Softmax
Description
Applies the Softmax function to the input tensor.
Input
input: tensor of type float16, double, or float.
Attribute
axis (optional): int, axis for Softmax calculation. The default value is -1.
Output
output: tensor of the identical data type and shape as input.
Constraints
None.
ONNX Opset Support
Opset v8/v9/v10/v11/v12/v13/v14/v15/v16/v17/v18
Parent topic: Supported ONNX Operators