Feature map

As explained in Learn Generative AI with PyTorch

An intermediate activation map in a neural network whose spatial resolution can be increased or preserved by convolutional operations.

A feature map is the output produced when a convolutional filter scans an image. It records detected spatial patterns and becomes an intermediate representation for later layers. section 4.2.1

A convolution creates a feature map by:

• Sliding a filter across different image regions while reusing the same weights. section 4.2.1
• Multiplying corresponding input and filter elements, then summing the results at each position. section 4.2.1
• Producing one output channel for each learned feature set selected by out_channels. section 4.2.1

A small PyTorch feature map

A 3×3 grayscale tensor passed through a 2×2 convolution with stride 1 and no padding produces a 2×2 feature map. Setting the filter weights to [[1,2],[3,4]] and the bias to 0 yields [[7,14],[54,50]]. section 4.2.1

Figure 4.5 A numerical example of how convolutional operations work, with stride equal to 1 and no padding

Inspect the numerical sliding-window calculation behind the feature-map values. section 4.2.1

How Learn Generative AI with PyTorch covers it

How deep it goes

Explains filter scanning, arithmetic, tensor shapes, and PyTorch parameters, stopping short of deeper network architectures.

Examples

Demonstrates a 3×3 grayscale tensor, a 2×2 filter, fixed weights, and a resulting 2×2 output.

What it assumes

Assumes familiarity with image grids and tensors while introducing channels, kernels, stride, and convolution arithmetic.

What you can do after

Builds a small feature map in PyTorch and verifies its values against manual convolution arithmetic.

How it connects

Connects feature maps with convolutional layers, filters, channels, stride, padding, and image classification.

liveBookmanning.com

Read Learn Generative AI with PyTorch on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  Deep Learning with R, Third EditionA feature map is a spatial array of activations indicating the presence or strength of a learned visual pattern at different image locations.
• 

  liveBookmanning.com
  Grokking Machine LearningA mapping that sends data points from an original input space into another feature space, usually of higher dimension.
• 

  liveBookmanning.com
  Grokking AI Algorithms, Second EditionA feature map is a spatially organized array of activation values representing learned features at different locations in an input or intermediate image representation.
• 

  liveBookmanning.com
  Math and Architectures of Deep LearningA spatial array of activation values produced by applying a convolution or pooling operation over an input image or prior layer output.
• 

  liveBookmanning.com
  Deep Learning with Python, Third EditionA spatial grid of activations produced by a convolutional or pooling layer, where each channel encodes the presence of a learned feature over locations.
• 

  liveBookmanning.com
  Sutskever's ListA spatial array of responses produced by applying a convolutional filter to an input.
• 

  liveBookmanning.com
  Machine Learning Algorithms in DepthA feature map is a function that represents input objects as vectors in a feature space, possibly an infinite-dimensional one.

Compare how 8 books explain feature map →

Related concepts

• convolutional layerproduced by · A convolutional layer is a neural-network layer that applies shared learned filters to local regions of structured input to produce feature representations.
• kernel functionproduced by · A kernel function is a mathematical function that measures similarity between pairs of inputs, often representing an inner product in an implicit feature space.
• convolution kernelproduced by · A convolution kernel is a small array or tensor of weights applied across local input regions to compute weighted responses and detect or transform patterns.
• Region Proposal Networkused by · A Region Proposal Network is a neural-network module that generates candidate object regions from image features for a two-stage detector.
• channelhas part · A channel is an independent component or dimension of image or tensor data carrying a distinct color, feature, activation, or value stream.
• max poolingused by · Max pooling is an aggregation operation that replaces each local or grouped region with its maximum value, often to downsample a representation.

This explainer was generated by Manning's knowledge graph from the text of Learn Generative AI with PyTorch. The section links point to the parts of the book it draws on.