Some problems I run into while using your model
Opened this issue · 0 comments
agil27 commented
- There should be a BatchNorm2d after every convolution, right? or the model won't work.
- Why are you using VGG19 instead of your own model in the training?
- Why are you re-inventing all the transforms defined in torchvision? it's perplexing
- WIl a Adam optimizer simply work better than your complicated SGD optimizer?