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

Hyperparamter Tuning Automated #3034

Open
Testbild opened this issue May 16, 2024 · 0 comments
Open

Hyperparamter Tuning Automated #3034

Testbild opened this issue May 16, 2024 · 0 comments

Comments

@Testbild
Copy link

Hi everyone,

is there a way to automatically tune the hyperparameters, like you can do with the keras tuner random search? I tried to implement it, but I could not succeed, as this wants the build function handed over, but the model in matterport is built directly when it initializes and I have not found anything in the issues here so far.

I would basically like to say:
Please take these 5 or 10 parameters and try them out and give me the results. The max/min values should be xy.

I can do all this manually, but that does not seem very effective. Thanks for your help.

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

No branches or pull requests

1 participant