lsgan
lsgan copied to clipboard
guojunq
This is the project for LS-GAN (Loss-Sensitive GAN)
The derivative of sigmoid is very small when the scores are away from zero, which is why sigmoid activation has all but abandoned in deep learning. In the original GAN,...
Hi, Prof. Qi, I am wondering why there is a ReLU layer at the top of discriminator (shown at line 120 in lsgan.lua)? With this ReLU layer, I found the...
@a-System-Product-Name ~/dp/lsgan-master $ dataset=mnist th clsgan.lua { ntrain : inf beta1 : 0.5 nThreads : 4 niter : 25 batchSize : 64 gamma : 1 ndf : 64 fineSize :...
