AdaptiveMaxPool3d

class torch.nn.modules.pooling.AdaptiveMaxPool3d(output_size, return_indices=False)

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

The output is of size $D_{out} \times H_{out} \times W_{out}$, for any input size. The number of output features is equal to the number of input planes.

Each output element is the maximum over a cuboidal region of the input. The bounds are computed independently for each spatial dimension, from an output index $k$, an input size $I$ and an output size $O$:

$$\text{start}(k, I, O) = \left\lfloor \frac{k \times I}{O} \right\rfloor \qquad \text{end}(k, I, O) = \left\lceil \frac{(k + 1) \times I}{O} \right\rceil$$

The region for output element $(d, h, w)$ spans $[\text{start}(d, D_{in}, D_{out}), \text{end}(d, D_{in}, D_{out}))$ along the depth dimension, and likewise with $(H_{in}, H_{out})$ and $(W_{in}, W_{out})$ along height and width.

When an input size is not divisible by the corresponding output size, these regions may have different sizes and may overlap.

Parameters:

• output_size (int | None | tuple[int | None, int | None, int | None]) – the target output size of the image of the form $D_{out} \times H_{out} \times W_{out}$. Can be a tuple $(D_{out}, H_{out}, W_{out})$ or a single $D_{out}$ for a cube $D_{out} \times D_{out} \times D_{out}$. $D_{out}$, $H_{out}$ and $W_{out}$ can be either an int, or None which means the size will be the same as that of the input.

• return_indices (bool) – if True, will return the indices along with the outputs. Useful to pass to nn.MaxUnpool3d. Default: False

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 $(D_{out}, H_{out}, W_{out})=\text{output\_size}$.

Examples

>>> # target output size of 5x7x9
>>> m = nn.AdaptiveMaxPool3d((5, 7, 9))
>>> input = torch.randn(1, 64, 8, 9, 10)
>>> output = m(input)
>>> # target output size of 7x7x7 (cube)
>>> m = nn.AdaptiveMaxPool3d(7)
>>> input = torch.randn(1, 64, 10, 9, 8)
>>> output = m(input)
>>> # target output size of 7x9x8
>>> m = nn.AdaptiveMaxPool3d((7, None, None))
>>> input = torch.randn(1, 64, 10, 9, 8)
>>> output = m(input)

forward(input)

Runs the forward pass.