Clément Pinard

1. Not sure, never tried it with windows. Theoretically yes, since I only use official pytorch extension tools. 2. You can build this repo without gpu by using `setup_cpu.py` instead...

Seems like your torch version is out of date, erorr are apparently bad use of std::tuple template (which is most probably a problem related to inner torch) and you only...

For the cluster issue, I never work on a cluster, so I'm not sure. It seems that you d'ont have the rights to read the folder /usr/local/cuda. Your cuda directory...

Yes You only need it for FlowNetC though

Sorry, I though I had linked it in the README but it does not seem to be the case https://github.com/ClementPinard/Pytorch-Correlation-extension Norally you should be able to install it directly with...

Hi, what is your question exactly ?

You can't, it's very hard. This is actually the point of the Flying Chair dataset : real optical flow requires heavy sensors (like Lidar) and algorithms, so we might as...

Ah at first I thought you wanted to generate ground truth optical from video, which is infeasible (as also stated by the paper you cite). If you want to generate...

Hello, for anyone visiting this issue, the problem is caused here : https://github.com/pytorch/pytorch/blob/master/torch/utils/cpp_extension.py#L1694 basically, the `arch_list` is supposed to be constructed with discovered architectures with `torch.cuda.get_device_capability(i)` The thing is, when...

@goldsborough @soumith any thoughts on this ? Should this solution be enforced in good practice ? Encountered the same issue with a user on my own module, so it's apparently...