Rate this Page
★★★★★

torch.sparse.log_softmax#

torch.sparse.log_softmax(input,dim,*,dtype=None)→Tensor#

Applies a softmax function followed by logarithm.

Seesoftmax for more details.

Parameters

  • input (Tensor) – input

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

  • dtype (torch.dtype, optional) – the desired data typeof returned tensor. If specified, the input tensor iscasted todtype before the operation isperformed. This is useful for preventing data typeoverflows. Default: None