masahi commented on pull request #6449: URL: https://github.com/apache/incubator-tvm/pull/6449#issuecomment-693096782
> @masahi Yeah. Those ops look like coming from scripted model. I believe for pt 1.6 if we trace the model there are 2 or 3 ops missing. To be clear, that list op is coming from **tracing** mask rcnn model, since mask rcnn is partly scripted, even if we `torch.jit.trace` on it, we still get partly scripted TorchScript IR. See the link to torchvision code I added above. For faster rcnn, which is **not** partly scripted and thus can be traced completely, I get following missing ops with PyTorch 1.6 ``` NotImplementedError: The following operators are not implemented: ['aten::tensor', 'aten::empty', 'aten::numel'] ``` ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected]
