ONNX tutorials
| Framework / tool | Installation | Exporting to ONNX (frontend) | Importing ONNX models (backend) |
|---|---|---|---|
| Caffe2 | part of caffe2 package | Exporting | Importing |
| PyTorch | part of pytorch package | Exporting, Extending support | coming soon |
| Cognitive Toolkit (CNTK) | built-in | Exporting | Importing |
| Apache MXNet | part of mxnet package docs github | coming soon | Importing [experimental] |
| Chainer | chainer/onnx-chainer | Exporting | coming soon |
| TensorFlow | onnx/onnx-tensorflow | Exporting | Importing [experimental] |
| Apple CoreML | onnx/onnx-coreml and onnx/onnxmltools | Exporting | Importing |
| SciKit-Learn | onnx/onnxmltools | Exporting | n/a |
- Docker image for Caffe2/PyTorch tutorials
- Converting SuperResolution model from PyTorch to Caffe2 and deploying on mobile device
- Transferring SqueezeNet from PyTorch to Caffe2 and to Android app
- Serving PyTorch Models on AWS Lambda with Caffe2 & ONNX
- Serving ONNX models with MXNet Model Server
- Converting Style Transfer model from PyTorch to CoreML and deploying to an iPhone
- Verifying correctness and comparing performance
- Visualizing an ONNX model (useful for debugging)
- Example of operating on ONNX protobuf
We welcome improvements to the convertor tools and contributions of new ONNX bindings. Check out contributor guide to get started.
Use ONNX for something cool? Send the tutorial to this repo by submitting a PR.