Files
pytorch/docs/cpp/source/api/nn/pooling.md
T
Svetlana Karslioglu 19da3da3d3 Restructure C++ docs (#174096)
The fix-cpp-build branch is a major restructuring that:

- Drops Exhale (which auto-generated API docs but caused OOM in CI) in favor of hand-written RST pages using Breathe directives
- Reorganizes notes into a hierarchical API reference with proper categories
- Adds new content: XPU docs, stable ABI docs, DeviceGuard/Stream docs
- Always runs Doxygen instead of gating on an env var

Pull Request resolved: https://github.com/pytorch/pytorch/pull/174096
Approved by: https://github.com/janeyx99, https://github.com/seemethere, https://github.com/albanD
2026-04-07 17:24:38 +00:00

4.9 KiB

myst
myst
html_meta
description keywords
Pooling layers in PyTorch C++ — MaxPool, AvgPool, AdaptiveMaxPool, AdaptiveAvgPool, and LPPool. PyTorch, C++, pooling, MaxPool2d, AvgPool2d, AdaptiveAvgPool2d, max pooling

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

:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:

Example:

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

AvgPool1d / AvgPool2d / AvgPool3d

:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:

AdaptiveAvgPool1d / AdaptiveAvgPool2d / AdaptiveAvgPool3d

:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:

Example:

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

AdaptiveMaxPool1d / AdaptiveMaxPool2d / AdaptiveMaxPool3d

:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:

FractionalMaxPool2d / FractionalMaxPool3d

:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:
: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.

:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:

Example:

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

:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members:
:members:
:undoc-members: