search

zhen8838 / Circle-Loss

Tensorflow2 implementation of CircleLoss. Support class-level, sparse class-level, pair-wise labels
MIT License
108 stars 40 forks source link

Why useing same y_pred for sn and sp? #8

Closed lbf4616 closed 2 years ago

lbf4616 commented 2 years ago

According to the paper and other implementations, sn and sp should be different, but you used y_pred for both of them, could you please explain why?

https://github.com/zhen8838/Circle-Loss/blob/fc4d73aea9d1b88cb104f011c9f4e425c57eb89d/circle_loss.py#L128-L129

lbf4616 commented 2 years ago

by multiply y_true and (1 - y_true) for sp and sn, thats awsome!