AdaptiveAvgPool2D

Description

Performs 2D adaptive average pooling calculation on the input.

Input

One input:

x: tensor of type float16 or float, in NCHW format.

Output

One output:

y: tensor in NCHW format. Has an identical data type to x.

Property

output_size: list of two int values, specifying the shape size of the output hw.

ONNX Opset Support

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