-
Notifications
You must be signed in to change notification settings - Fork 4.8k
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
Bug in diffusers basic training tutorial #7991
Labels
bug
Something isn't working
Comments
try instead using |
Thanks, this worked perfectly! |
would you like to open a pull request with an adjustment to the doc! i think @stevhliu would love that :D |
I would but I couldn't find where the repo for the doc was! |
in |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Describe the bug
In the diffusers basic training tutorial, setting the manual seed argument (
generator=torch.manual_seed(config.seed)
) in the pipeline call inside evaluate() function rewinds the dataloader shuffling, leading to overfitting due to the model see same sequence of training examples after every evaluation call. This can be tested by running the code without this argument. In the former case the training loss is lower but quality of sampled images are worse to the human eye.Reproduction
images = pipeline(
batch_size=config.eval_batch_size,
# generator=torch.manual_seed(config.seed), # Dataloader shuffling works fine once this is removed
).images
Logs
No response
System Info
diffusers
version: 0.28.0.dev0Who can help?
@stevhliu
The text was updated successfully, but these errors were encountered: