PyTorch is an open-source machine learning library developed by Facebook's AI Research lab, widely used for applications in deep learning and neural networks. It offers developers a flexible and dynamic computational graph that allows them to change network behaviors on-the-fly, which is particularly beneficial for tasks requiring variable input sizes or structures. PyTorch is favored for its intuitive Pythonic interface, making it easier for developers to integrate with other libraries and frameworks. Its seamless interoperability with NumPy and GPU acceleration through CUDA support facilitates building, training, and deploying complex models efficiently. PyTorch's active community and comprehensive documentation help streamline the development process, making it a go-to choice for research and production environments alike. Whether you're working on vision, language, or reinforcement learning tasks, PyTorch provides robust tools and a user-friendly environment for crafting innovative AI solutions.
View the most prominent open source PyTorch projects in the list below. Click on a specific project to view its alternative or complementary packages. Make comparisons and find the best package for your app.
- Stable Diffusion web UI☆153,904Updated last month
- 🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal model…☆146,154Updated this week
- The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.☆80,899Updated this week
- Deep Learning for humans☆63,155Updated this week
- 🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, fee…☆61,444Updated 10 months ago
- Clone a voice in 5 seconds to generate arbitrary speech in real-time☆54,575Updated last month
- YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite☆54,370Updated last week
- Implement a ChatGPT-like LLM in PyTorch from scratch, step by step☆57,201Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆50,864Updated this week
- Ultralytics YOLO11 🚀☆42,328Updated this week
- 🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production☆40,976Updated 10 months ago
- Learn how to design, develop, deploy and iterate on production-grade ML applications.☆39,740Updated 10 months ago
- DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.☆39,142Updated this week
- Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.☆37,737Updated this week
- GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.☆36,853Updated 11 months ago
- 🚀AI拟声: 5秒内克隆您的声音并生成任意语音内容 Clone a voice in 5 seconds to generate arbitrary speech in real-time☆36,372Updated 7 months ago
- The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights --…☆34,559Updated this week
- Facebook AI Research Sequence-to-Sequence Toolkit written in Python.☆31,582Updated 2 weeks ago
- PyTorch Tutorial for Deep Learning Researchers☆31,418Updated last year
- OpenMMLab Detection Toolbox and Benchmark☆31,240Updated 10 months ago
- Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.☆31,491Updated 10 months ago
- Visualizer for neural network, deep learning and machine learning models☆30,536Updated this week
- Pretrain, finetune ANY AI model of ANY size on multiple GPUs, TPUs with zero code changes.☆29,665Updated this week
- 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.☆29,526Updated this week
- SoftVC VITS Singing Voice Conversion☆27,300Updated last year
- The fastai deep learning library☆27,095Updated 3 weeks ago
- We write your reusable computer vision tools. 💜☆26,786Updated last week
- Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and …☆27,057Updated 9 months ago
- Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including …☆26,134Updated 10 months ago
- State-of-the-art 2D and 3D Face Analysis Project☆25,585Updated 2 weeks ago
- deep learning for image processing including classification and object-detection etc.☆25,047Updated 5 months ago
- JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf☆24,203Updated 9 months ago
- Image-to-Image Translation in PyTorch☆24,165Updated last year
- Graph Neural Network Library for PyTorch☆22,525Updated last week
- ncnn is a high-performance neural network inference framework optimized for the mobile platform☆21,680Updated this week
- Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powere…☆21,724Updated 2 months ago
- pytorch handbook是一本开源的书籍，目标是帮助那些希望和使用PyTorch进行深度学习开发和研究的朋友快速入门，其中包含的Pytorch教程全部通过测试保证可以成功运行☆21,022Updated 11 months ago
- AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file convert…☆21,281Updated this week
- GUI for a Vocal Remover that uses Deep Neural Networks.☆21,066Updated 3 months ago
- 🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools☆20,306Updated this week