torch.nn.functional.log_softmax

torch.nn.functional.log_softmax(input, dim=None, _stacklevel=3, dtype=None)

Apply a softmax followed by a logarithm.

While mathematically equivalent to log(softmax(x)), doing these two operations separately is slower and numerically unstable. This function uses an alternative formulation to compute the output and gradient correctly.

See LogSoftmax for more details.

Parameters

• input (Tensor) – input

• dim (int) – A dimension along which log_softmax will be computed.

• dtype (torch.dtype, optional) – the desired data type of returned tensor. If specified, the input tensor is cast to dtype before the operation is performed. This is useful for preventing data type overflows. Default: None.

Return type

Tensor