Scatter LogSumExp

torch_scatter.scatter_logsumexp(src, index, dim=-1, out=None, dim_size=None, fill_value=None, eps=1e-12)[source]

Fills out with the log of summed exponentials of all values from the src tensor at the indices specified in the index tensor along a given axis dim. If multiple indices reference the same location, their exponential contributions add (cf. scatter_add()).

For one-dimensional tensors, the operation computes

\[\mathrm{out}_i = \log \, \left( \exp(\mathrm{out}_i) + \sum_j \exp(\mathrm{src}_j) \right)\]

where \(\sum_j\) is over \(j\) such that \(\mathrm{index}_j = i\).

Parameters:
  • src (Tensor) – The source tensor.
  • index (LongTensor) – The indices of elements to scatter.
  • dim (int, optional) – The axis along which to index. (default: -1)
  • out (Tensor, optional) – The destination tensor. (default: None)
  • dim_size (int, optional) – If out is not given, automatically create output with size dim_size at dimension dim. If dim_size is not given, a minimal sized output tensor is returned. (default: None)
  • fill_value (int, optional) – If out is not given, automatically fill output tensor with fill_value. (default: None)
  • eps (float, optional) – Small value to ensure numerical stability. (default: 1e-12)
Return type:

Tensor