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

about memory size and train #76

Closed
Hephaestusxg opened this issue Apr 30, 2024 · 1 comment
Closed

about memory size and train #76

Hephaestusxg opened this issue Apr 30, 2024 · 1 comment

Comments

@Hephaestusxg
Copy link

In the init cls phase, is the incremental learning method used? If I want the initial class to be 7, then in the 0-6 phase of training, is the incremental learning method used, and can I save the weights? Secondly, regarding the memory size, how much should I set for small datasets like cifar10?

@zhoudw-zdw
Copy link
Collaborator

Of course, you can save the model weights. You might want to read the Pytorch tutorial on how to save and load models.

The memory size should be adjusted for your own datasets, and we cannot give specific suggestions.

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