pytorch / 2 / generated / torch.nn.maxpool3d.html

MaxPool3d

class torch.nn.MaxPool3d(kernel_size, stride=None, padding=0, dilation=1, return_indices=False, ceil_mode=False) [source]

Applies a 3D max 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 ) (N, C, D, H, W) , output ( N , C , D o u t , H o u t , W o u t ) (N, C, D_{out}, H_{out}, W_{out}) and kernel_size ( k D , k H , k W ) (kD, kH, kW) can be precisely described as:

out ( N i , C j , d , h , w ) = max k = 0 , , k D 1 max m = 0 , , k H 1 max n = 0 , , k W 1 input ( N i , C j , stride[0] × d + k , stride[1] × h + m , stride[2] × w + n ) \begin{aligned} \text{out}(N_i, C_j, d, h, w) ={} & \max_{k=0, \ldots, kD-1} \max_{m=0, \ldots, kH-1} \max_{n=0, \ldots, kW-1} \\ & \text{input}(N_i, C_j, \text{stride[0]} \times d + k, \text{stride[1]} \times h + m, \text{stride[2]} \times w + n) \end{aligned}

If padding is non-zero, then the input is implicitly padded with negative infinity on both sides for padding number of points. dilation controls the spacing between the kernel points. It is harder to describe, but this link has a nice visualization of what dilation does.

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.

The parameters kernel_size, stride, padding, dilation 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 to take a max over
  • 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 negative infinity padding to be added on all three sides
  • dilation (Union[int, Tuple[int, int, int]]) – a parameter that controls the stride of elements in the window
  • return_indices (bool) – if True, will return the max indices along with the outputs. Useful for torch.nn.MaxUnpool3d later
  • ceil_mode (bool) – when True, will use ceil instead of floor to compute the output shape
Shape:
  • Input: ( N , C , D i n , H i n , W i n ) (N, C, D_{in}, H_{in}, W_{in}) or ( C , D i n , H i n , W i n ) (C, D_{in}, H_{in}, W_{in}) .
  • Output: ( N , C , D o u t , H o u t , W o u t ) (N, C, D_{out}, H_{out}, W_{out}) or ( C , D o u t , H o u t , W o u t ) (C, D_{out}, H_{out}, W_{out}) , where

    D o u t = D i n + 2 × padding [ 0 ] dilation [ 0 ] × ( kernel_size [ 0 ] 1 ) 1 stride [ 0 ] + 1 D_{out} = \left\lfloor\frac{D_{in} + 2 \times \text{padding}[0] - \text{dilation}[0] \times (\text{kernel\_size}[0] - 1) - 1}{\text{stride}[0]} + 1\right\rfloor
    H o u t = H i n + 2 × padding [ 1 ] dilation [ 1 ] × ( kernel_size [ 1 ] 1 ) 1 stride [ 1 ] + 1 H_{out} = \left\lfloor\frac{H_{in} + 2 \times \text{padding}[1] - \text{dilation}[1] \times (\text{kernel\_size}[1] - 1) - 1}{\text{stride}[1]} + 1\right\rfloor
    W o u t = W i n + 2 × padding [ 2 ] dilation [ 2 ] × ( kernel_size [ 2 ] 1 ) 1 stride [ 2 ] + 1 W_{out} = \left\lfloor\frac{W_{in} + 2 \times \text{padding}[2] - \text{dilation}[2] \times (\text{kernel\_size}[2] - 1) - 1}{\text{stride}[2]} + 1\right\rfloor

Examples:

>>> # pool of square window of size=3, stride=2
>>> m = nn.MaxPool3d(3, stride=2)
>>> # pool of non-square window
>>> m = nn.MaxPool3d((3, 2, 2), stride=(2, 1, 2))
>>> input = torch.randn(20, 16, 50, 44, 31)
>>> output = m(input)

© 2024, PyTorch Contributors
PyTorch has a BSD-style license, as found in the LICENSE file.
https://pytorch.org/docs/2.1/generated/torch.nn.MaxPool3d.html