Prateek Shroff

loss += 0.8 * nn.L1Loss().cuda()(fps_pred[:][:2], y[:][:2]) loss += 0.2 * nn.L1Loss().cuda()(fps_pred[:][2:], y[:][2:]) With reference to above lines? I understand you are taking .8 times loss of first two examples ??...

Problem downloading the weights

1

Can someone share the weights via other media (via google drive/dropbox)? Not able to download from the Baidu site. Thanks

Receptive field calculation to get patch

1

Hi @songdejia , First of all great repo 👍 I am a little confused in this part of code. ` p_tl = (8*col, 8*row) p_br = (col*8+92, row*8+92)` I believe...

Paper level accuracy?

20

Hi @klrc , First of all great repo!! I have been trying to replicate the results of this paper. Till now, I am stuck at 68% top-1 accuracy. I saw...