LogSoftMax

Description

Computes the logsoftmax value of the input tensor.

Input

One input:

x: tensor of type float16 or float.

Output

One output:

y: tensor. Has an identical data type and shape to those of the input.

Attribute

axis: int, axis to be calculated. [-r, r-1], where r is the input rank.

Constraints

Float16 does not support ONNX v18.

ONNX Opset Support

Opset v8/v9/v10/v11/v12/v13/v14/v15/v16/v17/v18