Max pooling

As explained in Build a Text-to-Image Generator (from Scratch)

Max pooling is a spatial downsampling operation that retains the maximum activation within each local window.

Max pooling is a spatial downsampling operation that divides an image or feature map into local windows and retains the largest value from each window. It reduces height and width while preserving prominent features, making it useful in convolutional networks and U-Net down blocks. section 6.2.3 section 6.3.1

Process each pooling operation as follows:

• Choose a kernel size, such as 2 × 2 or 3 × 3, to define each local window. section 6.2.3
• Move the window by the configured stride; a stride of 2 advances two pixels horizontally and vertically. section 6.2.3
• Select the maximum value inside every window and place it in the downsampled feature map. section 6.2.3
• With nn.MaxPool2d(2), a U-Net down block reduces input width and height by half. section 6.3.1

A 4 × 4 tensor with 2 × 2 pooling

Applying torch.nn.MaxPool2d(2) with the default stride to a 4 × 4 input produces [[2, 4], [5, 7]]. Each output value is the largest value in one non-overlapping 2 × 2 region. section 6.2.3

Figure 6.5 A numerical example of how max pooling works, with a kernel size of 2 × 2 and a stride equal to 2

Use the numerical figure to trace each 2 × 2 window, its selected maximum, and the resulting downsampled output. section 6.2.3

How Build a Text-to-Image Generator (from Scratch) covers it

How deep it goes

Explains windows, kernel size, stride, numerical output, and PyTorch usage, but does not develop pooling internals.

Examples

Demonstrates a 4 × 4 tensor, 2 × 2 windows, stride 2, and the output tensor [[2, 4], [5, 7]].

What it assumes

Assumes familiarity with images, tensors, and convolutional layers while teaching kernel size, stride, windows, and maxima.

What you can do after

Apply it via PyTorch's nn.MaxPool2d(2) and verify its output on image tensors.

How it connects

Connects max pooling to convolutional layers, feature maps, U-Net down blocks, transposed convolution, and residual networks.

liveBookmanning.com

Read Build a Text-to-Image Generator (from Scratch) on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Math and Architectures of Deep Learning
• 

  liveBookmanning.com
  Deep Learning with R, Third EditionA max-pooling layer down-samples local regions by retaining their maximum values.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionA two-dimensional pooling layer that downsamples feature maps by taking local maxima.
• 

  liveBookmanning.com
  Deep Learning with PyTorch, Second Edition
• 

  liveBookmanning.com
  Graph Neural Networks in Actionmax_pool is a PyTorch Geometric pooling function that coarsens a graph by pooling clustered nodes using maximum-valued features.
• 

  liveBookmanning.com
  Natural Language Processing in Action, Second EditionMax pooling is a downsampling operation that retains the largest activation within each local region of a feature map.
• 

  liveBookmanning.com
  Evolutionary Deep Learning: Genetic algorithms and neural networksMax pooling is a neural-network operation that downsamples local activation regions by retaining their maximum values.
• 

  liveBookmanning.com
  Machine Learning Algorithms in DepthMax pooling is a downsampling operation that retains the largest value within each local window of a feature sequence.
• 

  liveBookmanning.com
  Sutskever's ListA downsampling operation that retains the largest activation within each local spatial window.

Compare how 10 books explain max pooling →

Related concepts

• downsamplingkind of · Downsampling is the reduction of data quantity, spatial resolution, temporal resolution, or sampling rate by retaining, selecting, or aggregating fewer representative values or observations.
• poolingkind of · Pooling is an operation that aggregates values or representations across regions or axes to produce a reduced or summarized representation.
• convolutional neural networkpart of · A convolutional neural network is a neural-network architecture that applies learned convolutional operations to extract patterns from structured data.
• strided convolutioncontrasts with · A strided convolution is a convolution whose filter moves across input positions by more than one step, typically reducing spatial or temporal resolution.
• convolutional layeruses · A convolutional layer is a neural-network layer that applies shared learned filters to local regions of structured input to produce feature representations.
• neural network layerkind of · A neural network layer is a computational stage or component that transforms input representations into outputs within a neural network.

This explainer was generated by Manning's knowledge graph from the text of Build a Text-to-Image Generator (from Scratch). The section links point to the parts of the book it draws on.