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
1401tensorflow/adanetFast and flexible AutoML with learning guarantees.★ 3.5kJupyter NotebookApache-2.0Archived
1402facebookresearch/PyTorch-BigGraphGenerate embeddings from large-scale graph-structured data.★ 3.5kPythonOtherArchived
1403HobbitLong/SupContrastPyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)★ 3.4kPythonBSD-2-ClauseStale
1404dair-ai/ML-Notebooks:fire: Machine Learning Notebooks★ 3.4kJupyter NotebookApache-2.0Stale
1405data-science-on-aws/data-science-on-awsAI and Machine Learning with Kubeflow, Amazon EKS, and SageMaker★ 3.4kJupyter NotebookApache-2.0Stale
1406aqlaboratory/openfoldTrainable, memory-efficient, and GPU-friendly PyTorch reproduction of AlphaFold 2★ 3.4kPythonApache-2.0Slowing
1407adamcohenhillel/ADeusAn open source AI wearable device that captures what you say and hear in the real world and then transcribes and stores it on your own serve★ 3.4kTypeScriptOtherStale
1408opengeos/geoaiGeoAI: Artificial Intelligence for Geospatial Data★ 3.4kPythonMITActive
1409clab/dynetDyNet: The Dynamic Neural Network Toolkit★ 3.4kC++Apache-2.0Stale
1410eragonruan/text-detection-ctpntext detection mainly based on ctpn model in tensorflow, id card detect, connectionist text proposal network★ 3.4kPythonMITStale
1411mani-skill/ManiSkillManipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark★ 3.4kPythonApache-2.0Active
1412ownthink/JiaguJiagu深度学习自然语言处理工具 知识图谱关系抽取 中文分词 词性标注 命名实体识别 情感分析 新词发现 关键词 文本摘要 文本聚类★ 3.4kPythonMITStale
1413waymo-research/waymo-open-datasetWaymo Open Dataset★ 3.4kPythonOtherSlowing
1414continue-revolution/sd-webui-animatediffAnimateDiff for AUTOMATIC1111 Stable Diffusion WebUI★ 3.4kPythonOtherStale
1415sail-sg/EditAnythingEdit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc. (ACM MM)★ 3.4kPythonApache-2.0Stale
1416chaofengc/IQA-PyTorch🔎 🖼️ 🔥PyTorch Toolbox for Image Quality Assessment, including PSNR, SSIM, LPIPS, FID, NIQE, NRQM(Ma), MUSIQ, TOPIQ, NIMA, DBCNN, BRISQUE, PI★ 3.4kPythonOtherActive
1417girls-in-ai/Girls-In-AI免费学代码系列：小白python入门、数据分析data analyst、机器学习machine learning、深度学习deep learning、kaggle实战★ 3.4kJupyter Notebook—Stale
1418makegirlsmoe/makegirlsmoe_webCreate Anime Characters with MakeGirlsMoe★ 3.4kJavaScriptOtherStale
1419GokuMohandas/mlops-courseLearn how to design, develop, deploy and iterate on production-grade ML applications.★ 3.4kJupyter NotebookMITStale
1420pytorch/ELFELF: a platform for game research with AlphaGoZero/AlphaZero reimplementation★ 3.4kC++OtherArchived
1421datawhalechina/learn-nlp-with-transformerswe want to create a repo to illustrate usage of transformers in chinese★ 3.4kShell—Stale
1422clovaai/CRAFT-pytorchOfficial implementation of Character Region Awareness for Text Detection (CRAFT)★ 3.4kPythonMITStale
1423xinghaochen/awesome-hand-pose-estimationAwesome work on hand pose estimation/tracking★ 3.4kPython—Slowing
1424facebookresearch/fairscalePyTorch extensions for high performance and large scale training.★ 3.4kPythonOtherStale
1425meetps/pytorch-semsegSemantic Segmentation Architectures Implemented in PyTorch★ 3.4kPythonMITStale
1426Visualize-ML/Book7_Visualizations-for-Machine-LearningBook_7_《机器学习》 | 鸢尾花书：从加减乘除到机器学习；欢迎批评指正★ 3.4kJupyter Notebook—Slowing
1427catalyst-team/catalystAccelerated deep learning R&D★ 3.4kPythonApache-2.0Slowing
1428ResearAI/DeepScientistNow, Stronger AI Pushes Frontiers, Stronger Our Shared Future.★ 3.4kTypeScriptApache-2.0Slowing
1429databricks/koalasKoalas: pandas API on Apache Spark★ 3.4kPythonApache-2.0Stale
1430libAudioFlux/audioFluxA library for audio and music analysis, feature extraction.★ 3.4kCMITSlowing
1431YangLing0818/Diffusion-Models-Papers-Survey-TaxonomyDiffusion model papers, survey, and taxonomy★ 3.4k——Stale
1432Peterande/D-FINED-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]★ 3.4kPythonApache-2.0Active
1433BandaiNamcoResearchInc/Bandai-Namco-Research-MotiondatasetThis repository provides motion datasets collected by Bandai Namco Research Inc★ 3.4kPython—Stale
1434NVIDIA/physicsnemoOpen-source deep-learning framework for building, training, and fine-tuning deep learning models using state-of-the-art Physics-ML methods★ 3.4kPythonApache-2.0Active
1435Kitt-AI/snowboyFuture versions with model training module will be maintained through a forked version here: https://github.com/seasalt-ai/snowboy★ 3.4kC++OtherStale
1436ahmetoner/whisper-asr-webserviceOpenAI Whisper ASR Webservice API★ 3.4kPythonMITActive
1437vladmandic/humanHuman: AI-powered 3D Face Detection & Rotation Tracking, Face Description & Recognition, Body Pose Tracking, 3D Hand & Finger Tracking, Iris★ 3.4kHTMLMITSlowing
1438Lagrange-Labs/deep-proveFramework to prove inference of ML models blazingly fast★ 3.4kRustOtherSlowing
1439hamuchiwa/AutoRCCarOpenCV Python Neural Network Autonomous RC Car★ 3.4kPythonBSD-2-ClauseStale
1440shankarpandala/lazypredictPython AutoML toolkit for benchmarking classification, regression, and time-series forecasting models, with GPU acceleration, MLflow trackin★ 3.4kPythonMITActive
1441tianzhi0549/FCOSFCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)★ 3.3kPythonOtherStale
1442xenova/whisper-webML-powered speech recognition directly in your browser★ 3.3kTypeScript—Stale
1443delta-io/delta-rsA native Rust library for Delta Lake, with bindings into Python★ 3.3kRustApache-2.0Active
1444NVIDIA-AI-IOT/jetbotAn educational AI robot based on NVIDIA Jetson Nano.★ 3.3kJupyter NotebookMITSlowing
1445tirthajyoti/Machine-Learning-with-PythonPractice and tutorial-style notebooks covering wide variety of machine learning techniques★ 3.3kJupyter NotebookBSD-2-ClauseStale
1446Farama-Foundation/HighwayEnvA collection of environments for autonomous driving and tactical decision-making tasks★ 3.3kPythonMITActive
1447tradytics/eitenStatistical and Algorithmic Investing Strategies for Everyone★ 3.3kPythonGPL-3.0Stale
1448root-project/rootThe official repository for ROOT: analyzing, storing and visualizing big data, scientifically★ 3.3kC++OtherActive
1449pytorch/glowCompiler for Neural Network hardware accelerators★ 3.3kC++Apache-2.0Archived
1450ayooshkathuria/pytorch-yolo-v3A PyTorch implementation of the YOLO v3 object detection algorithm★ 3.3kPython—Stale