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

Automatically log hyperparameters #19

Closed
lgvaz opened this issue May 16, 2020 · 3 comments
Closed

Automatically log hyperparameters #19

lgvaz opened this issue May 16, 2020 · 3 comments
Labels
workflow Improvements for the user workflow

Comments

@lgvaz
Copy link
Collaborator

lgvaz commented May 16, 2020

This can probably be done automatically by pytorch-lightning. More info here
@lgvaz lgvaz added the workflow Improvements for the user workflow label May 16, 2020
@lgvaz
Copy link
Collaborator Author

lgvaz commented May 19, 2020

It seems lightning is removing hparams? Link

It's a good idea to wait on this and see what happens

@williamFalcon
Copy link

williamFalcon commented May 20, 2020 •
edited
Loading

we already log hyperparameters... check the hparams tab in tensorboard.

https://colab.research.google.com/drive/1LroWmzmmYfriNqHkj7NTKPkTNCX4rBRu

This PR drops the hparams keyword and instead automatically logs anything passed to init (not objects of course)

@lgvaz
Copy link
Collaborator Author

lgvaz commented May 20, 2020

This PR drops the hparams keyword and instead automatically logs anything passed to init

Awesome!! I was never a fan of hparams, this PR is making me very happy hahaha

@lgvaz lgvaz closed this as completed Jun 25, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
workflow Improvements for the user workflow
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@williamFalcon @lgvaz