About output
hello,thx for your source code in the output image,what's the mean of G(z_opt).png and fake_sample.png which one is the output from the net?
the outputs are automatically saved in the output folder
hello,thx for your source code in the output image,what's the mean of G(z_opt).png and fake_sample.png which one is the output from the net?
If I'm correct, fake_sample is from "noise" which is used for the loss for discriminator, and G(z_opt) is from "z_opt" which is used for the reconstruction loss. In addition, z_opt is a kind of optional noise and we can walk in noise-space by changing z_opt. The animation function is enabled by changing z_opt.