openvino.runtime.opset14.avg_pool(data_batch: Node | int | float | ndarray, strides: List[int], pads_begin: List[int], pads_end: List[int], kernel_shape: List[int], exclude_pad: bool, rounding_type: str = 'floor', auto_pad: str | None = None, name: str | None = None) Node#

Return average pooling node.

  • data_batch – The input node providing data.

  • strides – The window movement strides.

  • pads_begin – The number of pixels to add at the beginning along each axis.

  • pads_end – The number of pixels to add at the end along each axis.

  • kernel_shape – The pooling window shape.

  • exclude_pad – Whether or not to include zero padding in average computations.

  • rounding_type – Determines used rounding schema when computing output shape. Acceptable values are: [‘floor’, ‘ceil’, ‘ceil_torch’]. Defaults to ‘floor’.

  • auto_pad – Determines how the padding is calculated. Acceptable values: [None, ‘same_upper’, ‘same_lower’, ‘valid’]. Defaults to None.

  • name – Optional name for the new output node.


New node with AvgPool operation applied on its data.