CoinCheung / pytorch-loss

label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

about smooth label

mk123qwe opened this issue · comments

if i choose smooth label ,what loss function do i choose?
in ptorch, celoss only support traget.long()

Sorry for replying so late. Maybe you have figured it out yourself, you can use label smooth just like you use cross-entropy-loss of pytorch, only to be sure to add the args of smooth which controls the smooth label.