Closed devraj89 closed 6 years ago
Hi,
[1] I think the diagram of ACGAN is wrong. discriminator process is right. [2] Yes, you are right. [3] I haven't tested C_fake_loss with random labels. Probably, it is possible. However, we do not need to use random labels because we already have label information.
Thanks.
Thanks for your quick reply !
R u planning to incorporate variational autoencoders in the future ?
I'm afraid that I have no plans yet.
Hi
Thanks for your wonderful code. I read the ACGAN paper and your implementation. I have a query, in the schematic diagram you have shown that
c
is used along-withx
in the DiscriminatorD
. However, in the code, you have not used the class informationc
while training theD
andG(z)
as you have done in CGAN ?[1] Is it wrong to use the class information in the discriminator process ? [2] If it is not required then shouldn't the variable
y_fill_
removed ? It seems to be redundant in this case.Also for the C_fake_loss can we use some random labels or is it required to use those labels that have been sampled from the data_loader (like you have done) ?
Thanks in advance !