SSealbook
Sealbook / Open source / Machine learning & data science

Top open-source machine learning & data science on GitHub

4,679 repositories with 1,000+ stars, ranked by stars. Leading: openclaw, tensorflow, stable-diffusion-webui.

RepositoryStarsLanguageLicenseActivity
51hpcaitech/ColossalAIMaking large AI models cheaper, faster and more accessible★ 41.4kPythonApache-2.0Active
52Crosstalk-Solutions/project-nomadProject NOMAD is an offline-first knowledge and education server. Wikipedia, thousands of books, courses, maps, and optional local AI, all r★ 40.5kTypeScriptApache-2.0Active
53photoprism/photoprismAI-Powered Photos App 🌈💎✨★ 40.3kGoOtherActive
54google-research/bertTensorFlow code and pre-trained models for BERT★ 40kPythonApache-2.0Archived
55floodsung/Deep-Learning-Papers-Reading-RoadmapDeep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!★ 39.6kPython—Stale
56OpenBMB/VoxCPMVoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning★ 39.5kPythonApache-2.0Active
57RSSNext/Folo🧡 Folo is the AI RSS Reader★ 39.1kTypeScriptAGPL-3.0Active
58google-research/google-researchGoogle Research★ 38.9kJupyter NotebookApache-2.0Active
59naptha/tesseract.jsPure Javascript OCR for more than 100 Languages 📖🎉🖥★ 38.8kJavaScriptApache-2.0Slowing
60fengdu78/Coursera-ML-AndrewNg-Notes吴恩达老师的机器学习课程个人笔记★ 38kHTML—Active
61myshell-ai/OpenVoiceInstant voice cloning by MIT and MyShell. Audio foundation model.★ 37.9kPythonMITStale
62TencentARC/GFPGANGFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.★ 37.7kPythonOtherStale
63microsoft/Data-Science-For-Beginners10 Weeks, 20 Lessons, Data Science for All!★ 37.6kJupyter NotebookMITActive
64google-ai-edge/mediapipeCross-platform, customizable ML solutions for live and streaming media.★ 37.3kC++Apache-2.0Active
65huggingface/pytorch-image-modelsThe largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- Re★ 37.2kPythonApache-2.0Active
66xinntao/Real-ESRGANReal-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.★ 37.1kPythonBSD-3-ClauseStale
67babysor/MockingBird🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time★ 36.9kPythonOtherSlowing
68blakeblackshear/frigateNVR with realtime local object detection for IP cameras★ 36.7kPythonMITActive
69hankcs/HanLPNatural Language Processing for the next decade. Tokenization, Part-of-Speech Tagging, Named Entity Recognition, Syntactic & Semantic Depend★ 36.5kPythonApache-2.0Active
70XingangPan/DragGANOfficial Code for DragGAN (SIGGRAPH 2023)★ 35.7kPythonOtherStale
71qdrant/qdrantQdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud★ 35.1kRustApache-2.0Active
72huggingface/diffusers🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.★ 34.8kPythonApache-2.0Active
73BVLC/caffeCaffe: a fast open framework for deep learning.★ 34.6kC++OtherStale
74CMU-Perceptual-Computing-Lab/openposeOpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation★ 34.5kC++OtherStale
75openai/CLIPCLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image★ 34.5kJupyter NotebookMITSlowing
76lllyasviel/ControlNetLet us control diffusion models!★ 34.1kPythonApache-2.0Stale
77cjpais/HandyA free, open source, and extensible speech-to-text application that works completely offline.★ 34.1kRustMITActive
78mli/paper-reading深度学习经典、新论文逐段精读★ 34k—Apache-2.0Stale
79explosion/spaCy💫 Industrial-strength Natural Language Processing (NLP) in Python★ 34kPythonMITActive
80tinygrad/tinygradYou like pytorch? You like micrograd? You love tinygrad! ❤️ ★ 33.8kPythonMITActive
81lutzroeder/netronVisualizer for neural network, deep learning and machine learning models★ 33.6kJavaScriptMITActive
82NandhaKishorM/layaNon-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ langua★ 33.4kPythonApache-2.0Active
83mckaywrigley/chatbot-uiAI chat for any model.★ 33.3kTypeScriptMITStale
84eriklindernoren/ML-From-ScratchMachine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aim★ 33kPythonMITStale
85open-mmlab/mmdetectionOpenMMLab Detection Toolbox and Benchmark★ 33kPythonApache-2.0Stale
86yunjey/pytorch-tutorialPyTorch Tutorial for Deep Learning Researchers★ 32.5kPythonMITStale
87facebookresearch/fairseqFacebook AI Research Sequence-to-Sequence Toolkit written in Python.★ 32.2kPythonMITArchived
88Lightning-AI/pytorch-lightningPretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.★ 31.4kPythonApache-2.0Active
89tqdm/tqdm:zap: A Fast, Extensible Progress Bar for Python and CLI★ 31.4kPythonOtherActive
90iperov/DeepFaceLiveReal-time face swap for PC streaming or video calls★ 31kPythonGPL-3.0Archived
91Anil-matcha/Open-Generative-AIUnrestricted Open-source alternative to AI video platforms — Free AI image & video generation studio with 600+ models (Flux, Midjourney, Kli★ 30.8kJavaScriptMITActive
92eugeneyan/applied-ml📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.★ 30.6k—MITStale
93nautechsystems/nautilus_traderProduction-grade Rust-native trading engine with deterministic event-driven architecture★ 30.3kRustLGPL-3.0Active
94tatsu-lab/stanford_alpacaCode and documentation to train Stanford's Alpaca models, and generate the data.★ 30.2kPythonApache-2.0Stale
95JaidedAI/EasyOCRReady-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc★ 30.1kPythonApache-2.0Slowing
96Genesis-Embodied-AI/genesis-worldSimulation platform for general-purpose robotics & embodied AI learning.★ 30.1kPythonApache-2.0Active
97deepinsight/insightfaceState-of-the-art 2D and 3D Face Analysis Project★ 30kPython—Active
98modular/modularThe Modular Platform (includes MAX & Mojo)★ 30kMojoOtherActive
99d2l-ai/d2l-enInteractive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Sta★ 29.9kPythonOtherStale
100donnemartin/data-science-ipython-notebooksData science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HD★ 29.4kPythonOtherStale