Shashank Shekhar

@mabdullahrafique Change the output of the discriminator to this : `return F.avg_pool2d(x, x.size()[2:]).view(x.size()[0]) `

Thanks for the reminder! I am a little busy with work and travel right now but will make a point to update with 2022 schools over the winter break.

Hi @datonefaridze I will be more than happy to add any schools you have found. Please send a PR (or share the links) of the schools you wanted to see...

Thanks a ton @dreamflasher! I will add these today :-)

Thank you for the contribution! Could you please make sure that the School is placed in its correct position chronologically (in reverse order by date of the school)?

Thanks for the prompt response. In my dataset the labels I have are in the form of images. What would be the fastest way to encode them into HxW with...

I also used pytorch 0.4.0 I will check this issue after the ICCV deadline and get back to you

I am still training and update with results once I have them. Please leave this issue open in the meanwhile for others' reference. Thanks a lot

Hi all, I haven't been able to reproduce the results yet. Mostly because 2000 epochs take extremely long for the SYSU dataset. I will run it once after ICCV deadline...

If I remember correctly the annotations were saved to .npy files for faster processing as reading individual text files repeatedly was much slower. The .npy files are not provided in...