LogSoftMax
Description
Computes the logarithm of the softmax value of a given input tensor.
Input
x: input tensor of type float16 or float.
Attribute
axis: int, specifying the axis to be calculated. The value range is [-r, r-1]. r is the input rank. The default value is -1.
Output
y: output tensor of the identical data type and shape to the input.
Constraints
Float16 does not support ONNX v18.
ONNX Opset Support
Opset v8/v9/v10/v11/v12/v13/v14/v15/v16/v17/v18
Parent topic: Supported ONNX Operators