LogSoftmax — PyTorch 2.7 documentation (original) (raw)

class torch.nn.LogSoftmax(dim=None)[source][source]¶

Applies the log⁡(Softmax(x))\log(\text{Softmax}(x)) function to an n-dimensional input Tensor.

The LogSoftmax formulation can be simplified as:

LogSoftmax(xi)=log⁡(exp⁡(xi)∑jexp⁡(xj))\text{LogSoftmax}(x_{i}) = \log\left(\frac{\exp(x_i) }{ \sum_j \exp(x_j)} \right)

Shape:

• Input: (∗)(*) where * means, any number of additional dimensions
• Output: (∗)(*), same shape as the input

Parameters

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

Returns

a Tensor of the same dimension and shape as the input with values in the range [-inf, 0)

Return type

None

Examples:

m = nn.LogSoftmax(dim=1) input = torch.randn(2, 3) output = m(input)