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

Make discriminator digit-aware #18

Merged
merged 5 commits into from
Jul 19, 2023
Merged

Make discriminator digit-aware #18

merged 5 commits into from
Jul 19, 2023

Conversation

johncf
Copy link
Owner

@johncf johncf commented Jul 19, 2023

Fixes #17

Implements a solution very similar to the one proposed in the issue:

  • "Fake" input: the one-hot representation of the label + the Encoder's style encoding output.
  • "Real" input: the one-hot representation of the label + a prior-distribution random-sampled style vector.
  • The first part of fake and real inputs are the same for each mini-batch.

Now, everything is great!

aae2-vis
aae2-gen

@johncf johncf marked this pull request as ready for review July 19, 2023 19:50
@johncf johncf enabled auto-merge July 19, 2023 19:50
@johncf johncf merged commit 7d1c561 into master Jul 19, 2023
@johncf johncf deleted the digit-aware-dis branch July 19, 2023 19:53
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

Successfully merging this pull request may close these issues.

Make adversarial training digit-aware
1 participant