PyTorch
torch / torch
torch.logcumsumexp¶
-
torch.
logcumsumexp
(input, dim, *, out=None) → Tensor¶ Returns the logarithm of the cumulative summation of the exponentiation of elements of
input
in the dimensiondim
.For summation index j given by dim and other indices i , the result is
logcumsumexp(x)ij=logj=0∑iexp(xij)- Parameters
- Keyword Arguments
out (Tensor, optional) – the output tensor.
- Example::
>>> a = torch.randn(10) >>> torch.logcumsumexp(a, dim=0) tensor([-0.42296738, -0.04462666, 0.86278635, 0.94622083, 1.05277811, 1.39202815, 1.83525007, 1.84492621, 2.06084887, 2.06844475]))
此页内容是否对您有帮助
感谢反馈!