Rate this Page
★★★★★

torch.nn.functional.log_softmax#

torch.nn.functional.log_softmax(input,dim=None,_stacklevel=3,dtype=None)[source]#

Apply a softmax followed by a logarithm.

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

SeeLogSoftmax 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 todtype before the operationis performed. This is useful for preventing data type overflows. Default: None.

Return type

Tensor