Wei Ouyang

Results 197 comments of Wei Ouyang

FYI: Since this PR is suspended, I had to publish the patched version for windows on pypi: https://pypi.org/project/jupyter-server-proxy-windows/ . It's a big urgly, but if you want a quick solution...

Hi, the gif was made by @felixlaumon (from https://github.com/felixlaumon/deform-conv), for more details, please consult him. With libraries such as imageio, one can easily generates gif image from a list of...

You can read this : https://medium.com/@phelixlau/notes-on-deformable-convolutional-networks-baaabbc11cf3 the read dots are sampling location, you can just plot the `offset` generated here: https://github.com/oeway/pytorch-deform-conv/blob/master/torch_deform_conv/layers.py#L39 plot it and make a gif when deforming the...

@kirkzZ Sorry that I haven't worked on this repo for a while, and some users mentioned there is some issue with the implementation here. So maybe you can try others'...

That's a way to match the indexes for `th_flatten(input)`, for a better understanding, I would suggest to clone the code, and change it by adding print statement to check each...

hey @cdowen and @Seashell_9 , thanks for looking into this, I am not working on this at the moment. If you find a potential bug, could you please try to...

I am afraid that there is no simple solution, you will need to make modification on each the deform_cov, try to search `input_size`, and change accordingly to width and height....

@bkvie thanks for the reminder, I will do that soon.

@rouniuyizu @bkvie I have just manually merged PR #3 , please try and report unexpected issues, notice that in the PR the coordinates are now not clipped, that may cause...

Hi, thanks for looking into this. This was a direct port from tensorflow to pytorch before the author of deformable conv release their code, and I am aware that there...