:orphan:

|rss_image| :ref:`<== <ap-main-1>`  **blog page - 3/3** :ref:`Blog <ap-main-0>` :ref:`benchmark (4) <ap-cat-benchmark-0>` :ref:`onnx (8) <ap-cat-onnx-0>`

.. |rss_image| image:: feed-icon-16x16.png
    :target: ../_downloads/rss.xml
    :alt: RSS

----


.. _ap-main-2:

blog page - 3/3
+++++++++++++++

.. blogpostagg::
    :title: ONNX, runtime, converters
    :date: 2019-06-15
    :keywords: onnx,onnxrt
    :categories: onnx
    :rawfile: 2019/2019-06-15_onnxrt.rst

    I have been recently working on :epkg:`sklearn-onnx`
    to write converter from :epkg:`scikit-learn` operators
    to :epkg:`ONNX` serialization format. I was talking
    about that a month ago and somebody asked me if there
    was a runtime implemented in `RUST <https://www.rust-lang.org/>`_.
    Not that I know of but I said it would not be too complex
    to implement one.
    

    ...




.. blogpostagg::
    :title: XGBoost into python code
    :date: 2018-04-30
    :keywords: xgboost,pyxgboost,python
    :categories: modules
    :rawfile: 2018/2018-04-30_anothersimilar.rst

    Package `pyxgboost <https://github.com/KOLANICH/pyxgboost>`_
    converts a tree from :epkg:`xgboost` into a :epkg:`Python` code.
    :epkg:`Python` still needs to be used if the models
    has to be deployed but it should be faster for small models.




.. blogpostagg::
    :title: Similar projects
    :date: 2018-03-31
    :keywords: sklearn-porter,onnx,onnxmltools,winmltools
    :categories: modules
    :rawfile: 2018/2018-03-31_similar_project.rst

    I would not say this module is actively maintained.
    It was more fun to have the idea, to test it on some
    simple model than to extend its coverage to all available
    models in :epkg:`scikit-learn`. Some altenatives exists
    but it is still ongoing work.
    `sklearn-porter <https://github.com/nok/sklearn-porter>`_
    proposed to produce code into many languages,
    C++, Javascipt, PHP, Java, Ruby, Go. It only includes
    learners and not transforms.
    `onnx <https://github.com/onnx/onnx>`_ proposes to convert
    any models into a unified format. This module implements
    the format,
    `onnxmltools <https://github.com/onnx/onnxmltools>`_,
    `winmltools <https://pypi.python.org/pypi/winmltools>`_
    do the conversion of many models from
    :epkg:`scikit-learn`,
    `xgboost <https://github.com/dmlc/xgboost>`_,
    `lightgbm <https://github.com/Microsoft/LightGBM>`_.
    The produced file can be used to run prediction on GPU
    and Windows with a dedicated runtime.




.. blogpostagg::
    :title: Why mlprodict?
    :date: 2017-11-30
    :keywords: reference,blog,post
    :categories: documentation
    :rawfile: 2017/2017-11-30_first.rst

    What about predicting with :epkg:`scikit-learn`
    with :epkg:`C` but still training in :epkg:`Python`?





----

|rss_image| :ref:`<== <ap-main-1>`  **blog page - 3/3** :ref:`2021-08 (3) <ap-month-2021-08-0>` :ref:`2022-02 (1) <ap-month-2022-02-0>` :ref:`2022-05 (1) <ap-month-2022-05-0>` :ref:`2022-06 (1) <ap-month-2022-06-0>` :ref:`2022-11 (1) <ap-month-2022-11-0>`