Skip to content

Update LDM trainer README to add evaluation metrics #3

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

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

Update LDM trainer README to add evaluation metrics #3

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
5 changes: 4 additions & 1 deletion LDM_TRAINER.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -167,6 +167,9 @@ The performance is greatly improved by applying classifier-free diffusion guidan


### FID
https://lightning.ai/docs/torchmetrics/stable/image/frechet_inception_distance.html
https://en.wikipedia.org/wiki/Fr%C3%A9chet_inception_distance

### Inception Score

## LDM Training Configuration
Expand Down Expand Up @@ -245,4 +248,4 @@ SD V1.4 [CompVis/stable-diffusion-v1-4](https://huggingface.co/CompVis/stable-di


## Observations from initial training runs
- a larger batch size stabilizes the gradients. Training on small batch size results in very noisy generated images.
- a larger batch size stabilizes the gradients. Training on small batch size results in very noisy generated images.