WGAN gradient penalty coupled with spectral normalization，generator and discriminator loss are both nan about compare_gan HOT 4 CLOSED

Should be fine using both gp and sn for discriminator, and it may work better than just sn.

from compare_gan.

I use wrong sn code, just use google sn code,it's fine.

from compare_gan.

@chentingpc Sorry bother your again. Spectral_norm function in the code performs Spectral Normalization on a weight tensor. Authors use it on convolution. I wonder whether spectral_norm function code can apply to deconvolution. But, the shape of w in convolution is

from compare_gan.

it is fine, power iteration of both converges to the same largest singular value of A. may save some small compute if done power iteration is put on the smaller dimensions.

from compare_gan.