Negin Raoof

Hi @daquexian Caffe2 backend is not updated recently, but the existing code and tests for older opsets are maintained as part of the repo. This issue looks like a bug...

cc @gramalingam and @askhade FYI, this issue is currently blocking the use of onnx/optimizer for us in: https://github.com/pytorch/pytorch/pull/55889

@daquexian Thanks for your help. This is currently needed for ONNX in PyTorch. Do you think we can help with anything here? I can prepare a PR for split pass.

@daquexian This is high priority for us as mentioned. Could you please take a look at the PR: https://github.com/onnx/optimizer/pull/41 Thanks.

I created a duplicate to check CI failures: https://github.com/onnx/optimizer/pull/42

@daquexian Also, would you please help us with the CI workflow issue?

@ericdanz @daquexian Do you happen to have such large pytorch model that could be further optimized after ONNX export?

Hey @mmuckley, I'm trying to reproduce table 1 FID scores, and I'm unable to match FFHQ random inpainting results. I'm wondering if I'm missing some preprocessing steps. Here I'm using...

Hi @imoneoi @lightaime What is the status of this work? I am interested in re-generating the math and science datasets.