ReduceMax
Description
Computes the maximum value of the input tensor in the specified direction.
Input
One input:
x: tensor of type float16, float, int8, int32, int64 or double.
Output
One output. :
y: tensor of type float16, float, int8, int32, int64 or double.
Attribute
axes: The data type is an int list. Meaning: calculation axis. Value range: [-r, r-1], where r is the rank of the input data.
keepdims: int, specifying whether to retain the reduced dimensions. Defaults to 1.
Constraints
When the input is of the float16, float, or int32 type, the axes attribute can be empty. When the input is of other types, you need to configure the axes attribute value.
ONNX Opset Support
Opset v8/v9/v10/v11/v12/v13/v14/v15/v16/v17
Parent topic: Operators Specifications of the AI Framework