Open jinyuanwong opened 3 months ago
Hi @luisguiserrano, your video about GAN is informative and easy-to-follow! Thanks a lot! @jinyuanwong, thanks for pointing this formula issue. I noticed it too and found it to be more than a redundant term.
Actually, this is supposed to be W_i instead, coming from the partial derivative ∂D/∂G. Below should be the correct formula from my understanding
This corrected math formula is reflected truthfully in the codes, which is correct. factor = -(1-dgz) discriminator_weights gz *(1-gz)
@luisguiserrano, if you approve it, perhaps you can modify the LaTeX for this image? Thanks again for the great video!
G(z) is redundant in the formula, in which I added a text to point out.