GlobalLpPool

Description

Receives an input tensor and performs the LpPool pooling operation on the tensor in the same channel. This is equivalent to using LpPool pooling with a kernel size equal to the dimension of the input tensor space.

Input

input: tensor of type float16 or float.

Attribute

p: pooling the p value of the Lp norm of the input data. The data type is int32, and the default value is 2.

Output

y: output tensor of the same data type as the input.

Constraints

None.

ONNX Opset Support

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