Stefano Savian

@Blcony by any chance did you manage to implement this (#7) solution? Could you post here the code? I think it should be added between line 549 and 553 of...

Hi @guuusss , I am also inspecting data augmentation of PWC-Net. Could you provide the paper reference? I think that your point 3 might be mistaken. As far as I...

Thanks, you are right, they all use the same augmentation. But PWC-Net ROB, when fine tuning on sintel also performs horizontal frame flipping, It is written and I also have...

Same problem here, I am using tensorflow 1.10.0 installed thorugh conda. this might be useful, resnet 101 has the same problem, some people solved by deleting the folder and saving...

Hi all, I also run into the same problem and at the end I went for this version of pwc (PWC-net_ROB) which uses cupy and weighted ported from caffe https://github.com/sniklaus/pytorch-pwc...

I am also forced to use CUDA 10 and I gave up for another implementation (only tried for inference) https://github.com/sniklaus/pytorch-pwc. I would be happy if someone could help

Dear @NagabhushanSN95, thanks for pointing it out, It helped me to let the network run on Sintel. My guess is that the input shape should be diadic (divisible by 2)...

yes sorry you are right, it should not be just two. To be honest I don't know the exact minimum divider. Anyway the number makes sense for Sintel. the original...

I am not the author of this paper, but in my view it should be ok. However if you use the pretrained model you should be careful...If I am not...

Dear @avirambh I have a similar problem. I have adapted the testing script from the IRR repository , however I get nonsense outputs using your checkpoints and model. Is there...