# wiseodd/generative-models

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/wiseodd-generative-models).**

7,497 stars · 2,013 forks · Python · Unlicense

## Links

- GitHub: https://github.com/wiseodd/generative-models
- Homepage: http://wiseodd.github.io
- awesome-repositories: https://awesome-repositories.com/repository/wiseodd-generative-models.md

## Description

This is a generative AI model library containing a collection of PyTorch and TensorFlow implementations for creating synthetic data and modeling complex probability distributions. It serves as a multi-framework repository of deep learning models designed for learning and replicating data patterns.

The project provides specialized implementation suites for several generative architectures. This includes Generative Adversarial Networks using competing generator and discriminator models, Variational Autoencoder frameworks that map data to a latent space, and Restricted Boltzmann Machine and Deep Belief Network implementations.

The library covers broad capabilities in probabilistic data modeling and unsupervised representation learning. It includes tools for synthetic data generation and the use of energy-based networks to model binary data distributions.

## Tags

### Artificial Intelligence & ML

- [Synthetic Data Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/dataset-generation/synthetic-data-generators.md) — Provides a comprehensive library of synthetic data generators including GANs, VAEs, and energy-based networks. ([source](https://github.com/wiseodd/generative-models/blob/master/README.md))
- [Generative AI Models](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-models.md) — Provides a comprehensive library of generative AI models for creating synthetic data and modeling probability distributions.
- [Boltzmann Machines](https://awesome-repositories.com/f/artificial-intelligence-ml/boltzmann-machines.md) — Implements Restricted Boltzmann Machines to model binary data distributions using energy-based networks. ([source](https://github.com/wiseodd/generative-models#readme))
- [Energy-Based Models](https://awesome-repositories.com/f/artificial-intelligence-ml/energy-based-models.md) — Implements energy-based models that represent data patterns by assigning scalar energy values to variable configurations.
- [Generative Adversarial Networks](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-adversarial-networks.md) — Implements Generative Adversarial Networks architectures using competing generator and discriminator models to create realistic synthetic data.
- [Helmholtz Machines](https://awesome-repositories.com/f/artificial-intelligence-ml/helmholtz-machines.md) — Implements Helmholtz Machines that use bidirectional neural networks and wake-sleep algorithms to model complex data patterns. ([source](https://github.com/wiseodd/generative-models/blob/master/README.md))
- [Variational Autoencoders](https://awesome-repositories.com/f/artificial-intelligence-ml/model-training/variational-autoencoders.md) — Implements Variational Autoencoders that map inputs to a continuous latent distribution for generative tasks. ([source](https://github.com/wiseodd/generative-models#readme))
- [Vector-Quantized VAEs](https://awesome-repositories.com/f/artificial-intelligence-ml/model-training/variational-autoencoders/vector-quantized-vaes.md) — Provides a framework for Variational Autoencoder models that map data to a latent space for sample generation.
- [Energy-Based Models](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-implementations/energy-based-models.md) — Implements Restricted Boltzmann Machines and Deep Belief Networks using energy-based modeling and contrastive divergence.
- [Generative Adversarial Networks](https://awesome-repositories.com/f/artificial-intelligence-ml/neural-network-implementations/generative-adversarial-networks.md) — Implements generative adversarial networks using competing generator and discriminator models to produce synthetic data.
- [Probabilistic Models](https://awesome-repositories.com/f/artificial-intelligence-ml/probabilistic-models.md) — Implements probabilistic models that represent complex data patterns using energy-based networks and contrastive divergence.
- [Synthetic Data Generators](https://awesome-repositories.com/f/artificial-intelligence-ml/synthetic-data-generators.md) — Ships diverse generative architectures for creating synthetic data based on existing data distributions. ([source](http://wiseodd.github.io/))
- [Bidirectional Neural Architectures](https://awesome-repositories.com/f/artificial-intelligence-ml/bidirectional-neural-architectures.md) — Provides bidirectional neural architectures designed to learn underlying probability distributions of complex datasets.
- [Contrastive Divergence Learning](https://awesome-repositories.com/f/artificial-intelligence-ml/contrastive-divergence-learning.md) — Implements the contrastive divergence algorithm for training energy-based models and Restricted Boltzmann Machines.
- [Latent Space Encoders](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-ai-resources/diffusion-visual-models/generative-ai-models/latent-space-generative-models/latent-space-projections/latent-space-encoders.md) — Ships latent-space encoding capabilities that map high-dimensional data into compressed representations for synthetic sample generation.
- [Generative Model Training Tools](https://awesome-repositories.com/f/artificial-intelligence-ml/generative-model-training-tools.md) — Provides training tools for fitting binary visible and hidden variables in generative models. ([source](https://github.com/wiseodd/generative-models/tree/master/RBM))
- [Multi-Framework Model Collections](https://awesome-repositories.com/f/artificial-intelligence-ml/multi-framework-model-collections.md) — Offers a multi-framework collection of deep learning models implemented in both PyTorch and TensorFlow.
- [Unsupervised Learning](https://awesome-repositories.com/f/artificial-intelligence-ml/unsupervised-learning.md) — Implements algorithms for discovering hidden patterns and hierarchical representations in unlabeled datasets.
- [Wake-Sleep Algorithms](https://awesome-repositories.com/f/artificial-intelligence-ml/wake-sleep-algorithms.md) — Implements the wake-sleep algorithm to coordinate generative and recognition models for learning hierarchical representations.

### Part of an Awesome List

- [Generative Model Implementations](https://awesome-repositories.com/f/awesome-lists/ai/generative-model-implementations.md) — PyTorch and TensorFlow implementations of generative models.