torch.sparse.softmax¶
- torch.sparse.softmax(input, dim, *, dtype=None) Tensor ¶
Applies a softmax function.
Softmax is defined as:
where run over sparse tensor indices and unspecified entries are ignores. This is equivalent to defining unspecified entries as negative infinity so that when the entry with index has not specified.
It is applied to all slices along dim, and will re-scale them so that the elements lie in the range [0, 1] and sum to 1.
- Parameters
input (Tensor) – input
dim (int) – A dimension along which softmax will be computed.
dtype (
torch.dtype
, optional) – the desired data type of returned tensor. If specified, the input tensor is casted todtype
before the operation is performed. This is useful for preventing data type overflows. Default: None