luisguiserrano / gans Goto Github PK

Hi @luisguiserrano , thanks a lot about this friendly intro to GAN, it is really helpful. But I have a question about the code in the notebook where you calculate the error for discriminator. Use calculate the error using <errors_discriminator.append(sum(D.error_from_image(face) + D.error_from_noise(z)))>. When you calculate the error from noise you pass which is the random number, shouldn't you pass the noise generated by the generator i.e <G.forward(z)>. So the error for discriminator is <errors_discriminator.append(D.error_from_image(face) + D.error_from_noise(G.forward(z)))>??

G(z) is redundant in the formula, in which I added a text to point out.

Hello @luisguiserrano! A very friendly introduction to GANs indeed :) I'm utilizing your code to carry out a class project to visualize a pandas df (50 x 300). So far, I've made alterations as shown to generate my dataframe:

def view_samples(samples, m, n): fig, axes = plt.subplots(figsize=(10, 10), nrows=m, ncols=n, sharey=True, sharex=True) for ax, img in zip(axes.flatten(), samples): ax.xaxis.set_visible(False) ax.yaxis.set_visible(False) im = ax.imshow(1-img.reshape((50,300)), cmap='Greys_r') return fig, axes

Is the discriminator not training? Not sure if my error is zero or nothing is happening at all? Would you happen to know where the issue lies? Thank you!