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

    Click :ref:`here <sphx_glr_download_how_to_compile_models_from_coreml.py>` to download the full example code
.. rst-class:: sphx-glr-example-title

.. _sphx_glr_how_to_compile_models_from_coreml.py:


Compile CoreML Models
=====================
**Author**: `Joshua Z. Zhang <https://zhreshold.github.io/>`_,             `Kazutaka Morita <https://github.com/kazum>`_,             `Zhao Wu <https://github.com/FrozenGene>`_

This article is an introductory tutorial to deploy CoreML models with Relay.

For us to begin with, coremltools module is required to be installed.

A quick solution is to install via pip

.. code-block:: bash

    pip install -U coremltools --user

or please refer to official site
https://github.com/apple/coremltools


.. code-block:: default

    import tvm
    from tvm import te
    import tvm.relay as relay
    from tvm.contrib.download import download_testdata
    import coremltools as cm
    import numpy as np
    from PIL import Image







Load pretrained CoreML model
----------------------------
We will download and load a pretrained mobilenet classification network
provided by apple in this example


.. code-block:: default

    model_url = "https://docs-assets.developer.apple.com/coreml/models/MobileNet.mlmodel"
    model_file = "mobilenet.mlmodel"
    model_path = download_testdata(model_url, model_file, module="coreml")
    # Now you have mobilenet.mlmodel on disk
    mlmodel = cm.models.MLModel(model_path)







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


.. code-block:: default

    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))
    # Mobilenet.mlmodel's input is BGR format
    img_bgr = np.array(img)[:, :, ::-1]
    x = np.transpose(img_bgr, (2, 0, 1))[np.newaxis, :]







Compile the model on Relay
---------------------------
We should be familiar with the process right now.


.. code-block:: default

    target = "llvm"
    shape_dict = {"image": x.shape}

    # Parse CoreML model and convert into Relay computation graph
    mod, params = relay.frontend.from_coreml(mlmodel, shape_dict)

    with tvm.transform.PassContext(opt_level=3):
        lib = relay.build(mod, target, params=params)







Execute on TVM
-------------------
The process is no different from other example


.. code-block:: default

    from tvm.contrib import graph_executor

    dev = tvm.cpu(0)
    dtype = "float32"
    m = graph_executor.GraphModule(lib["default"](dev))
    # set inputs
    m.set_input("image", tvm.nd.array(x.astype(dtype)))
    # execute
    m.run()
    # get outputs
    tvm_output = m.get_output(0)
    top1 = np.argmax(tvm_output.numpy()[0])







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


.. 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 = eval(f.read())
    # You should see the following result: Top-1 id 282 class name tiger cat
    print("Top-1 id", top1, "class name", synset[top1])




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

 Out:

 .. code-block:: none

    Top-1 id 282 class name tiger cat




.. _sphx_glr_download_how_to_compile_models_from_coreml.py:


.. only :: html

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



  .. container:: sphx-glr-download

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



  .. container:: sphx-glr-download

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


.. only:: html

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

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