pytorch/caffe2/python/onnx
Nikita Shulga eae84f0d5d Fix ONNX forward compatibility (#59327)
Summary:
Fixes `onnx.utils.polish_model` not found exception when executed using onnx-1.9

Pull Request resolved: https://github.com/pytorch/pytorch/pull/59327

Reviewed By: H-Huang

Differential Revision: D28840563

Pulled By: malfet

fbshipit-source-id: 403a29a88e7dee8b3414602b9fe2b31baf737dce
2021-06-02 12:39:56 -07:00
..
bin
tests
__init__.py
backend.py Fix ONNX forward compatibility (#59327) 2021-06-02 12:39:56 -07:00
backend_cpp_rep.py
backend_rep.py
error.py
frontend.py
helper.py
onnxifi.py
ONNXOpCoverage.md
README.md
test_onnxifi.py
workspace.py

Caffe2 implementation of Open Neural Network Exchange (ONNX)

Usage

Installation

onnx-caffe2 is installed as a part of Caffe2. Please follow the instructions to install Caffe2.

Folder Structure

  • ./: the main folder that all code lies under
    • frontend.py: translate from caffe2 model to onnx model
    • backend.py: execution engine that runs onnx on caffe2
  • tests/: test files

Testing

onnx-caffe2 uses pytest as test driver. In order to run tests, first you need to install pytest:

pip install pytest-cov

After installing pytest, do

pytest

to run tests.

Testing coverage issues/status: https://github.com/caffe2/caffe2/blob/master/caffe2/python/onnx/ONNXOpCoverage.md

Development

During development it's convenient to install caffe2 in development mode:

cd /path/to/caffe2
pip install -e caffe2/

License

MIT License