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

ResNet model used for feature extraction #3

Open
mujavidb opened this issue Jan 12, 2024 · 2 comments
Open

ResNet model used for feature extraction #3

mujavidb opened this issue Jan 12, 2024 · 2 comments

Comments

@mujavidb
Copy link

I can see from the paper that a ResNet18 model was used for feature extraction. On further examination of the pkl files, they are in a particular format, particularly the features which are a 1D array.

Do you know if more details are available on the model used to extract these features? Is it available to use by others or was it custom/fine-tuned?

@kylemin
Copy link
Member

kylemin commented Jan 13, 2024

Hi,

Thank you for your interest in this work. Please refer to this link. You can use the checkpoints of ResNet-TSM models for the feature extraction.

Kyle

@charlotteburkirts
Copy link

Hi,

Just to follow up as I'm trying to train the model on a new dataset, in the pkl file you have a global_id for each detected face. Where does that come from? It is not in the original csv for the old repo SPELL neither.

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