ReduceLogSumExp

Description

Computes the exponent of the logarithm sum in the specified direction of the input tensor.

Input

One input:

data: tensor of type float16 or float.

Output

One output:

reduced: tensor of type float16 or float.

Property

axes: 1D tensor of type int32 or int64. [-r, r-1], where r is the number of dimensions of the input data.

keepdims: int, specifying whether to reduce dimensions. The default value is 1, indicating that dimensions are reduced.

ONNX Opset Support

Opset v8/v9/v10/v11/v12/v13/v14/v15/v16