houseroad / onnx-caffe2

Caffe2 implementation of Open Neural Network Exchange (ONNX)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

onnx-caffe2

Build Status

Caffe2 implementation of Open Neural Network Exchange (ONNX).

Repository location may change.

Installation

pip install onnx-caffe2

Usage

Folder Structure

  • 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

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

Development

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

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

License

MIT License

About

Caffe2 implementation of Open Neural Network Exchange (ONNX)

License:Other


Languages

Language:Python 56.3%Language:C++ 41.0%Language:Shell 2.2%Language:CMake 0.6%