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 implement the phrase 1 pretraining by contrasive learning? #614

Open
indeedzcr opened this issue Dec 20, 2024 · 0 comments
Open

how to implement the phrase 1 pretraining by contrasive learning? #614

indeedzcr opened this issue Dec 20, 2024 · 0 comments

Comments

@indeedzcr
Copy link

There are 3 stages of training in your paper, in which the first one is contrasive learning.
which token do you use to get the embedding of text in the image-text pair?
And how do you get the embedding of the image in the image-text pair?

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

1 participant