:orphan:

|rss_image|  **blog page - 1/3** :ref:`==> <ap-main-1>` :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

----


.. index:: blog


.. _ap-main-0:

blog page - 1/3
+++++++++++++++

.. blogpostagg::
    :title: Don't use id(node)
    :date: 2022-11-15
    :keywords: onnx,protobuf,id
    :categories: bug
    :rawfile: 2022/2022-11-15_idnode.rst

    I was expecting the following code to be produce unique keys.
    But it seems python objects for the nodes are created one the fly
    and destroyed in the same loop. Then `id(node)` are not unique.
    

    ...




.. blogpostagg::
    :title: Array API
    :date: 2022-06-29
    :keywords: onnx,numpy,API,array
    :categories: api
    :rawfile: 2022/2022-06-29_array_api.rst

    `Python array API <https://data-apis.org/array-api/latest/>`_
    
    `Path for Adopting the Array API spec
    <https://github.com/scikit-learn/scikit-learn/issues/22352>`_
    
    `ENH Adds Array API support to LinearDiscriminantAnalysis
    <https://github.com/scikit-learn/scikit-learn/pull/22554>`_
    
    `array-api-tests
    <https://github.com/data-apis/array-api-tests>`_
    
    `NEP 47 — Adopting the array API standard
    <https://numpy.org/neps/nep-0047-array-api-standard.html>`_
    
    `napari
    <https://napari.org/index.html>`_
    
    `PyTorch and Python Data API comparison
    <https://docs.google.com/spreadsheets/d/13amsIeHhe38apCeZrOmsbsHT-aysmYur9-cugw5jVg0/edit#gid=1251843034>`_
    
    `NVFuser <https://github.com/pytorch/pytorch/blob/release/1.12/torch/csrc/jit/codegen/cuda/README.md>`_s




.. blogpostagg::
    :title: ONNX Backend Scoreboard
    :date: 2022-05-29
    :keywords: onnx,coverage,scoreboard
    :categories: benchmark
    :rawfile: 2022/2022-05-29_onnxcov.rst

    `ONNX Backend Scoreboard
    <http://onnx.ai/backend-scoreboard/index.html>`_
    shows how many operators a runtime supports.
    Page :ref:`l-backend-python-coverage` computes the
    same figure for the Python Runtime implemented
    in this package, more than 90%.




.. blogpostagg::
    :title: Xop, easy to create onnx graph
    :date: 2022-02-27
    :keywords: tips,tensorflow,tensorflow-onnx
    :categories: xop,onnx
    :rawfile: 2022/2022-02-27_xop.rst

    :epkg:`onnx` package has a very verbose API to create ONNX
    graph. Could you imagine a user to directly write the syntax tree
    of a program instead of some python code? Creating a ONNX graph is
    very similar to that task except ONNX language is more simple
    than python.
    

    ...




.. blogpostagg::
    :title: A few tricks for tf2onnx
    :date: 2021-08-12
    :keywords: tips,tensorflow,tensorflow-onnx
    :categories: tf2onnx
    :rawfile: 2021/2021-08-12_tf2onnx.rst

    A few things I tend to forget. To run a specific
    test on a specific opset.
    

    ...




.. blogpostagg::
    :title: Decompose einsum into numpy operators
    :date: 2021-08-11
    :keywords: einsum
    :categories: onnx
    :rawfile: 2021/2021-08-11_einsum.rst

    Notebook :ref:`einsumdecompositionrst` what function :epkg:`numpy:einsum`
    does and how it can be decomposed into a series of basic operations,
    all available in ONNX. That's the purpose of function
    Function :func:`decompose_einsum_equation
    <mlprodict.testing.einsum.einsum_impl.decompose_einsum_equation>`.
    With function :func:`export2numpy
    <mlprodict.onnx_tools.onnx_export.export2numpy>`, it is possible to
    convert back this ONNX graph into a series of numpy operations.
    

    ...




.. blogpostagg::
    :title: onnxruntime shape [] != None
    :date: 2021-08-10
    :keywords: onnxruntime
    :categories: onnx
    :rawfile: 2021/2021-08-10_shape.rst

    `None` is the undefined shape, `[]` is an empty shape.
    And when shapes do not fit the results, the outputs can
    be suprising. The following example shows what :epkg:`onnxruntime`
    produces for the same graph except input and output shapes
    when defined as `None` and `[]`.
    

    ...




.. blogpostagg::
    :title: ONNX from C#
    :date: 2021-07-09
    :keywords: ONNX,C#
    :categories: runtime
    :rawfile: 2021/2021-07-09_csharp.rst

    This example shows how to compute the predictions of a model
    using C#.
    

    ...




.. blogpostagg::
    :title: Convert a Lightgbm dump
    :date: 2021-07-09
    :keywords: ONNX,lightgbm,onnxmltools
    :categories: converters
    :rawfile: 2021/2021-07-09_lightgbm.rst

    This example shows how to convert a :epkg:`lightgbm` model
    dumped as a text file. It uses :epkg:`lightgbm` to restore
    the model, converts it and checks the discrepencies.
    

    ...




.. blogpostagg::
    :title: Numpy API for ONNX and scikit-learn (part II)
    :date: 2021-05-05
    :keywords: ONNX,API,numpy,scikit-learn
    :categories: API
    :rawfile: 2021/2021-05-05_numpyapionnx2.rst

    This follows blog post :ref:`Numpy API for ONNX and scikit-learn (part I)
    <blog-onnx-api-part1>`. It demonstrated how to insert a custom
    function in a pipeline and still be able to convert that pipeline
    into ONNX. This blog post shows how to implement a custom transformer.
    

    ...





----

|rss_image|  **blog page - 1/3** :ref:`==> <ap-main-1>` :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>`