Clément Pinard

Thanks for the answer ! > I do wish the built-in had copy and copytree methods. Agreed, it was part of path.py, but was stripped down when converted into PathLib,...

Yes, please. Even if you don't have time to polish it, ugly code is better than no code.

These are the values to which we normalize images coming from Flying Chairs dataset. It's a legacy from original implementation in caffe. I belive these numbers can be seen in...

Haven't checked, but It seems to me that your images are grayscale. That would mean that the operation `np.transpose(array, (2,0,1))` cannot be applied since there is not dimension 2. You...

Hi, I think you are right. When e.g. we take the point in the center of rotation, and suppose it moved outside of this center of rotation, the added optical...

Hello, for a bit of context, I will need to see some code. Are you using the code in run_inference.py to generate colored flow maps ? For synthesized views, you...

The reconstruction in this direction is not possible, you would need a "direct_warp" function instead of "inverse_warp" that uses grid_sample function. It's counter intuitive but it has to do with...

thanks ! I have issued a feature request for correlation module here some time ago : pytorch/pytorch/issues/4073 As for now, I don't have much time to spend on this personal...

You can have a look a this implementation, I'm planning on using it for a FlowNetC version and then hopefully a full FlowNet2 architecture https://github.com/ClementPinard/Pytorch-Correlation-extension

Hi Can you try to build it from the repo ? The log says that build failed but there's no other detail.