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.

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

feat: modified fit() function in cnn #98

Merged
merged 5 commits into from
Jul 22, 2024

Conversation

sameerashahh
Copy link
Collaborator

Modified the fit function to evaluate validation losses, and return both the training losses and validation losses.

@sameerashahh sameerashahh changed the title feat: modified fit() function feat: modified fit() function in cnn Jul 8, 2024
# print(loss.item())
loss.backward()
opt.step()
losses.append(loss)
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Should append loss.item()

@carynbear carynbear merged commit 61e2491 into DynaDojo:main Jul 22, 2024
1 check passed
carynbear pushed a commit that referenced this pull request Jul 22, 2024
…fit() (#98, #99, #100, #102)

feat: return loss dict in dnn.fit() (#101)
feat: return loss dict in dnn.fit() (#99)
feat: return loss dict in cnn.fit() (#98)
* modified fit function to return loss.item()
modified fit function to return losses
modified fit function to track training losses
modified fit function to return loss
added loss in fit function
lmclane04 pushed a commit to lmclane04/dynadojo that referenced this pull request Jul 26, 2024
…fit() (DynaDojo#98, DynaDojo#99, DynaDojo#100, DynaDojo#102)

feat: return loss dict in dnn.fit() (DynaDojo#101)
feat: return loss dict in dnn.fit() (DynaDojo#99)
feat: return loss dict in cnn.fit() (DynaDojo#98)
* modified fit function to return loss.item()
modified fit function to return losses
modified fit function to track training losses
modified fit function to return loss
added loss in fit function
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants