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

if I want to use customed dataset, which config file can i refer to? #4

Closed
lynshwoo2022 opened this issue Feb 1, 2023 · 2 comments
Closed

Comments

@lynshwoo2022
Copy link

hi there,
thanks for your great work!
I'm a little confused about those config files for different datasets, especially the margin parameter in it. If I want to train this model all from start, should I set it to True? what about other parameters like learning rate?

@SanyeungWang
Copy link
Owner

For a new dataset, you also need to create a new config file to control the parameters more conveniently, otherwise you have to modify it in option.py every time you train or test.

Regardless of whether the value of margin is True or False, this will directly affect line 343 of model/resnet.py. Setting it to True means that m_p of formula 4 in the paper is not 0.

You should of course set this to True if you want to train the model from the start, otherwise it will become a vanilla method.

For other parameters, you can try to fine-tune them according to the dataset you are using.

If you have further questions, please open an issue.

@lynshwoo2022
Copy link
Author

thanks

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

2 participants