MaxUnpool

Description

Indicates the reverse of the MaxPool operation.

Input

Three inputs:

X: tensor of type float16 or float.

I: tensor of type int64.

output_shape: (optional) int64, output shape.

Output

One output:

Y: tensor of the identical data type as the input.

Attribute

kernel_shape: (mandatory) a list of int or int values, specifying the kernel size along each axis. The data type is INTS.

pads: list of int or int types, padding along each axis. Data type: INTS.

strides: a list of int or int values, strides along each axis. Data type: INTS.

ONNX Opset Support

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