mone in generator about improved-wgan-pytorch

[jalola]

Hi,

The last gen_cost = -gen_cost does not affect the gradients or the optimizer_g.step() because after backward(), gradients are calculated. It only affects the graph when we draw the gen_cost (It just flips vertically when you're putting - or not putting -)

What matters here is:
gen_cost.backward(mone) and
disc_cost = disc_fake - disc_real + gradient_penalty
disc_cost.backward()

After optimizer.step(), G tries to maximize gen_cost and D tries to minimize disc_fake(kind of gen_cost). So there is a fight between G and D.

[udion]

yes thank you.
Tell me though are these 2 equivalent:

• gen_cost = -gen_cost and then gen_cost.backward()
• no need to invert gen_cost before calling backward and instead pass mone in backward (i.e what you did)

[jalola]

thanks too,

That's true

gen_cost = -gen_cost
gen_cost.backward()

would result the same.

[Nikasa1889]

The issue is solved.