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

Validation on the fly and saving models according to validation accuracy #95

Closed
ashwinvaswani opened this issue Sep 8, 2020 · 3 comments · Fixed by #112
Closed

Validation on the fly and saving models according to validation accuracy #95

ashwinvaswani opened this issue Sep 8, 2020 · 3 comments · Fixed by #112

Comments

@ashwinvaswani
Copy link
Member

Currently, validation is only done after training and it's good to have validation on the fly as it gives a better understanding of over / underfitting of the model. Moreover, models are saved on the basis of training metrics and not validation metrics currently.
@Het-Shah
Copy link
Member

Het-Shah commented Sep 8, 2020

Yea i think we should be taking in a val loader as well in the __init__. Great, we surely missed this small error!

@avishreekh
Copy link
Collaborator

Can I take this up? Thanks!

@Het-Shah
Copy link
Member

Yea go ahead :)

@avishreekh avishreekh mentioned this issue May 30, 2021
Merged
@Het-Shah Het-Shah linked a pull request May 30, 2021 that will close this issue
Add validation on the fly #112
Merged
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

Successfully merging a pull request may close this issue.

Add validation on the fly avishreekh/KD_Lib
3 participants
@Het-Shah @avishreekh @ashwinvaswani