Generative adversarial network

As explained in Learn Generative AI with PyTorch

A generative adversarial network, a model family trained with a generator and discriminator to synthesize realistic data or transform data between domains.

A generative adversarial network (GAN) trains two neural networks together. The generator makes samples intended to resemble the training data; the discriminator tries to tell those samples from real ones. Their competition helps the generator produce more realistic results. Unlike a discriminative model used to assign labels to inputs, the finished GAN is used to create new data. section 1.2.1 section 1.1.1

Figure 1.2 GANs architecture and its components. GANs employ a dual-network architecture comprising a generative model (left) tasked with capturing the underlying data distribution and a discriminative model (center) that serves to estimate the likelihood that a given sample originates from the authentic training dataset (considered as “real”) rather than being a product of the generative model (considered as “fake”).

Follow both paths into the discriminator: one carries training samples, and the other carries samples made by the generator. section 1.2.1

A first GAN project follows a short workflow:

• Prepare examples of the pattern to reproduce. The generated content depends on this training data. section 3.6
• Build a discriminator to classify real versus generated samples and a generator to make new samples. section 3.6
• Train the networks, decide when to stop, then discard the discriminator and use the trained generator. section 3.6

Generate a number pattern

To generate sequences of ten integers that are multiples of 5, first turn the training integers into one-hot variables the networks can use. Build and train both networks, use early stopping, then convert the generator’s output back into readable integers. The same workflow can instead learn pairs of values following an exponential growth curve. section 3.5 section 3.6

The pattern need not be numeric. Training images can lead to generated clothing or face images; a CycleGAN can instead transform an image attribute, such as changing blond hair to black hair and back. GAN projects also extend to music, where choosing a digital representation is part of preparing the data. section 1.2.1 section 1.2.3 section 13.1

How Learn Generative AI with PyTorch covers it

How deep it goes

Develops a build-train-stop-use workflow, including data preparation and early stopping in a number-pattern project.

Examples

Works through exponential-curve data and sequences of multiples of 5, alongside face-image transformation and music generation.

What it assumes

Assumes basic deep-learning skills while preparing readers with PyTorch classification; teaches the generator–discriminator workflow from scratch.

What you can do after

Build it from scratch in PyTorch, then train, save, load, and use a generator to produce patterned samples.

How it connects

Connects binary classification and one-hot encoding to the discriminator, and CycleGAN to image-domain transformation.

liveBookmanning.com

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

Also explained in

• 

  liveBookmanning.com
  Inside Deep Learning: Math, Algorithms, ModelsA generative deep-learning model consisting of a generator and discriminator trained adversarially to produce realistic samples.
• 

  liveBookmanning.com
  Outlier Detection in PythonA generative adversarial network is a model consisting of a generator and discriminator trained competitively so the generator produces data resembling a reference distribution.
• 

  liveBookmanning.com
  Grokking Machine LearningA generative adversarial network is a generative model composed of competing generator and discriminator networks that learn to produce realistic data.
• 

  liveBookmanning.com
  Sutskever's ListA generative adversarial network is a model architecture in which a generator creates candidates and a discriminator learns to distinguish them from genuine data.
• 

  liveBookmanning.com
  Generative AI in ActionA generative adversarial network is a generative model composed of a generator and discriminator trained adversarially to produce realistic synthetic data.
• 

  liveBookmanning.com
  Evolutionary Deep Learning: Genetic algorithms and neural networksA generative adversarial network is a model consisting of a generator and discriminator trained in opposition to produce realistic synthetic data.
• 

  liveBookmanning.com
  Data Without LabelsA generative adversarial network is a generative model consisting of a generator and discriminator trained adversarially to produce realistic samples.
• 

  liveBookmanning.com
  Machine Learning for Tabular Data: XGBoost, Deep Learning, and AIA generative adversarial network is a deep learning architecture consisting of a generator and discriminator trained adversarially to produce samples resembling real data.
• 

  liveBookmanning.com
  Introduction to Generative AI, Second EditionA generative adversarial network is a model composed of a generator and discriminator trained through competition between synthetic-data creation and authenticity evaluation.
• 

  liveBookmanning.com
  Grokking AI Algorithms, Second EditionA generative adversarial network is a machine-learning model consisting of a generator and a discriminator trained through competition to produce increasingly realistic synthetic data.
• 

  liveBookmanning.com
  Build a Text-to-Image Generator (from Scratch)A generative adversarial network is a generative model trained through competition between a generator that creates samples and a discriminator that distinguishes generated samples from real data.

Compare how 12 books explain generative adversarial network →

Related concepts

• generatorhas part · A generator is a computational component or construct that produces data or values from inputs, representations, context, or specified constraints.
• discriminatorhas part · A discriminator is the model component of a generative adversarial network that distinguishes real data from data generated by its generator.
• VQGANincludes · VQGAN is a generative model that combines vector-quantized discrete latent representations with adversarial and perceptual objectives to synthesize images.
• generative modelingkind of · Generative modeling is a machine-learning approach that learns patterns or a data distribution to generate new samples resembling the data.
• DCGAN / deep convolutional ganincludes · A deep convolutional generative adversarial network is a GAN whose generator and discriminator use deep convolutional neural-network architectures.
• generationkind of · Generation is the computational production of outputs from supplied inputs or context, often by applying a model to produce predictions or new content.

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.