &#39;pid&#39;: 2949,
+  &#39;tid&#39;: 2949,
+  &#39;ts&#39;: 80}]
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.005 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 0 minutes  0.008 seconds)</p>
 <div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-plot-profiling-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../downloads/cfe61aca1f0a89486c7024466ea500fd/plot_profiling.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_profiling.py</span></code></a></p>

docs/api/python/auto_examples/plot_train_convert_predict.html

@@ -73,16 +73,7 @@ <h2><a class="toc-backref" href="#id1">Train a logistic regression</a><a class="
 </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>/home/runner/.local/lib/python3.8/site-packages/sklearn/linear_model/_logistic.py:814: ConvergenceWarning: lbfgs failed to converge (status=1):
-STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.
-
-Increase the number of iterations (max_iter) or scale the data as shown in:
-    https://scikit-learn.org/stable/modules/preprocessing.html
-Please also refer to the documentation for alternative solver options:
-    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression
-  n_iter_i = _check_optimize_result(
-
-LogisticRegression()
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>LogisticRegression()
 </pre></div>
 </div>
 <p>We compute the prediction on the test set
@@ -94,9 +85,9 @@ <h2><a class="toc-backref" href="#id1">Train a logistic regression</a><a class="
 </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>[[11  0  0]
- [ 0 18  0]
- [ 0  0  9]]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[[13  0  0]
+ [ 0 10  2]
+ [ 0  0 13]]
 </pre></div>
 </div>
 </section>
@@ -140,9 +131,9 @@ <h2><a class="toc-backref" href="#id2">Conversion to ONNX format</a><a class="he
 </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>[[11  0  0]
- [ 0 18  0]
- [ 0  0  9]]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[[13  0  0]
+ [ 0 10  0]
+ [ 0  0 15]]
 </pre></div>
 </div>
 <p>The prediction are perfectly identical.</p>
@@ -158,9 +149,9 @@ <h2><a class="toc-backref" href="#id3">Probabilities</a><a class="headerlink" hr
 </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>[[1.14573460e-04 7.54078165e-02 9.24477610e-01]
- [2.53130984e-02 9.27734094e-01 4.69528077e-02]
- [2.45989404e-06 1.17669280e-02 9.88230612e-01]]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[[1.26071894e-02 8.64522533e-01 1.22870277e-01]
+ [9.19091446e-05 4.65963473e-02 9.53311744e-01]
+ [2.31274116e-02 9.49638079e-01 2.72345094e-02]]
 </pre></div>
 </div>
 <p>And then with ONNX Runtime.
@@ -173,9 +164,9 @@ <h2><a class="toc-backref" href="#id3">Probabilities</a><a class="headerlink" hr
 </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: 0.00011457340588094667, 1: 0.07540777325630188, 2: 0.9244776964187622},
- {0: 0.025313090533018112, 1: 0.9277341365814209, 2: 0.04695282503962517},
- {0: 2.459894403727958e-06, 1: 0.01176692359149456, 2: 0.9882306456565857}]
+<div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>[{0: 0.012607195414602757, 1: 0.864522397518158, 2: 0.12287036329507828},
+ {0: 9.190914715873078e-05, 1: 0.04659634083509445, 2: 0.9533118009567261},
+ {0: 0.02312742918729782, 1: 0.9496380686759949, 2: 0.027234479784965515}]
 </pre></div>
 </div>
 <p>Let’s benchmark.</p>
@@ -198,11 +189,11 @@ <h2><a class="toc-backref" href="#id3">Probabilities</a><a class="headerlink" hr
 </div>
 <p class="sphx-glr-script-out">Out:</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time for clr.predict
-Average 4.61e-05 min=3.94e-05 max=6.49e-05
+Average 7.82e-05 min=7.26e-05 max=9.47e-05
 Execution time for ONNX Runtime
-Average 2.28e-05 min=2.2e-05 max=2.82e-05
+Average 3.12e-05 min=2.83e-05 max=4.09e-05
 
-2.2846775000004982e-05
+3.116068000025507e-05
 </pre></div>
 </div>
 <p>Let’s benchmark a scenario similar to what a webservice
@@ -228,11 +219,11 @@ <h2><a class="toc-backref" href="#id3">Probabilities</a><a class="headerlink" hr
 </div>
 <p class="sphx-glr-script-out">Out:</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time for clr.predict
-Average 0.00406 min=0.00364 max=0.00451
+Average 0.00672 min=0.00652 max=0.00703
 Execution time for sess_predict
-Average 0.00103 min=0.000915 max=0.00109
+Average 0.00152 min=0.00146 max=0.00166
 
-0.001034282179998911
+0.0015232249750000903
 </pre></div>
 </div>
 <p>Let’s do the same for the probabilities.</p>
@@ -248,11 +239,11 @@ <h2><a class="toc-backref" href="#id3">Probabilities</a><a class="headerlink" hr
 </div>
 <p class="sphx-glr-script-out">Out:</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time for predict_proba
-Average 0.00624 min=0.00571 max=0.00771
+Average 0.00994 min=0.00965 max=0.0113
 Execution time for sess_predict_proba
-Average 0.00104 min=0.00088 max=0.00111
+Average 0.00158 min=0.00154 max=0.00166
 
-0.0010414897500004372
+0.0015761207799998545
 </pre></div>
 </div>
 <p>This second comparison is better as
@@ -288,11 +279,11 @@ <h2><a class="toc-backref" href="#id4">Benchmark with RandomForest</a><a class="
 </div>
 <p class="sphx-glr-script-out">Out:</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>Execution time for predict_proba
-Average 0.701 min=0.678 max=0.748
+Average 1.25 min=1.22 max=1.28
 Execution time for sess_predict_proba
-Average 0.001 min=0.000928 max=0.00113
+Average 0.00204 min=0.00196 max=0.00223
 
-0.0010013645900008327
+0.0020432242550009506
 </pre></div>
 </div>
 <p>Let’s see with different number of trees.</p>
@@ -326,40 +317,40 @@ <h2><a class="toc-backref" href="#id4">Benchmark with RandomForest</a><a class="
 </div>
 <img src="../images/sphx_glr_plot_train_convert_predict_001.png" srcset="../images/sphx_glr_plot_train_convert_predict_001.png" alt="Speed comparison between scikit-learn and ONNX Runtime For a random forest on Iris dataset" class = "sphx-glr-single-img"/><p class="sphx-glr-script-out">Out:</p>
 <div class="sphx-glr-script-out highlight-none notranslate"><div class="highlight"><pre><span></span>5
-Average 0.0623 min=0.0609 max=0.0637
-Average 0.000827 min=0.000764 max=0.000927
+Average 0.108 min=0.107 max=0.11
+Average 0.00132 min=0.00122 max=0.00148
 10
-Average 0.096 min=0.095 max=0.0966
-Average 0.000966 min=0.000837 max=0.00105
+Average 0.17 min=0.167 max=0.172
+Average 0.00138 min=0.00132 max=0.00152
 15
-Average 0.135 min=0.128 max=0.144
-Average 0.000857 min=0.000802 max=0.000915
+Average 0.233 min=0.231 max=0.236
+Average 0.00142 min=0.00134 max=0.0015
 20
-Average 0.173 min=0.164 max=0.186
-Average 0.00106 min=0.00103 max=0.0011
+Average 0.293 min=0.288 max=0.297
+Average 0.00176 min=0.00147 max=0.00277
 25
-Average 0.204 min=0.197 max=0.211
-Average 0.000966 min=0.000937 max=0.00101
+Average 0.355 min=0.347 max=0.36
+Average 0.0015 min=0.00144 max=0.0016
 30
-Average 0.232 min=0.228 max=0.234
-Average 0.000895 min=0.000789 max=0.000962
+Average 0.414 min=0.412 max=0.419
+Average 0.00154 min=0.0015 max=0.00157
 35
-Average 0.266 min=0.26 max=0.272
-Average 0.000964 min=0.000911 max=0.00101
+Average 0.472 min=0.47 max=0.476
+Average 0.00155 min=0.00145 max=0.00162
 40
-Average 0.304 min=0.295 max=0.316
-Average 0.00095 min=0.000807 max=0.00099
+Average 0.533 min=0.53 max=0.536
+Average 0.00161 min=0.00153 max=0.00176
 45
-Average 0.356 min=0.343 max=0.381
-Average 0.00101 min=0.00089 max=0.00117
+Average 0.589 min=0.588 max=0.591
+Average 0.00161 min=0.00154 max=0.00171
 50
-Average 0.394 min=0.38 max=0.411
-Average 0.00113 min=0.0011 max=0.00116
+Average 0.654 min=0.646 max=0.66
+Average 0.00174 min=0.00166 max=0.00183
 
-&lt;matplotlib.legend.Legend object at 0x7f5f44352130&gt;
+&lt;matplotlib.legend.Legend object at 0x7fd438d41220&gt;
 </pre></div>
 </div>
-<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 3 minutes  19.889 seconds)</p>
+<p class="sphx-glr-timing"><strong>Total running time of the script:</strong> ( 5 minutes  51.038 seconds)</p>
 <div class="sphx-glr-footer class sphx-glr-footer-example docutils container" id="sphx-glr-download-auto-examples-plot-train-convert-predict-py">
 <div class="sphx-glr-download sphx-glr-download-python docutils container">
 <p><a class="reference download internal" download="" href="../downloads/c647c128e0cf2b3db04ce60b41ef1a14/plot_train_convert_predict.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_train_convert_predict.py</span></code></a></p>