Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Lab3-2] Question about loss function of discriminator #7

Open
doom8199 opened this issue Nov 27, 2017 · 2 comments
Open

[Lab3-2] Question about loss function of discriminator #7

doom8199 opened this issue Nov 27, 2017 · 2 comments

Comments

@doom8199
Copy link

Dear TA:
I tried to modify sample code below, but finally got the garbage results QQ ...
Could you give me some hints why this change cannot work ?

errD_real = criterion(...)
#errD_real.backward()

errD_fake = criterion(...)
#errD_fake.backward()

errD = errD_real + errD_fake
errD.backward()

[Note] Training dataloader has been followed by Lab3_2's requirement.

@hui-po-wang
Copy link
Contributor

Hi @doom8199,

At first glance, they should be equal if you didn't modify anything else.
It's hard to debug without any details.

Thanks

@doom8199
Copy link
Author

Dear TA:
Details are just code changes I mentioned before. I will try to run more than one time to see if it can be reproducible or not.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants