Function torch::special::log_softmax

• Defined in File special.h

Function Documentation

inline Tensor torch::special::log_softmax(const Tensor &self, int64_t dim, c10::optional<ScalarType> dtype)

Computes log followed by softmax(x) of the input See https://pytorch.org/docs/master/special.html#torch.special.log_softmax.

Example:

auto t = torch::randn(128, 128, dtype=kDouble);
torch::special::log_softmax(t, 0);