AvgPool2d¶

class AvgPool2d(kernel_size, stride=None, padding=0, mode='average_count_exclude_padding', **kwargs)[source]¶

Applies a 2D average pooling over an input.

For instance, given an input of the size \((N, C, H_{\text{in}}, W_{\text{in}})\) and kernel_size \((kH, kW)\), this layer generates the output of the size \((N, C, H_{\text{out}}, W_{\text{out}})\) through a process described as:

\[out(N_i, C_j, h, w) = \frac{1}{kH * kW} \sum_{m=0}^{kH-1} \sum_{n=0}^{kW-1} input(N_i, C_j, stride[0] \times h + m, stride[1] \times w + n)\]

If padding is non-zero, then the input is implicitly zero-padded on both sides for padding number of points.

Parameters

kernel_size (Union[int, Tuple[int, int]]) – the size of the window.
stride (Union[int, Tuple[int, int]]) – the stride of the window. Default value is kernel_size.
padding (Union[int, Tuple[int, int]]) – implicit zero padding to be added on both sides.Default: 0.
mode (str) – whether to include the padding values while calculating the average, set to “average” will do counting. Default: “average_count_exclude_padding”

Shape:

Input: \((N, C, H_{in}, W_{in})\) or \((C, H_{in}, W_{in})\).
Output: \((N, C, H_{out}, W_{out})\) or \((C, H_{out}, W_{out})\), where

\[H_{out} = \left\lfloor\frac{H_{in} + 2 \times \text{padding}[0] - \text{kernel\_size}[0]}{\text{stride}[0]} + 1\right\rfloor\]

\[W_{out} = \left\lfloor\frac{W_{in} + 2 \times \text{padding}[1] - \text{kernel\_size}[1]}{\text{stride}[1]} + 1\right\rfloor\]

Returns: module. The instance of the AvgPool2d module.
Return type: Return type

Examples

>>> import numpy as np
>>> m = M.AvgPool2d(kernel_size=2, stride=2, padding=[1,0], mode="average")
>>> inp = mge.tensor(np.arange(1 * 1 * 3 * 4).astype(np.float32).reshape(1, 1, 3, 4))
>>> output = m(inp)
>>> output
Tensor([[[[0.25 1.25]
          [6.5  8.5 ]]]], device=xpux:0)

SlidingWindowTranspose

MaxPool2d