torch.sparse.log_softmax

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

Applies a softmax function followed by logarithm.

See softmax for more details.

参数

• input (张量) – 输入

• dim (int) – 将计算 softmax 的维度。

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