AdaptiveMaxPool3d — PyTorch 2.7 documentation (original) (raw)

class torch.nn.AdaptiveMaxPool3d(output_size, return_indices=False)[source][source]¶

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

The output is of size Dout×Hout×WoutD_{out} \times H_{out} \times W_{out}, for any input size. The number of output features is equal to the number of input planes.

Parameters

• output_size (Union[_int,_ None , tuple_[_Optional_[_int] , Optional_[_int] , Optional_[_int] ] ]) – the target output size of the image of the form Dout×Hout×WoutD_{out} \times H_{out} \times W_{out}. Can be a tuple (Dout,Hout,Wout)(D_{out}, H_{out}, W_{out}) or a singleDoutD_{out} for a cube Dout×Dout×DoutD_{out} \times D_{out} \times D_{out}.DoutD_{out}, HoutH_{out} and WoutW_{out} can be either aint, 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,Din,Hin,Win)(N, C, D_{in}, H_{in}, W_{in}) or (C,Din,Hin,Win)(C, D_{in}, H_{in}, W_{in}).
• Output: (N,C,Dout,Hout,Wout)(N, C, D_{out}, H_{out}, W_{out}) or (C,Dout,Hout,Wout)(C, D_{out}, H_{out}, W_{out}), where (Dout,Hout,Wout)=output_size(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)