Pooling Layers

Pooling layers reduce spatial dimensions by aggregating values in local regions, providing translation invariance and reducing computational cost in deeper layers.

MaxPool: Takes the maximum value in each pooling window (preserves strong features)
AvgPool: Takes the average value in each pooling window (smoother downsampling)
AdaptivePool: Automatically calculates kernel size to produce a target output size
FractionalMaxPool: Randomized pooling with fractional output size
MaxUnpool: Computes the partial inverse of MaxPool using stored indices
LPPool: Power-average pooling (generalization of avg/max pooling)

MaxPool1d / MaxPool2d / MaxPool3d

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

Example:

cpp

auto pool = torch::nn::MaxPool2d(
    torch::nn::MaxPool2dOptions(2).stride(2));

AvgPool1d / AvgPool2d / AvgPool3d

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

AdaptiveAvgPool1d / AdaptiveAvgPool2d / AdaptiveAvgPool3d

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

Example:

cpp

// Output will always be 7x7 regardless of input size
auto adaptive_pool = torch::nn::AdaptiveAvgPool2d(
    torch::nn::AdaptiveAvgPool2dOptions({7, 7}));

AdaptiveMaxPool1d / AdaptiveMaxPool2d / AdaptiveMaxPool3d

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

FractionalMaxPool2d / FractionalMaxPool3d

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

MaxUnpool1d / MaxUnpool2d / MaxUnpool3d

Computes a partial inverse of MaxPool, using the indices of the maximum values computed during pooling to place values back into unpooled positions.

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

Example:

cpp

auto pool = torch::nn::MaxPool2d(
    torch::nn::MaxPool2dOptions(2).stride(2).return_indices(true));
auto unpool = torch::nn::MaxUnpool2d(
    torch::nn::MaxUnpoolOptions<2>(2).stride(2));

auto [output, indices] = pool->forward_with_indices(input);
auto reconstructed = unpool->forward(output, indices);

LPPool1d / LPPool2d / LPPool3d

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members:

{doxygenclass}

:members:
:undoc-members: