Travis	Jenkins

Caffe2 implementation of Open Neural Network Exchange (ONNX).

Repository location may change.

pip install onnx-caffe2

• ONNX to Caffe2
• Caffe2 to ONNX
• other end-to-end tutorials

• onnx_caffe2/: 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

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/onnx/onnx-caffe2/blob/master/tests/ONNXOpCoverage.md

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

git clone  https://github.com/onnx/onnx-caffe2.git --recursive
pip install -e onnx-caffe2/

MIT License