Amin Ghiasi
Amin Ghiasi
Could you solve it? I have the same problem.
I'm experiencing the same issue.
I figured out a way to prevent this. If you look at `pyramidnet.py` lines 106-120: ```python if residual_channel != shortcut_channel: padding = torch.autograd.Variable( torch.cuda.FloatTensor(batch_size, residual_channel - shortcut_channel, featuremap_size[0], featuremap_size[1]).fill_(0)) out...
@seuretm All points you mentioned are true. However, even if you don't use the test data during training, and only use it once (after the training is done), you get...
Probably not! It also depends on the number of classes. So if you have 2000 datapoints for a binary (2 class) classification, it means 1000 points per each, so it...
@HeekangPark First version of pytorch did not have the learning rate schedulers (or maybe they had but they were not as popular back then). So many of the code bases...
@adam-erickson Hey did you figure this out? Update: I think I figure this out. Probably you're opening the `index.html` on your own machine. But if you had a server the...
I'm having the same issue. Any suggestions?