Skip to content

Conversation

@recoverer214
Copy link

Partially completed UNet report.
Train: Hold-out training loop with Cross Entropy loss and SGD.
Test: Same as Train. Dice similarity coefficient is used.
Dataset: Custom Image dataset is used.
Modules: Normal 2D Unet.

@shakes76 shakes76 added invalid This doesn't seem right Improved UNet labels Dec 23, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Improved UNet invalid This doesn't seem right

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants