https://github.com/onnx/onnx-caffe2

Caffe2 implementation of Open Neural Network Exchange (ONNX)
https://github.com/onnx/onnx-caffe2

caffe2 deep-learning deep-neural-networks

Last synced: 29 days ago
JSON representation

Caffe2 implementation of Open Neural Network Exchange (ONNX)

• Host: GitHub
• URL: https://github.com/onnx/onnx-caffe2
• Owner: onnx
• License: other
• Archived: true
• Created: 2017-09-07T05:06:02.000Z (over 7 years ago)
• Default Branch: master
• Last Pushed: 2018-03-02T07:53:14.000Z (almost 7 years ago)
• Last Synced: 2024-10-30T02:03:50.619Z (about 2 months ago)
• Topics: caffe2, deep-learning, deep-neural-networks
• Language: Python
• Size: 376 KB
• Stars: 165
• Watchers: 21
• Forks: 66
• Open Issues: 37
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
NOTICE: THIS REPO IS DEPRECATED! onnx-caffe2 has been merge into [Caffe2](https://github.com/caffe2/caffe2/tree/master/caffe2/python/onnx).

=======

onnx-caffe2

========

| Travis | Jenkins |

|--------|---------|

| [![Build Status](https://travis-ci.org/onnx/onnx-caffe2.svg?branch=master)](https://travis-ci.org/onnx/onnx-caffe2) | [![Build Status](https://ci.pytorch.org/jenkins/buildStatus/icon?job=onnx-caffe2-master)](https://ci.pytorch.org/jenkins/job/onnx-caffe2-master/) |

Caffe2 implementation of Open Neural Network Exchange (ONNX).

Repository location may change.

# Installation

```

pip install onnx-caffe2

```

# Usage

* [ONNX to Caffe2](https://github.com/onnx/tutorials/blob/master/tutorials/OnnxCaffe2Import.ipynb)

* [Caffe2 to ONNX](https://github.com/onnx/tutorials/blob/master/tutorials/Caffe2OnnxExport.ipynb)

* [other end-to-end tutorials](https://github.com/onnx/tutorials)

# 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](https://docs.pytest.org) 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 --recursive

pip install -e onnx-caffe2/

```

# License

[MIT License](LICENSE)