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

batch size of 32 do not generate useful segmentation models (64 does) #105

Open
dcianferoni opened this issue Jul 21, 2023 · 0 comments
Open

batch size of 32 do not generate useful segmentation models (64 does) #105

dcianferoni opened this issue Jul 21, 2023 · 0 comments

Comments

@dcianferoni
Copy link

For some reason when I train using batch size of 32 the accuracy is below 0.5 and visualizing prediction leds to all points predicted with same class. Increasing to 64 leads to good performances. Any explanation?
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
@dcianferoni