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.

Sign up for GitHub

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

Jump to bottom

Numbers of positives Nyi #19

Open
lclkent opened this issue Jul 8, 2020 · 1 comment
Open

Numbers of positives Nyi #19

lclkent opened this issue Jul 8, 2020 · 1 comment

Comments

@lclkent
Copy link

lclkent commented Jul 8, 2020

Hi thanks for the great work! It seems that the numbers of positives described in the paper is a critical parameters, but the train_loader code isn't specified of this parameter Nyi. Does that means it is ok to randomly sample images of different class?
@lclkent
Copy link
Author

lclkent commented Jul 13, 2020

I am trying this approach on my own dataset of a binary classification task, the data is unbalanced. My loss for the pretraining stage is always around 10.00, I wonder it's because of the unbalanced data and may relate to Nyi mentioned in the paper. Can someone kindly help me out? Appreciated.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@lclkent