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

[Question]How to use early stopping in advisor when I train a CNN model? #19

Closed
githubche opened this issue Oct 18, 2018 · 3 comments
Closed

[Question]How to use early stopping in advisor when I train a CNN model? #19

githubche opened this issue Oct 18, 2018 · 3 comments

Comments

@githubche
Copy link

No description provided.

@githubche githubche changed the title How to use early stopping in advisor when I train a CNN model? [Question]How to use early stopping in advisor when I train a CNN model? Oct 18, 2018
@tobegit3hub
Copy link
Owner

Advisor is model-agnostic and you can get the recommended parameters and train easily. We have the examples of tensorflow mnist so that you can refer to them.

Now we have some early stopping algorithm but they require more data and not efficient.

@githubche
Copy link
Author

I have seen the examples, they just output the final objective such as accuracy. I wonder how to output the training step information, and let advisor help to early stop the trial, avoiding over fitting.

@ed-word
Copy link

ed-word commented Feb 23, 2019

@githubche did you manage to find a solution?

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

No branches or pull requests
3 participants
@tobegit3hub @githubche @ed-word