easynlp.utils.losses

MSE Loss

MSE loss

param inputs:input tensor
param targets:prediction tensor

CrossEntropy Loss

Cross Entropy loss

param input:input tensor
param target:prediction tensor
param weight:weighted cross-entropy loss (sample level weights)
param size_average:
 size average
param ignore_index:
 ignore index
param reduction:
 default 'mean' reduction

Vanilla KD Loss

Vanilla KD loss

param s_logits:student logits
param t_logits:target logits
param alpha:kd loss weight
param temperature:
 temperature

MultiLabel Sigmoid CrossEntropy Loss

MultiLabel Sigmoid Cross Entropy loss

param input:input tensor
param target:prediction tensor
param weight:weighted cross-entropy loss (sample level weights)
param size_average:
 size average
param ignore_index:
 ignore index
param reduction:
 default 'mean' reduction

Soft Input CrossEntropy Loss

Soft Input Cross Entropy loss

param input:input tensor
param target:prediction tensor
param weight:weighted cross-entropy loss (sample level weights)
param size_average:
 size average
param ignore_index:
 ignore index
param reduction:
 default 'mean' reduction

Hinge Loss for Embeddings

Hinge loss for embeddings

param emb1:embedding tensor
param emb2:embedding tensor
param margin:margin (default 0.3)