docs/_sources/how_to/compile_models/from_paddle.rst.txt

.. DO NOT EDIT. THIS FILE WAS AUTOMATICALLY GENERATED BY
.. TVM'S MONKEY-PATCHED VERSION OF SPHINX-GALLERY. TO MAKE
.. CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "how_to/compile_models/from_paddle.py"

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        This tutorial can be used interactively with Google Colab! You can also click
        :ref:`here <sphx_glr_download_how_to_compile_models_from_paddle.py>` to run the Jupyter notebook locally.

        .. image:: https://raw.githubusercontent.com/tlc-pack/web-data/main/images/utilities/colab_button.svg
            :align: center
            :target: https://colab.research.google.com/github/apache/tvm-site/blob/asf-site/docs/_downloads/a608d8b69371e9bc149dd89f6db2c38e/from_paddle.ipynb
            :width: 300px

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_how_to_compile_models_from_paddle.py:


Compile PaddlePaddle Models
===========================
**Author**: `Ziyuan Ma <https://github.com/ZiyuanMa/>`_

This article is an introductory tutorial to deploy PaddlePaddle models with Relay.
To begin, we'll install PaddlePaddle>=2.1.3:

.. code-block:: bash

    %%shell
    pip install paddlepaddle -i https://mirror.baidu.com/pypi/simple

For more details, refer to the official install instructions at:
https://www.paddlepaddle.org.cn/install/quick?docurl=/documentation/docs/zh/install/pip/linux-pip.html

.. GENERATED FROM PYTHON SOURCE LINES 33-41

.. code-block:: default


    import tarfile
    import paddle
    import numpy as np
    import tvm
    from tvm import relay
    from tvm.contrib.download import download_testdata








.. GENERATED FROM PYTHON SOURCE LINES 42-45

Load pretrained ResNet50 model
---------------------------------------------
We load a pretrained ResNet50 provided by PaddlePaddle.

.. GENERATED FROM PYTHON SOURCE LINES 45-55

.. code-block:: default

    url = "https://bj.bcebos.com/x2paddle/models/paddle_resnet50.tar"
    model_path = download_testdata(url, "paddle_resnet50.tar", module="model")

    with tarfile.open(model_path) as tar:
        names = tar.getnames()
        for name in names:
            tar.extract(name, "./")

    model = paddle.jit.load("./paddle_resnet50/model")








.. GENERATED FROM PYTHON SOURCE LINES 56-59

Load a test image
---------------------------------------------
A single cat dominates the examples!

.. GENERATED FROM PYTHON SOURCE LINES 59-80

.. code-block:: default


    from PIL import Image
    import paddle.vision.transforms as T


    transforms = T.Compose(
        [
            T.Resize((256, 256)),
            T.CenterCrop(224),
            T.ToTensor(),
            T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
        ]
    )

    img_url = "https://github.com/dmlc/mxnet.js/blob/main/data/cat.png?raw=true"
    img_path = download_testdata(img_url, "cat.png", module="data")
    img = Image.open(img_path).resize((224, 224))

    img = transforms(img)
    img = np.expand_dims(img, axis=0)








.. GENERATED FROM PYTHON SOURCE LINES 81-83

Compile the model with relay
---------------------------------------------

.. GENERATED FROM PYTHON SOURCE LINES 83-93

.. code-block:: default


    target = "llvm"
    shape_dict = {"inputs": img.shape}
    mod, params = relay.frontend.from_paddle(model, shape_dict)

    with tvm.transform.PassContext(opt_level=3):
        executor = relay.build_module.create_executor(
            "graph", mod, tvm.cpu(0), target, params
        ).evaluate()








.. GENERATED FROM PYTHON SOURCE LINES 94-96

Execute on TVM
---------------------------------------------

.. GENERATED FROM PYTHON SOURCE LINES 96-99

.. code-block:: default

    dtype = "float32"
    tvm_output = executor(tvm.nd.array(img.astype(dtype))).numpy()








.. GENERATED FROM PYTHON SOURCE LINES 100-103

Look up synset name
---------------------------------------------
Look up prediction top 1 index in 1000 class synset.

.. GENERATED FROM PYTHON SOURCE LINES 103-119

.. code-block:: default


    synset_url = "".join(
        [
            "https://gist.githubusercontent.com/zhreshold/",
            "4d0b62f3d01426887599d4f7ede23ee5/raw/",
            "596b27d23537e5a1b5751d2b0481ef172f58b539/",
            "imagenet1000_clsid_to_human.txt",
        ]
    )
    synset_name = "imagenet1000_clsid_to_human.txt"
    synset_path = download_testdata(synset_url, synset_name, module="data")
    with open(synset_path) as f:
        synset = f.readlines()

    top1 = np.argmax(tvm_output[0])
    print(f"TVM prediction top-1 id: {top1}, class name: {synset[top1]}")




.. rst-class:: sphx-glr-script-out

 .. code-block:: none

    TVM prediction top-1 id: 282, class name:  282: 'tiger cat',






.. rst-class:: sphx-glr-timing

   **Total running time of the script:** ( 1 minutes  10.711 seconds)


.. _sphx_glr_download_how_to_compile_models_from_paddle.py:

.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-example


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

      :download:`Download Python source code: from_paddle.py <from_paddle.py>`

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

      :download:`Download Jupyter notebook: from_paddle.ipynb <from_paddle.ipynb>`


.. only:: html

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

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