Wenhao Hu

@BruceRayWilson Thanks for your contribution! I left a commend and `Tanh`, `Range`, `Pow` has already implemented in #21 . To avoid conflicting, could you remove these parts in this PR?

@AyanKumarBhunia Welcome for contribution. You could follow some PRs to implement a new OpCodeGenerator.

@Aivean Sorry for late reply. Some PR will resolve this issue.

@sharoseali Sorry for late reply. Just need to implement `Softplus`. Welcome for contribution.

@nmoran I think you installed by `pip install onnx-pytorch`. Try install from source by `pip install -e .` I haven't released to PyPI for a while.

And I check the unet, there are also some ops not supported yet.

@nmoran You could checkout develop branch. I've implemented ConvTranspose, Pad and Resize. BUT they are not fully tested. I can't ensure consistency between ONNX and PyTorch code. Update: FYI, I've...

@chinhuang007 We want tf_rep.run be stateless.

I guess there are some pooling ops in your onnx pb. You could take a look of them. If they satisfy one of following conditions, - `auto_pad` not be set...

@kartk Could you upload your onnx pb?