Multi Label Cross Entropy

This is used in the output layer of multi label classification
AKA Multiple Binary Cross Entropy
Usually used after Sigmoid Function Layer
For implementation: PyTorch Loss Functions

$B C E = - (y l o g \hat{y} + (1 - y) l o g (1 - \hat{y})$ $Total-CE Loss = \frac{1}{M} \sum_{i}^{M} - (y_{i} l o g \hat{y_{i}} + (1 - y_{i}) l o g (1 - \hat{y_{i}})$

Related Notes