Angular-Penalty-Softmax-Losses-Pytorch icon indicating copy to clipboard operation
Angular-Penalty-Softmax-Losses-Pytorch copied to clipboard

Published 20 hours ago • verified publisher icon cvqluu

questions about SphereFace

Open LeeBC2298 opened this issue 4 years ago • 0 comments

I think the implementation of SphereFace is wrong, because in the original paper of SphereFace:

  1. The hyperparameter 'm', which means the angular restrain, should be no less than 3 in multiclassifition task, but I could not get correct visualizing result when set m bigger than 2.
  2. cos(m*theta) was replaced by another function called 'pht(theta)'.
  3. the feature vector x wasn't normalized in SphereFace, so there is not hyperparameter 's' in SphereFace.

LeeBC2298 avatar Jun 07 '20 18:06 LeeBC2298