pytorch/caffe2/python/onnx
Kazuaki Ishizaki daff5d3556 Fix typos under caffe2 directory (#87840)
This PR fixes typos in `.md` files under caffe2 directory

Pull Request resolved: https://github.com/pytorch/pytorch/pull/87840
Approved by: https://github.com/kit1980
2022-10-28 04:53:36 +00:00
..
bin Drop unused imports from caffe2/python (#49980) 2021-01-05 13:17:46 -08:00
tests [ONNX] Update onnx submodule to 1.12 (#79585) 2022-06-23 18:09:07 +00:00
__init__.py remediation of S205607 2020-07-17 17:19:47 -07:00
backend_cpp_rep.py Lint trailing newlines (#54737) 2021-03-30 13:09:52 -07:00
backend_rep.py Remove __future__ imports for legacy Python2 supports (#45033) 2020-09-23 17:57:02 -07:00
backend.py Fix use of ONNX optimizer by Caffe2 backend 2022-04-14 21:48:48 +00:00
error.py Remove __future__ imports for legacy Python2 supports (#45033) 2020-09-23 17:57:02 -07:00
frontend.py Remove redundant code for unsupported Python versions (#49486) 2021-01-06 12:45:46 -08:00
helper.py Drop unused imports from caffe2/python (#49980) 2021-01-05 13:17:46 -08:00
onnxifi.py Add onnxifi interface for set/get options (#52388) 2021-02-18 20:12:34 -08:00
ONNXOpCoverage.md Fix typos under caffe2 directory (#87840) 2022-10-28 04:53:36 +00:00
README.md Lint trailing newlines (#54737) 2021-03-30 13:09:52 -07:00
test_onnxifi.py Lint trailing newlines (#54737) 2021-03-30 13:09:52 -07:00
workspace.py Remove __future__ imports for legacy Python2 supports (#45033) 2020-09-23 17:57:02 -07:00

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