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

Softmax layers on output of models #37

Closed
hzavadil98 opened this issue Feb 5, 2025 · 0 comments
Closed

Softmax layers on output of models #37

hzavadil98 opened this issue Feb 5, 2025 · 0 comments
Assignees
@hzavadil98

Comments

@hzavadil98
Copy link
Contributor

Hi, in the main.py in the training loop we are currently using nn.CrossEntropyLoss(), it should take as input the raw logits (not softmaxed probabilities) and targets - https://pytorch.org/docs/stable/generated/torch.nn.CrossEntropyLoss.html if I'm not mistaken.
@hzavadil98 hzavadil98 self-assigned this Feb 5, 2025
@hzavadil98 hzavadil98 mentioned this issue Feb 5, 2025
Merged
hzavadil98 added a commit that referenced this issue Feb 5, 2025
@hzavadil98
Removed the test veryfying softmaxity of output
2d21b03 
The model should output raw logits for nn.CrossEntropyLoss() #37
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@hzavadil98 hzavadil98

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@hzavadil98