-
Notifications
You must be signed in to change notification settings - Fork 120
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
A question about training code #6
Comments
Yes, I have the same feeling, and I had the same feeling in the paper itself, can someone clarifies? |
The labels information was used to organize data into positive and negative examples. The actual contrastive prediction was on images. No labels were used there. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi, nice code, but I'm confused about the training code of encoder. I think the training of encoder via CPC is unsupervised, however, you used some label information (made by original mnist dataset), which makes the training process supervised. Am I right?
The text was updated successfully, but these errors were encountered: