-
Notifications
You must be signed in to change notification settings - Fork 35
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
recall calculation #14
Comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
https://github.com/PkuRainBow/Hard-Aware-Deeply-Cascaded-Embedding_release/blob/e2f5462aab0ed1c9d6a85503bf7d42eac632d5b1/src_code/test_deep_fashion.py#L29
Hi, I was wondering how you calculated the recall. In fact, in your code, if you query K images and once you get one correct, and this is a 100% recall in your code. But as far as I know, recall@K means if you have N images in the gallery corresponding to the anchor and you find M images correct in these K images, the recall@K=M/N and precision=N/K. But in your code, once M is not zero, your recall got to be 1. Can you explain this for me? I'm really confused. Thank you a lot.
The text was updated successfully, but these errors were encountered: