- log-softmax x #!key (axis -1)procedure
Log-softmax with batch support. It is more numerically stable than log(softmax(x)).
Input shapes:
- 1-D: (n_classes)
- 2-D: (batch_size, n_classes) - log-softmax along axis
Gradient: dL/dx = dL/dy - exp(log_softmax(x)) * sum(dL/dy)