:orphan:



.. _sphx_glr_auto_examples:

Examples
========



.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="ONNX operators does not contain operator from numpy. There is no operator for `solve &lt;https://n...">

.. only:: html

 .. figure:: /auto_examples/images/thumb/sphx_glr_plot_qextend_onnxruntime_thumb.png
     :alt: Fast runtime with onnxruntime

     :ref:`sphx_glr_auto_examples_plot_qextend_onnxruntime.py`

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_qextend_onnxruntime

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This program starts from an example in scikit-learn documentation: `Plot individual and voting ...">

.. only:: html

 .. figure:: /auto_examples/images/thumb/sphx_glr_plot_abegin_convert_pipeline_thumb.png
     :alt: Train and deploy a scikit-learn pipeline

     :ref:`sphx_glr_auto_examples_plot_abegin_convert_pipeline.py`

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_abegin_convert_pipeline

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Every library is versioned. scikit-learn may change the implementation of a specific model. Tha...">

.. only:: html

 .. figure:: /auto_examples/images/thumb/sphx_glr_plot_cbegin_opset_thumb.png
     :alt: What is the opset number?

     :ref:`sphx_glr_auto_examples_plot_cbegin_opset.py`

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_cbegin_opset

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="sklearn-onnx only converts scikit-learn models into *ONNX* but many libraries implement scikit-...">

.. only:: html

 .. figure:: /auto_examples/images/thumb/sphx_glr_plot_gexternal_lightgbm_thumb.png
     :alt: Convert a pipeline with a LightGBM model

     :ref:`sphx_glr_auto_examples_plot_gexternal_lightgbm.py`

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_gexternal_lightgbm

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="There are many reasons why a user wants more than using the converted model into ONNX. Intermed...">

.. only:: html

 .. figure:: /auto_examples/images/thumb/sphx_glr_plot_fbegin_investigate_thumb.png
     :alt: Intermediate results and investigation

     :ref:`sphx_glr_auto_examples_plot_fbegin_investigate.py`

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_fbegin_investigate

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Some runtimes do not implement a runtime for every available operator in ONNX. The converter do...">

.. only:: html

 .. figure:: /auto_examples/images/thumb/sphx_glr_plot_dbegin_options_list_thumb.png
     :alt: Black list operators when converting

     :ref:`sphx_glr_auto_examples_plot_dbegin_options_list.py`

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_dbegin_options_list

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Example l-simple-deploy-1 converts a simple model. This example takes a similar example but on ...">

.. only:: html

 .. figure:: /auto_examples/images/thumb/sphx_glr_plot_bbegin_measure_time_thumb.png
     :alt: Benchmark ONNX conversion

     :ref:`sphx_glr_auto_examples_plot_bbegin_measure_time.py`

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_bbegin_measure_time

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="A pipeline usually ingests data as a matrix. It may be converted in a matrix if all the data sh...">

.. only:: html

 .. figure:: /auto_examples/images/thumb/sphx_glr_plot_gbegin_dataframe_thumb.png
     :alt: Dataframe as an input

     :ref:`sphx_glr_auto_examples_plot_gbegin_dataframe.py`

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_gbegin_dataframe

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="There is not one way to convert a model. A new operator might have been added in a newer versio...">

.. only:: html

 .. figure:: /auto_examples/images/thumb/sphx_glr_plot_dbegin_options_thumb.png
     :alt: One model, many possible conversions with options

     :ref:`sphx_glr_auto_examples_plot_dbegin_options.py`

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_dbegin_options

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="In many cases, a custom models leverages existing models which already have an associated conve...">

.. only:: html

 .. figure:: /auto_examples/images/thumb/sphx_glr_plot_kcustom_converter_wrapper_thumb.png
     :alt: Implement a new converter using other converters

     :ref:`sphx_glr_auto_examples_plot_kcustom_converter_wrapper.py`

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_kcustom_converter_wrapper

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="By default, sklearn-onnx assumes that a classifier has two outputs (label and probabilities), a...">

.. only:: html

 .. figure:: /auto_examples/images/thumb/sphx_glr_plot_mcustom_parser_thumb.png
     :alt: Change the number of outputs by adding a parser

     :ref:`sphx_glr_auto_examples_plot_mcustom_parser.py`

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_mcustom_parser

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="There are two ways to write a converter. The first one is very verbose (see `ada_boost.py &lt;http...">

.. only:: html

 .. figure:: /auto_examples/images/thumb/sphx_glr_plot_jcustom_syntax_thumb.png
     :alt: Two ways to implement a converter

     :ref:`sphx_glr_auto_examples_plot_jcustom_syntax.py`

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_jcustom_syntax

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="sklearn-onnx only converts scikit-learn models into ONNX but many libraries implement scikit-le...">

.. only:: html

 .. figure:: /auto_examples/images/thumb/sphx_glr_plot_gexternal_xgboost_thumb.png
     :alt: Convert a pipeline with a XGBoost model

     :ref:`sphx_glr_auto_examples_plot_gexternal_xgboost.py`

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_gexternal_xgboost

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Options are used to implement different conversion for a same model. The options can be used to...">

.. only:: html

 .. figure:: /auto_examples/images/thumb/sphx_glr_plot_lcustom_options_thumb.png
     :alt: A new converter with options

     :ref:`sphx_glr_auto_examples_plot_lcustom_options.py`

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_lcustom_options

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Transfer learning is common with deep learning. A deep learning model is used as preprocessing ...">

.. only:: html

 .. figure:: /auto_examples/images/thumb/sphx_glr_plot_gbegin_transfer_learning_thumb.png
     :alt: Transfer Learning with ONNX

     :ref:`sphx_glr_auto_examples_plot_gbegin_transfer_learning.py`

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_gbegin_transfer_learning

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Most models in scikit-learn do computation with double, not float. Most models in deep learning...">

.. only:: html

 .. figure:: /auto_examples/images/thumb/sphx_glr_plot_ebegin_float_double_thumb.png
     :alt: Issues when switching to float

     :ref:`sphx_glr_auto_examples_plot_ebegin_float_double.py`

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_ebegin_float_double

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="By default, sklearn-onnx assumes that a classifier has two outputs (label and probabilities), a...">

.. only:: html

 .. figure:: /auto_examples/images/thumb/sphx_glr_plot_icustom_converter_thumb.png
     :alt: Implement a new converter

     :ref:`sphx_glr_auto_examples_plot_icustom_converter.py`

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_icustom_converter

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="`TfidfVectorizer &lt;https://scikit-learn.org/stable/modules/ generated/sklearn.feature_extraction...">

.. only:: html

 .. figure:: /auto_examples/images/thumb/sphx_glr_plot_usparse_xgboost_thumb.png
     :alt: TfIdf and sparse matrices

     :ref:`sphx_glr_auto_examples_plot_usparse_xgboost.py`

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_usparse_xgboost

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="ONNX operators do not contain all operators from numpy. There is no operator for `solve &lt;https:...">

.. only:: html

 .. figure:: /auto_examples/images/thumb/sphx_glr_plot_pextend_python_runtime_thumb.png
     :alt: Fast design with a python runtime

     :ref:`sphx_glr_auto_examples_plot_pextend_python_runtime.py`

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_pextend_python_runtime

.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="l-custom-parser shows how to add a parser to define a converter a model which works differently...">

.. only:: html

 .. figure:: /auto_examples/images/thumb/sphx_glr_plot_mcustom_parser_dataframe_thumb.png
     :alt: Add a parser to handle dataframes

     :ref:`sphx_glr_auto_examples_plot_mcustom_parser_dataframe.py`

.. raw:: html

    </div>


.. toctree::
   :hidden:

   /auto_examples/plot_mcustom_parser_dataframe
.. raw:: html

    <div class="sphx-glr-clear"></div>



.. only :: html

 .. container:: sphx-glr-footer
    :class: sphx-glr-footer-gallery


  .. container:: sphx-glr-download sphx-glr-download-python

    :download:`Download all examples in Python source code: auto_examples_python.zip </auto_examples/auto_examples_python.zip>`



  .. container:: sphx-glr-download sphx-glr-download-jupyter

    :download:`Download all examples in Jupyter notebooks: auto_examples_jupyter.zip </auto_examples/auto_examples_jupyter.zip>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_