AvgPool3d

class torch.nn.modules.pooling.AvgPool3d(kernel_size, stride=None, padding=0, ceil_mode=False, count_include_pad=True, divisor_override=None)

Applies a 3D average pooling over an input signal composed of several input planes.

In the simplest case, the output value of the layer with input size $(N, C, D, H, W)$, output $(N, C, D_{out}, H_{out}, W_{out})$ and kernel_size $(kD, kH, kW)$ can be precisely described as:

$$\begin{aligned} \text{out}(N_i, C_j, d, h, w) ={} & \sum_{k=0}^{kD-1} \sum_{m=0}^{kH-1} \sum_{n=0}^{kW-1} \\ & \frac{\text{input}(N_i, C_j, \text{stride}[0] \times d + k, \text{stride}[1] \times h + m, \text{stride}[2] \times w + n)} {kD \times kH \times kW} \end{aligned}$$

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

Note

When ceil_mode=True, sliding windows are allowed to go off-bounds if they start within the left padding or the input. Sliding windows that would start in the right padded region are ignored.

Note

pad should be at most half of effective kernel size.

The parameters kernel_size, stride can either be:

• a single int – in which case the same value is used for the depth, height and width dimension

• a tuple of three ints – in which case, the first int is used for the depth dimension, the second int for the height dimension and the third int for the width dimension

Parameters

• kernel_size (Union[int, tuple[int, int, int]]) – the size of the window

• stride (Union[int, tuple[int, int, int]]) – the stride of the window. Default value is kernel_size

• padding (Union[int, tuple[int, int, int]]) – implicit zero padding to be added on all three sides

• ceil_mode (bool) – when True, will use ceil instead of floor to compute the output shape

• count_include_pad (bool) – when True, will include the zero-padding in the averaging calculation

• divisor_override (Optional[int]) – if specified, it will be used as divisor, otherwise kernel_size will be used

Shape:

• Input: $(N, C, D_{in}, H_{in}, W_{in})$ or $(C, D_{in}, H_{in}, W_{in})$.

• Output: $(N, C, D_{out}, H_{out}, W_{out})$ or $(C, D_{out}, H_{out}, W_{out})$, where

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

  Per the note above, if ceil_mode is True and $(D_{out} - 1)\times \text{stride}[0]\geq D_{in} + \text{padding}[0]$, we skip the last window as it would start in the padded region, resulting in $D_{out}$ being reduced by one.

  The same applies for $W_{out}$ and $H_{out}$.

Examples:

>>> # pool of square window of size=3, stride=2
>>> m = nn.AvgPool3d(3, stride=2)
>>> # pool of non-square window
>>> m = nn.AvgPool3d((3, 2, 2), stride=(2, 1, 2))
>>> input = torch.randn(20, 16, 50, 44, 31)
>>> output = m(input)

forward(input)

Runs the forward pass.

Return type

Tensor