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
Spandan Tiwari 9ef8eb4cbc Fix case for activations attribute in nn.RNN ONNX export. (#19368) 
Summary:
This PR addresses the https://github.com/pytorch/pytorch/issues/19366 issue.
Pull Request resolved: https://github.com/pytorch/pytorch/pull/19368

Reviewed By: zrphercule

Differential Revision: D15043949

Pulled By: houseroad

fbshipit-source-id: 9b90410307d31bc5f2fd14aa0cdd33b22572ed7c
2019-04-25 16:31:25 -07:00
..
bin
tests Automatic update of fbcode/onnx to 27d4b617e7097cda7d0d4c45ff2b09d248f33179 (#19718) 2019-04-25 10:54:15 -07:00
__init__.py
backend.py Fix case for activations attribute in nn.RNN ONNX export. (#19368) 2019-04-25 16:31:25 -07:00
backend_cpp_rep.py
backend_rep.py
error.py
frontend.py Fix caffe2 => onnx exporter for ConvTranspose (#14143) 2018-11-26 15:51:42 -08:00
helper.py Add debug logic to c2_ref_test and its helpers (#19359) 2019-04-22 12:08:55 -07:00
onnxifi.py Add back option to not adjust output batch size (#19442) 2019-04-22 12:29:24 -07:00
ONNXOpCoverage.md
README.md
test_onnxifi.py Skip tests if C2/ONNX models cannot be read (#18494) 2019-03-27 11:21:44 -07:00
workspace.py

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