.. DO NOT EDIT. .. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY. .. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE: .. "auto_examples/plot_black_op.py" .. LINE NUMBERS ARE GIVEN BELOW. .. only:: html .. note:: :class: sphx-glr-download-link-note :ref:`Go to the end ` to download the full example code .. rst-class:: sphx-glr-example-title .. _sphx_glr_auto_examples_plot_black_op.py: .. _l-black-op: Convert a model with a reduced list of operators ================================================ Some runtime dedicated to onnx do not implement all the operators and a converted model may not run if one of them is missing from the list of available operators. Some converters may convert a model in different ways if the users wants to blacklist some operators. .. contents:: :local: GaussianMixture +++++++++++++++ The first converter to change its behaviour depending on a black list of operators is for model *GaussianMixture*. .. GENERATED FROM PYTHON SOURCE LINES 25-44 .. code-block:: default import onnxruntime import onnx import numpy import os from timeit import timeit import numpy as np import matplotlib.pyplot as plt from onnx.tools.net_drawer import GetPydotGraph, GetOpNodeProducer from onnxruntime import InferenceSession from sklearn.mixture import GaussianMixture from sklearn.datasets import load_iris from sklearn.model_selection import train_test_split from skl2onnx import to_onnx data = load_iris() X_train, X_test = train_test_split(data.data) model = GaussianMixture() model.fit(X_train) .. raw:: html

GaussianMixture()

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

.. GENERATED FROM PYTHON SOURCE LINES 45-47 Default conversion ++++++++++++++++++ .. GENERATED FROM PYTHON SOURCE LINES 47-60 .. code-block:: default model_onnx = to_onnx( model, X_train[:1].astype(np.float32), options={id(model): {'score_samples': True}}, target_opset=12) sess = InferenceSession(model_onnx.SerializeToString(), providers=["CPUExecutionProvider"]) xt = X_test[:5].astype(np.float32) print(model.score_samples(xt)) print(sess.run(None, {'X': xt})[2]) .. rst-class:: sphx-glr-script-out .. code-block:: none [-1.72919528 -1.85788654 -5.59535063 -2.38812314 -3.28480539] [[-1.7291949] [-1.8578851] [-5.595351 ] [-2.3881223] [-3.2848065]] .. GENERATED FROM PYTHON SOURCE LINES 61-62 Display the ONNX graph. .. GENERATED FROM PYTHON SOURCE LINES 62-77 .. code-block:: default pydot_graph = GetPydotGraph( model_onnx.graph, name=model_onnx.graph.name, rankdir="TB", node_producer=GetOpNodeProducer("docstring", color="yellow", fillcolor="yellow", style="filled")) pydot_graph.write_dot("mixture.dot") os.system('dot -O -Gdpi=300 -Tpng mixture.dot') image = plt.imread("mixture.dot.png") fig, ax = plt.subplots(figsize=(40, 20)) ax.imshow(image) ax.axis('off') .. image-sg:: /auto_examples/images/sphx_glr_plot_black_op_001.png :alt: plot black op :srcset: /auto_examples/images/sphx_glr_plot_black_op_001.png :class: sphx-glr-single-img .. rst-class:: sphx-glr-script-out .. code-block:: none (-0.5, 4023.5, 8425.5, -0.5) .. GENERATED FROM PYTHON SOURCE LINES 78-84 Conversion without ReduceLogSumExp ++++++++++++++++++++++++++++++++++ Parameter *black_op* is used to tell the converter not to use this operator. Let's see what the converter produces in that case. .. GENERATED FROM PYTHON SOURCE LINES 84-97 .. code-block:: default model_onnx2 = to_onnx( model, X_train[:1].astype(np.float32), options={id(model): {'score_samples': True}}, black_op={'ReduceLogSumExp'}, target_opset=12) sess2 = InferenceSession(model_onnx2.SerializeToString(), providers=["CPUExecutionProvider"]) xt = X_test[:5].astype(np.float32) print(model.score_samples(xt)) print(sess2.run(None, {'X': xt})[2]) .. rst-class:: sphx-glr-script-out .. code-block:: none [-1.72919528 -1.85788654 -5.59535063 -2.38812314 -3.28480539] [[-1.7291949] [-1.8578851] [-5.595351 ] [-2.3881223] [-3.2848065]] .. GENERATED FROM PYTHON SOURCE LINES 98-99 Display the ONNX graph. .. GENERATED FROM PYTHON SOURCE LINES 99-114 .. code-block:: default pydot_graph = GetPydotGraph( model_onnx2.graph, name=model_onnx2.graph.name, rankdir="TB", node_producer=GetOpNodeProducer("docstring", color="yellow", fillcolor="yellow", style="filled")) pydot_graph.write_dot("mixture2.dot") os.system('dot -O -Gdpi=300 -Tpng mixture2.dot') image = plt.imread("mixture2.dot.png") fig, ax = plt.subplots(figsize=(40, 20)) ax.imshow(image) ax.axis('off') .. image-sg:: /auto_examples/images/sphx_glr_plot_black_op_002.png :alt: plot black op :srcset: /auto_examples/images/sphx_glr_plot_black_op_002.png :class: sphx-glr-single-img .. rst-class:: sphx-glr-script-out .. code-block:: none (-0.5, 4143.5, 13264.5, -0.5) .. GENERATED FROM PYTHON SOURCE LINES 115-117 Processing time +++++++++++++++ .. GENERATED FROM PYTHON SOURCE LINES 117-124 .. code-block:: default print(timeit(stmt="sess.run(None, {'X': xt})", number=10000, globals={'sess': sess, 'xt': xt})) print(timeit(stmt="sess2.run(None, {'X': xt})", number=10000, globals={'sess2': sess2, 'xt': xt})) .. rst-class:: sphx-glr-script-out .. code-block:: none 1.7430899823084474 1.9910656181164086 .. GENERATED FROM PYTHON SOURCE LINES 125-126 The model using ReduceLogSumExp is much faster. .. GENERATED FROM PYTHON SOURCE LINES 128-135 If the converter cannot convert without... ++++++++++++++++++++++++++++++++++++++++++ Many converters do not consider the white and black lists of operators. If a converter fails to convert without using a blacklisted operator (or only whitelisted operators), *skl2onnx* raises an error. .. GENERATED FROM PYTHON SOURCE LINES 135-146 .. code-block:: default try: to_onnx( model, X_train[:1].astype(np.float32), options={id(model): {'score_samples': True}}, black_op={'ReduceLogSumExp', 'Add'}, target_opset=12) except RuntimeError as e: print('Error:', e) .. rst-class:: sphx-glr-script-out .. code-block:: none Error: Operator 'Add' is black listed. .. GENERATED FROM PYTHON SOURCE LINES 147-148 **Versions used for this example** .. GENERATED FROM PYTHON SOURCE LINES 148-156 .. code-block:: default import sklearn # noqa print("numpy:", numpy.__version__) print("scikit-learn:", sklearn.__version__) import skl2onnx # noqa print("onnx: ", onnx.__version__) print("onnxruntime: ", onnxruntime.__version__) print("skl2onnx: ", skl2onnx.__version__) .. rst-class:: sphx-glr-script-out .. code-block:: none numpy: 1.23.5 scikit-learn: 1.2.2 onnx: 1.13.1 onnxruntime: 1.14.1 skl2onnx: 1.14.0 .. rst-class:: sphx-glr-timing **Total running time of the script:** ( 1 minutes 0.423 seconds) .. _sphx_glr_download_auto_examples_plot_black_op.py: .. only:: html .. container:: sphx-glr-footer sphx-glr-footer-example .. container:: sphx-glr-download sphx-glr-download-python :download:`Download Python source code: plot_black_op.py ` .. container:: sphx-glr-download sphx-glr-download-jupyter :download:`Download Jupyter notebook: plot_black_op.ipynb ` .. only:: html .. rst-class:: sphx-glr-signature `Gallery generated by Sphinx-Gallery `_