ONNX export failed on ATEn operator upsample bilinear2d

1

I am trying to export this segmentation model to ONNX. On export I get the error:

/home/diego/.pyenv/versions/gsoc/lib/python3.6/site-packages/torch/onnx/utils.py:662: UserWarning: ONNX export failed on ATen operator upsample_bilinear2d because torch.onnx.symbolic_opset9.upsample_bilinear2d does not exist
  .format(op_name, opset_version, op_name))
*** KeyError: 'upsample_bilinear2d'

I found this issue and this fix saying the problem was fixed on master. However I am working on PyTorch Nightly and I am still getting this error. In this model it comes its various nn.function.interpolate operations, same as in the example referenced in the issue.

I am also facing this problem when exporting the ‘fcn_resnet101’ from torchvision, since it has these operations as well.

2

Same issue here, have you found any solution?

3

Hey, I think someone found a workaround, but I havent tried it yet. Check out the issue I referenced on the first post.

4

Thank you!. I managed to fix it with the solution in the issue.

5

@Vincent_Cheng I’m currently having this issue, did you use the solution in this link: