pytorch/caffe2/python/onnx
Lu Fang 796a39ba85 Automatic update of fbcode/onnx to 707064980b9825b8705b9d1c9aad34d8b022d5dd (#22981)
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/22981

Previous import was 806aa863020fa180e57f576cb032ec44ce8ddcca

Included changes:
- **[70706498](https://github.com/onnx/onnx/commit/70706498)**: TensorProto::INT8 & INT16 were missed here (#2164) <ZINEKS>
- **[8218a4ea](https://github.com/onnx/onnx/commit/8218a4ea)**: Fix LabelEncoder's shape inference (#2170) <Wei-Sheng Chin>
- **[0f1a9a1c](https://github.com/onnx/onnx/commit/0f1a9a1c)**: Fixing a unit test in Cumsum Operator (#2157) <Jeff Saremi>
- **[2c03cff0](https://github.com/onnx/onnx/commit/2c03cff0)**: [New Operator] CumSum (#2030) <Jeff Saremi>
- **[220b8300](https://github.com/onnx/onnx/commit/220b8300)**: Fix globalpool output shape (#2147) <daquexian>

Reviewed By: benoitsteiner

Differential Revision: D16341736

fbshipit-source-id: 7e7a2684d8c821991231bfd6558f9f6cb4fb05fb
2019-07-17 14:05:14 -07:00
..
bin
tests Automatic update of fbcode/onnx to 707064980b9825b8705b9d1c9aad34d8b022d5dd (#22981) 2019-07-17 14:05:14 -07:00
__init__.py
backend.py Add ONNX export support for torch.rand. (#20559) 2019-06-03 16:09:01 -07:00
backend_cpp_rep.py
backend_rep.py
error.py
frontend.py
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

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