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

DinoV2-vs-ResnetClassification #5

Open
SameerShanbhogue opened this issue Oct 19, 2024 · 0 comments
Open

DinoV2-vs-ResnetClassification #5

SameerShanbhogue opened this issue Oct 19, 2024 · 0 comments

Comments

@SameerShanbhogue
Copy link

Hi @purnasai

In DinoV2-vs-ResnetClassification notebook. In Resnet model1 training step - optimizer used is initialized with model.parameters(), which is of DinoV2 model. Shouldn't we use a dedicated optimizer for model1 training like optimizer1 = optim.Adam(model1.parameters(), lr=0.000001). The Resnet accuracy improves to approx 90% using this...

BR

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