saymrwulf/pytorch
1
0
Fork 0
mirror of https://github.com/saymrwulf/pytorch.git synced 2026-05-15 21:00:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
pytorch/caffe2/python/onnx
History
Lu Fang cda2f02f89 Skip the test average pool same mode tests (#2324)
2018-03-20 00:13:31 -07:00
..
bin Onnx caffe2 backend (#2039) 2018-03-12 15:18:05 -07:00
tests Skip the test average pool same mode tests (#2324) 2018-03-20 00:13:31 -07:00
__init__.py Move onnx-caffe2 inside caffe2 (#1921) 2018-02-20 13:56:52 -08:00
backend.py Update onnx frontend to emit new onnx Reshape (with shape as input) (#2287) 2018-03-16 16:32:35 -07:00
backend_cpp_rep.py Expose more APIs for onnx cpp backend (#2317) 2018-03-19 22:46:26 -07:00
backend_rep.py Move onnx-caffe2 inside caffe2 (#1921) 2018-02-20 13:56:52 -08:00
error.py Move onnx-caffe2 inside caffe2 (#1921) 2018-02-20 13:56:52 -08:00
frontend.py Handle the legacy padding in global pooling case (#2292) 2018-03-18 21:28:15 -07:00
helper.py Fix useless opset_import in onnx (#2243) 2018-03-14 10:17:32 -07:00
ONNXOpCoverage.md Add README and ONNXOpCoverage doc back (#2102) 2018-03-01 17:05:25 -08:00
README.md Add README and ONNXOpCoverage doc back (#2102) 2018-03-01 17:05:25 -08:00
workspace.py Move onnx-caffe2 inside caffe2 (#1921) 2018-02-20 13:56:52 -08:00

README.md

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