Sealbook
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
1501ddz16/TSFpaperThis repository contains a reading list of papers on Time Series Forecasting/Prediction (TSF) and Spatio-Temporal Forecasting/Prediction (ST★ 3.2k——Active
1502textlint/textlinttextlint is the pluggable linter for natural language text.★ 3.2kTypeScriptMITActive
1503hankcs/pyhanlp中文分词★ 3.2kPythonApache-2.0Stale
1504xiamuceer-j/MuMuAINovel一款基于 AI 的智能小说创作助手，帮助你轻松创作精彩故事★ 3.2kPythonGPL-3.0Active
1505megvii-research/NAFNetThe state-of-the-art image restoration model without nonlinear activation functions.★ 3.2kPythonOtherStale
1506ARM-software/ComputeLibraryThe Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.★ 3.2kC++—Active
1507dotnet/interactive.NET Interactive combines the power of .NET with many other languages to create notebooks, REPLs, and embedded coding experiences. Share cod★ 3.2kC#MITArchived
1508VinsonLaro/stable-diffusion-webui-chinesestable-diffusion-webui 的汉化扩展★ 3.2k—GPL-3.0Stale
1509tinyvision/DAMO-YOLODAMO-YOLO: a fast and accurate object detection method with some new techs, including NAS backbones, efficient RepGFPN, ZeroHead, AlignedOTA★ 3.2kPythonApache-2.0Stale
1510imbue-bit/AlphaGPT基于深度强化学习的开源自动因子工厂。★ 3.2kPythonApache-2.0Slowing
1511higgsfield/RL-AdventurePytorch Implementation of DQN / DDQN / Prioritized replay/ noisy networks/ distributional values/ Rainbow/ hierarchical RL★ 3.2kJupyter Notebook—Stale
1512tslearn-team/tslearnThe machine learning toolkit for time series analysis in Python★ 3.2kPythonBSD-2-ClauseActive
1513yusugomori/DeepLearningDeep Learning (Python, C, C++, Java, Scala, Go)★ 3.2kJavaMITStale
1514astorfi/Deep-Learning-Roadmap:satellite: Organized Resources for Deep Learning Researchers and Developers★ 3.2kPythonMITStale
1515sbrugman/deep-learning-papersPapers about deep learning ordered by task, date. Current state-of-the-art papers are labelled.★ 3.2k——Archived
1516datascale-ai/opentalkingOpenTalking: An industrial-grade open-source AI digital human framework that supports real-time conversation, private deployment, and plugga★ 3.2kPythonApache-2.0Active
1517kzbkzb/Python-AI深度学习100例、深度学习DL、图片分类、目标识别、目标检测、自然语言处理nlp、文本分类、TensorFlow、PyTorch★ 3.2kJupyter Notebook—Stale
1518louisfb01/best_AI_papers_2022A curated list of the latest breakthroughs in AI (in 2022) by release date with a clear video explanation, link to a more in-depth article, ★ 3.2k—MITStale
1519automeris-io/WebPlotDigitizerComputer vision assisted tool to extract numerical data from plot images.★ 3.2kJavaScriptAGPL-3.0Active
1520stemrollerapp/stemrollerIsolate vocals, drums, bass, and other instrumental stems from any song★ 3.2kSvelteOtherSlowing
1521adambielski/siamese-tripletSiamese and triplet networks with online pair/triplet mining in PyTorch★ 3.2kPythonBSD-3-ClauseStale
1522netptop/siteproxyreverse proxy, online proxy, 反向代理,免翻墙访问Youtube/twitter/Google, 支持github和telegram web登录(请注意不要通过不信任的代理进行登录)。支持DuckDuckGo AI Chat★ 3.2kJavaScriptMITActive
1523jettify/pytorch-optimizertorch-optimizer -- collection of optimizers for Pytorch★ 3.2kPythonApache-2.0Stale
1524SciML/DifferentialEquations.jlMulti-language suite for high-performance solvers of differential equations and scientific machine learning (SciML) components. Ordinary dif★ 3.2kJuliaOtherActive
1525tensorflow/skflowSimplified interface for TensorFlow (mimicking Scikit Learn) for Deep Learning★ 3.2kPythonApache-2.0Archived
1526nesaorg/nesaRun AI models end-to-end encrypted.★ 3.2kPython—Stale
1527facebookresearch/habitat-labA modular high-level library to train embodied AI agents across a variety of tasks and environments.★ 3.2kPythonMITSlowing
1528parrt/dtreevizA python library for decision tree visualization and model interpretation.★ 3.2kJupyter NotebookMITSlowing
1529SegFault42/HeliosGen🏆 Self Hosted Gen AI desktop app. Free alternative to Higgsfield, OpenArt, Freepik....★ 3.2kTypeScript—Active
1530geohot/minikeyvalueA distributed key value store in under 1000 lines. Used in production at comma.ai★ 3.2kGoMITStale
1531scikit-learn-contrib/hdbscanA high performance implementation of HDBSCAN clustering.★ 3.2kJupyter NotebookBSD-3-ClauseActive
1532neuralmagic/deepsparseSparsity-aware deep learning inference runtime for CPUs★ 3.2kPythonOtherArchived
1533cleardusk/3DDFA_V2The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.★ 3.2kPythonMITStale
1534ali-vilab/VGenOfficial repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models★ 3.2kPython—Stale
1535open-mmlab/mmdeployOpenMMLab Model Deployment Framework★ 3.1kPythonApache-2.0Stale
1536migueldeicaza/TensorFlowSharpTensorFlow API for .NET languages★ 3.1kC#MITArchived
1537elevenlabs/elevenlabs-pythonThe official Python SDK for the ElevenLabs API.★ 3.1kPythonMITActive
1538NeuromatchAcademy/course-contentNMA Computational Neuroscience course★ 3.1kJupyter NotebookCC-BY-4.0Active
1539microsoft/torchscaleFoundation Architecture for (M)LLMs★ 3.1kPythonMITStale
1540nidhaloff/igela delightful machine learning tool that allows you to train, test, and use models without writing code★ 3.1kPythonMITSlowing
1541FudanNLP/fastNLPfastNLP: A Modularized and Extensible NLP Framework. Currently still in incubation.★ 3.1kPythonApache-2.0Stale
1542spark-notebook/spark-notebookInteractive and Reactive Data Science using Scala and Spark.★ 3.1kJavaScriptApache-2.0Stale
1543OpenDCAI/DataFlex[NeurIPS 2026] DataFlex: A Unified Benchmark and Evaluation Platform for Data-Centric Training of Large Language Models★ 3.1kPythonApache-2.0Active
1544ml-tooling/opyrator🪄 Turns your machine learning code into microservices with web API, interactive GUI, and more.★ 3.1kPythonMITActive
1545handong1587/handong1587.github.io★ 3.1kCSSMITStale
1546open-mmlab/mmskeletonA OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.★ 3.1kPythonApache-2.0Stale
1547fbdesignpro/sweetvizVisualize and compare datasets, target values and associations, with one line of code.★ 3.1kPythonMITSlowing
1548bfortuner/ml-glossaryMachine learning glossary★ 3.1kPythonMITStale
1549chenyme/Chenyme-AAVT这是一个全自动（音频）视频翻译项目。利用Whisper识别声音，AI大模型翻译字幕，最后合并字幕视频，生成翻译后的视频。★ 3.1kPythonMITArchived
1550google-deepmind/trflTensorFlow Reinforcement Learning★ 3.1kPythonApache-2.0Stale