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
701flashinfer-ai/flashinferFlashInfer: Kernel Library for LLM Serving★ 6.7kCudaApache-2.0Active
702dair-ai/ML-Course-Notes🎓 Sharing machine learning course / lecture notes.★ 6.7k—OtherStale
703ibis-project/ibisthe portable Python dataframe library★ 6.7kPythonApache-2.0Active
704charliedream1/ai_quant_tradeStock AI Trader: 1-stop platform for learning, sim & live trading. Covers: stock basics, strategies, LLMs, factor mining, ML/DL/RL, graph ne★ 6.6kJupyter NotebookApache-2.0Active
705MycroftAI/mycroft-coreMycroft Core, the Mycroft Artificial Intelligence platform. ★ 6.6kPythonApache-2.0Archived
706scikit-image/scikit-imageImage processing in Python★ 6.6kPythonOtherActive
707levihsu/OOTDiffusion[AAAI 2025] Official implementation of "OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on"★ 6.6kPythonOtherStale
708yandexdataschool/Practical_RLA course in reinforcement learning in the wild★ 6.6kJupyter NotebookUnlicenseSlowing
709mesop-dev/mesopRapidly build AI apps in Python★ 6.6kPythonApache-2.0Archived
710ml5js/ml5-libraryFriendly machine learning for the web! 🤖 ★ 6.6kJavaScriptOtherStale
711speedyapply/2027-AI-College-Jobs2027 AI/ML internship & new graduate job list updated daily★ 6.6k——Active
712openMVG/openMVGopen Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.★ 6.6kC++MPL-2.0Active
713argosopentech/argos-translateOpen-source offline translation library written in Python★ 6.6kPythonMITActive
714zhangqianhui/AdversarialNetsPapersAwesome paper list with code about generative adversarial nets ★ 6.6k——Stale
715open-mmlab/mmdetection3dOpenMMLab's next-generation platform for general 3D object detection.★ 6.6kPythonApache-2.0Stale
716pixie-io/pixieInstant Kubernetes-Native Application Observability★ 6.5kC++Apache-2.0Active
717zhouhaoyi/Informer2020The GitHub repository for the paper "Informer" accepted by AAAI 2021.★ 6.5kPythonApache-2.0Stale
718PufferAI/PufferLibPuffing up reinforcement learning★ 6.5kCMITActive
719codertimo/BERT-pytorchGoogle AI 2018 BERT pytorch implementation★ 6.5kPythonApache-2.0Stale
720hongleizhang/RSPapersRSTutorials: A Curated List of Must-read Papers on Recommender System.★ 6.5k—MITSlowing
721therealXiaomanChu/ex-skill把前任蒸馏成 AI Skill，用ta的方式跟你说话。★ 6.5kPythonMITSlowing
722NLPchina/ansj_segansj分词.ict的真正java实现.分词效果速度都超过开源版的ict. 中文分词,人名识别,词性标注,用户自定义词典★ 6.5kJavaApache-2.0Stale
723nteract/papermill📚 Parameterize, execute, and analyze notebooks★ 6.5kPythonBSD-3-ClauseActive
724dair-ai/Mathematics-for-ML🧮 A collection of resources to learn mathematics for machine learning★ 6.5k——Stale
725open-mmlab/mmcvOpenMMLab Computer Vision Foundation★ 6.5kPythonApache-2.0Active
726HVision-NKU/StoryDiffusionAccepted as [NeurIPS 2024] Spotlight Presentation Paper★ 6.5kJupyter NotebookApache-2.0Stale
727google/automlGoogle Brain AutoML★ 6.5kJupyter NotebookApache-2.0Archived
728cleverhans-lab/cleverhansAn adversarial example library for constructing attacks, building defenses, and benchmarking both★ 6.5kJupyter NotebookMITStale
729kuangliu/pytorch-cifar95.47% on CIFAR10 with PyTorch★ 6.4kPythonMITStale
730flashlight/wav2letterFacebook AI Research's Automatic Speech Recognition Toolkit ★ 6.4kC++OtherActive
731jason718/awesome-self-supervised-learningA curated list of awesome self-supervised methods★ 6.4k——Slowing
732liuruoze/EasyPR(CGCSTCD'2017) An easy, flexible, and accurate plate recognition project for Chinese licenses in unconstrained situations. CGCSTCD = China ★ 6.4kC++Apache-2.0Stale
733microsoft/nlp-recipesNatural Language Processing Best Practices & Examples★ 6.4kPythonMITArchived
734argmaxinc/argmax-oss-swiftOn-device Speech AI for Apple Silicon★ 6.4kSwiftMITActive
735CodeWithCJ/SparkyFitnessSparkyFitness: Built for Families. Powered by AI. Track food, fitness, water, and health — together.★ 6.4kTypeScriptOtherActive
736mindee/doctrdocTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks powered by Deep Learning. Ongoing★ 6.4kPythonApache-2.0Active
737koharu-rs/koharuML-powered manga translator, written in Rust.★ 6.4kRustApache-2.0Active
738cocodataset/cocoapiCOCO API - Dataset @ http://cocodataset.org/ ★ 6.4kJupyter NotebookOtherStale
739aymericdamien/TopDeepLearningA list of popular github projects related to deep learning★ 6.4kPythonMITSlowing
740yl4579/StyleTTS2StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models★ 6.4kPythonMITStale
741spotify/pedalboard🎛 🔊 A Python library for audio.★ 6.4kC++GPL-3.0Active
742tensorflow/servingA flexible, high-performance serving system for machine learning models★ 6.4kC++Apache-2.0Active
743numenta/nupic-legacyNumenta Platform for Intelligent Computing is an implementation of Hierarchical Temporal Memory (HTM), a theory of intelligence based strict★ 6.3kPythonMITStale
744KevinMusgrave/pytorch-metric-learningThe easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.★ 6.3kPythonMITStale
745dragen1860/TensorFlow-2.x-TutorialsTensorFlow 2.x version's Tutorials and Examples, including CNN, RNN, GAN, Auto-Encoders, FasterRCNN, GPT, BERT examples, etc. TF 2.0版入门实例代码★ 6.3kJupyter Notebook—Stale
746tensorflow/docsTensorFlow documentation★ 6.3kJupyter NotebookApache-2.0Active
747rushter/data-science-blogsA curated list of data science blogs★ 6.3kPython—Stale
748aisingapore/TagUIFree RPA tool by AI Singapore★ 6.3kJavaScriptApache-2.0Active
749SmirkCao/LihangStatistical learning methods, 统计学习方法(第2版)[李航] [笔记, 代码, notebook, 参考文献, Errata, lihang]★ 6.3kPython—Stale
750pachyderm/pachydermData-Centric Pipelines and Data Versioning★ 6.3kGoApache-2.0Stale