mindspore.nn.ReduceLogSumExp

class mindspore.nn.ReduceLogSumExp(axis, keep_dims=False)[source]

Reduces a dimension of a tensor by calculating exponential for all elements in the dimension, then calculate logarithm of the sum.

The dtype of the tensor to be reduced is number.

\[ReduceLogSumExp(x) = \log(\sum(e^x))\]
Parameters

  • axis (Union[int, tuple(int), list(int)]) – (), reduce all dimensions. Only constant value is allowed.

  • keep_dims (bool) – If True, keep these reduced dimensions and the length is 1. If False, don’t keep these dimensions. Default : False.

Inputs:

  • x (Tensor) - The input tensor. With float16 or float32 data type.

Outputs:

Tensor, has the same dtype as the x.

  • If axis is (), and keep_dims is False, the output is a 0-D tensor representing the sum of all elements in the input tensor.

  • If axis is int, set as 2, and keep_dims is False, the shape of output is \((x_1, x_3, ..., x_R)\).

  • If axis is tuple(int), set as (2, 3), and keep_dims is False, the shape of output is \((x_1, x_4, ..., x_R)\).

Raises

  • TypeError – If axis is not one of int, list, tuple.

  • TypeError – If keep_dims is not bool.

  • TypeError – If dtype of x is neither float16 nor float32.

Supported Platforms:

Ascend GPU

Examples

>>> input_x = Tensor(np.random.randn(3, 4, 5, 6).astype(np.float32))
>>> op = nn.ReduceLogSumExp(1, keep_dims=True)
>>> output = op(input_x)
>>> print(output.shape)
(3, 1, 5, 6)