sagan-pytorch

sagan-pytorch copied to clipboard

Reloading model causes issue

5

I save model during training with G: 1.42529; D: 1.17999 After loading discriminator and generator I get G: -26.45726; D: 0.89195 It looks like discriminator behaves differently. Removing 'd_optimizer.step' gives...

AlexanderMath

I used this network to train the mini-imagenet dataset, and the effect was very poor.

2

I used the mini-imagenet data set, but the result was very poor. How can I improve it?

LittleStars666

Why so many ConvBlock(512, 512 ???

2

self.conv = nn.ModuleList([ConvBlock(512, 512, n_class=n_class), ConvBlock(512, 512, n_class=n_class), ConvBlock(512, 512, n_class=n_class, self_attention=True), ConvBlock(512, 256, n_class=n_class), ConvBlock(256, 128, n_class=n_class)])

c1a1o1