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

default value of n_signal, re: RandomCrop and 16GB GPUs #262

Open
victor-shepardson opened this issue Oct 12, 2023 · 0 comments
Open

default value of n_signal, re: RandomCrop and 16GB GPUs #262

victor-shepardson opened this issue Oct 12, 2023 · 0 comments

Comments

@victor-shepardson
Copy link

Suggestion: change the default value of n_signal in train.py to 122880.

If I'm not mistaken, the current defaults for preprocess.py (train.py) set num_signal (n_signal) to the same value, 131072, which means the random cropping data augmentation is effectively turned off by default. I'm also seeing occasional OOM when training v3 models on a 16 GB GPU. To address both, I made n_signal in train.py slightly shorter (122880).

Posting this as an issue since it might be more user-friendly to adopt as the default.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@victor-shepardson