awesome-repositories.com
博客
MCP
awesome-repositories.com

通过 AI 驱动的搜索，发现最优秀的开源仓库。

探索精选搜索开源替代品自托管软件博客网站地图
项目MCP 服务器关于排名机制媒体报道
法律隐私政策服务条款
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
wiseodd avatar

wiseodd/generative-models

0
View on GitHub↗
7,497 星标·2,013 分支·Python·Unlicense·12 次浏览wiseodd.github.io↗

Generative Models

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.

Features

  • Synthetic Data Generators - Provides a comprehensive library of synthetic data generators including GANs, VAEs, and energy-based networks.
  • Generative AI Models - Provides a comprehensive library of generative AI models for creating synthetic data and modeling probability distributions.
  • Boltzmann Machines - Implements Restricted Boltzmann Machines to model binary data distributions using energy-based networks.
  • Energy-Based Models - Implements energy-based models that represent data patterns by assigning scalar energy values to variable configurations.

AI 搜索

探索更多 awesome 仓库

用简单的语言描述您的需求 —— AI 将根据相关性为您从数千个精选开源项目中进行排序。

Start searching with AI
  • Generative Adversarial Networks - Implements Generative Adversarial Networks architectures using competing generator and discriminator models to create realistic synthetic data.
  • Helmholtz Machines - Implements Helmholtz Machines that use bidirectional neural networks and wake-sleep algorithms to model complex data patterns.
  • Variational Autoencoders - Implements Variational Autoencoders that map inputs to a continuous latent distribution for generative tasks.
  • Vector-Quantized VAEs - Provides a framework for Variational Autoencoder models that map data to a latent space for sample generation.
  • Energy-Based Models - Implements Restricted Boltzmann Machines and Deep Belief Networks using energy-based modeling and contrastive divergence.
  • Generative Adversarial Networks - Implements generative adversarial networks using competing generator and discriminator models to produce synthetic data.
  • Probabilistic Models - Implements probabilistic models that represent complex data patterns using energy-based networks and contrastive divergence.
  • Synthetic Data Generators - Ships diverse generative architectures for creating synthetic data based on existing data distributions.
  • Bidirectional Neural Architectures - Provides bidirectional neural architectures designed to learn underlying probability distributions of complex datasets.
  • Contrastive Divergence Learning - Implements the contrastive divergence algorithm for training energy-based models and Restricted Boltzmann Machines.
  • Latent Space Encoders - Ships latent-space encoding capabilities that map high-dimensional data into compressed representations for synthetic sample generation.
  • Generative Model Training Tools - Provides training tools for fitting binary visible and hidden variables in generative models.
  • Multi-Framework Model Collections - Offers a multi-framework collection of deep learning models implemented in both PyTorch and TensorFlow.
  • Unsupervised Learning - Implements algorithms for discovering hidden patterns and hierarchical representations in unlabeled datasets.
  • Wake-Sleep Algorithms - Implements the wake-sleep algorithm to coordinate generative and recognition models for learning hierarchical representations.
  • Deep Learning Models - Implementations of generative models like GANs and VAEs.
  • Generative Adversarial Networks - Comprehensive collection of generative architectures including GANs and VAEs.
  • Generative Model Implementations - PyTorch and TensorFlow implementations of generative models.
  • GANs, VAEs, and AEs - Listed in the “GANs, VAEs, and AEs” section of the The Incredible Pytorch awesome list.

    • Star 历史

    wiseodd/generative-models 的 Star 历史图表wiseodd/generative-models 的 Star 历史图表

    Generative Models 的开源替代方案

    相似的开源项目，按与 Generative Models 的功能重合度排序。
    • dragen1860/tensorflow-2.x-tutorialsdragen1860 的头像

      dragen1860/TensorFlow-2.x-Tutorials

      6,351在 GitHub 上查看↗

      This project is a collection of TensorFlow 2.x machine learning tutorials and practical code examples. It serves as a deep learning implementation guide for constructing diverse neural network architectures, including convolutional, recurrent, and generative networks. The repository provides templates and examples for several specialized domains, including computer vision for image classification and object detection, natural language processing for text generation and language understanding, and generative AI for synthesizing data using adversarial networks and autoencoders. It also includes

      Jupyter Notebookartificial-intelligencecomputer-visiondeep-learning
      在 GitHub 上查看↗6,351
    • nvlabs/stylegan2NVlabs 的头像

      NVlabs/stylegan2

      11,186在 GitHub 上查看↗

      StyleGAN2 is a TensorFlow generative adversarial network and image synthesis model designed to produce high-resolution synthetic visual content. It functions as a deep learning architecture that learns patterns from image datasets to synthesize new images. The project includes a latent space projection tool for mapping existing images to latent vectors to analyze their representation within a generative model. It also provides an image quality evaluation framework to measure the visual fidelity and diversity of synthetic outputs. The system covers the full generative pipeline, including imag

      Python
      在 GitHub 上查看↗11,186
    • borisdayma/dalle-miniborisdayma 的头像

      borisdayma/dalle-mini

      14,756在 GitHub 上查看↗

      dalle-mini is a text-to-image model and generative AI system designed to transform natural language descriptions into synthetic images. It functions as an image generation training toolkit and a generative model capable of creating visual representations from text prompts. The project provides a containerized deployment for consistent execution across different computing environments. It includes the necessary scripts and configuration files to train custom generative models from datasets. The system utilizes an autoregressive transformer architecture that treats visual data as discrete toke

      Python
      在 GitHub 上查看↗14,756
    • aladdinpersson/machine-learning-collectionaladdinpersson 的头像

      aladdinpersson/Machine-Learning-Collection

      8,465在 GitHub 上查看↗

      This project is a machine learning educational repository providing a collection of implementations and guides for machine learning and deep learning algorithms. It serves as a deep learning model library and a reference for training workflows, covering foundational machine learning, convolutional, recurrent, and transformer architectures. The collection includes a generative adversarial network suite for synthesizing realistic images and performing image-to-image translation. It also functions as a computer vision implementation guide for object detection and semantic segmentation, alongside

      Pythonmachine-learningmachine-learning-algorithmspytorch
      在 GitHub 上查看↗8,465
    查看 Generative Models 的所有 30 个替代方案→

    常见问题解答

    wiseodd/generative-models 是做什么的？

    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.

    wiseodd/generative-models 的主要功能有哪些？

    wiseodd/generative-models 的主要功能包括：Synthetic Data Generators, Generative AI Models, Boltzmann Machines, Energy-Based Models, Generative Adversarial Networks, Helmholtz Machines, Variational Autoencoders, Vector-Quantized VAEs。

    wiseodd/generative-models 有哪些开源替代品？

    wiseodd/generative-models 的开源替代品包括： dragen1860/tensorflow-2.x-tutorials — This project is a collection of TensorFlow 2.x machine learning tutorials and practical code examples. It serves as a… nvlabs/stylegan2 — StyleGAN2 is a TensorFlow generative adversarial network and image synthesis model designed to produce high-resolution… borisdayma/dalle-mini — dalle-mini is a text-to-image model and generative AI system designed to transform natural language descriptions into… aladdinpersson/machine-learning-collection — This project is a machine learning educational repository providing a collection of implementations and guides for… soumith/ganhacks — This project is a PyTorch-based generative framework and implementation template for building Generative Adversarial… antixk/pytorch-vae — This project is a deep learning research toolkit and generative model library providing implementations of Variational…