@draz - I posted a gist for a toy example to convert to ONNX - https://gist.github.com/sampathweb/7b6fbb35095835e9f5a12136f7494197
Please note that as specified in this post (Using a fast.ai model in production), we can’t export Fast.AI models right now to ONNX because of AdaptiveMaxPool and AdaptiveAvgPool Layers. This was an issue with PyTorch 0.3, I have not tested with PyTorch 0.4