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

How to search the best temperature and alpha #16

Open
TimeBear opened this issue Jul 17, 2020 · 5 comments
Open

How to search the best temperature and alpha #16

TimeBear opened this issue Jul 17, 2020 · 5 comments

Comments

@TimeBear
Copy link

hello ,author.
I read the paper, the parameters (temperature and alpha) are obtained by gird search.
can you release the code . I want to learn it . Thank you.

@yuanli2333
Copy link
Owner

hello ,author.
I read the paper, the parameters (temperature and alpha) are obtained by gird search.
can you release the code . I want to learn it . Thank you.

Hi
It is very simple to search hyper-parameters (grid search), just write a simple python script or bash script to run the main.py and pass the hyper-parameters to args . I will upload a simple example.

@TimeBear
Copy link
Author

Hello, author.
I am waiting for your simple example.
I really need it.
Thank you very much.

@JiyueWang
Copy link

Just change the hyperparameter manually

@yuanli2333
Copy link
Owner

Hello, author.
I am waiting for your simple example.
I really need it.
Thank you very much.

Here is a simple example for how to search hyperparameters: https://github.com/peterliht/knowledge-distillation-pytorch/blob/master/search_hyperparams.py
But make sure you are searching on a validation set that is splitted from the training set rather than the testing set.

@TimeBear
Copy link
Author

TimeBear commented Aug 5, 2020

Thankyou

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

3 participants