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.

Sign up for GitHub

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

Jump to bottom

added simple trick #50

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

added simple trick #50

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,6 +80,7 @@ In practice, works well:
## 10: Track failures early

- D loss goes to 0: failure mode
- Simple sanity check : Train G without updating weights for D (don't do G_optimizer.step()) and make sure loss goes down and vice versa.
- check norms of gradients: if they are over 100 things are screwing up
- when things are working, D loss has low variance and goes down over time vs having huge variance and spiking
- if loss of generator steadily decreases, then it's fooling D with garbage (says martin)
Expand Down