DCGAN / deep convolutional gan
A deep convolutional generative adversarial network is a GAN whose generator and discriminator use deep convolutional neural-network architectures.
Evolutionary Deep Learning: Genetic algorithms and neural networks
A deep convolutional generative adversarial network is a generative adversarial network whose generator and discriminator use convolutional neural-network architectures.
- How it is used
- Builds and trains convolutional GANs for generating image samples in executable Keras notebooks.
- How deep it goes
- Explains architecture, hyperparameters, compilation, and alternating training, while deferring detailed convolution theory.
- Examples
- Uses MNIST digit fives, Fashion-MNIST, CIFAR support, ten-epoch outputs, and dataset-variation exercises.
- What you can do after
- Build it from scratch in Keras, train it on image data, inspect generated outputs, and experiment with datasets and hyperparameters.
Learn Generative AI with PyTorch
A deep convolutional generative adversarial network architecture for image generation.
- How it is used
- Generates novel color images by training a generator and discriminator against one another.
- How deep it goes
- Explains adversarial roles, layer symmetry, activations, tensor channels, and optimizer settings, stopping short of extensive mathematical derivation.
- Examples
- Uses a 63,632-image anime-face dataset, latent vectors, discriminator and generator listings, and generated-face figures.
- What you can do after
- Build it from scratch in PyTorch, train both networks, and generate novel RGB images from latent noise.
Read how Learn Generative AI with PyTorch explains DCGAN / deep convolutional gan →
Related concepts
- generative adversarial networkkind of · A generative adversarial network is a generative model with a generator and discriminator trained in competition, enabling the generator to produce samples resembling a target dataset or distribution.
- genetic algorithmaddressed by · A genetic algorithm is an evolutionary optimization method that improves a population of candidate solutions through fitness-based selection and variation, often including recombination and mutation.
- generatoruses · A generator is a computational component or construct that produces data or values from inputs, representations, context, or specified constraints.
- discriminatoruses · A discriminator is the model component of a generative adversarial network that distinguishes real data from data generated by its generator.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.