Di Huang comments

Repositories
Issues
Comments

Results 2 comments of


                                            Di Huang

Confusion on comments 'y_pred must be cos similarity'

And for implementing the Sparse version, it should be equivalent to changing the y_true to one hot labels and then directly apply the CircleLoss class's call, is that correct?

Confusion on comments 'y_pred must be cos similarity'

Thanks for your quick reply! for 2 if K >1 I still have some questions. Basically it is a sum of exp(-gamma...s_p...). This means that you cannot take the sum...