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
2751WXinlong/SOLOSOLO and SOLOv2 for instance segmentation, ECCV 2020 & NeurIPS 2020.★ 1.8kPythonOtherStale
2752microsoft/mupmaximal update parametrization (µP)★ 1.8kJupyter NotebookMITArchived
2753firmai/machine-learning-asset-managementMachine Learning in Asset Management (by @firmai)★ 1.8kJupyter Notebook—Stale
2754datastax/jvectorJVector: the most advanced embedded vector search engine★ 1.8kJavaApache-2.0Active
2755apachecn/.githubApacheCN 开源组织：公告、介绍、成员、活动、交流方式★ 1.8kCSS—Slowing
2756decisionintelligence/TFB[PVLDB 2024 Best Paper Nomination] TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods★ 1.8kShellMITActive
2757BeaconBay/ckLocal first semantic and hybrid BM25 grep / search tool for use by AI and humans! ★ 1.8kRustApache-2.0Active
2758MaliosDark/wifi-3d-fusionWiFi-3D-Fusion is an open-source research project that leverages WiFi CSI signals and deep learning to estimate 3D human pose, fusing wirele★ 1.8kPythonOtherStale
2759linjinjin123/awesome-AIOpsAIOps学习资料汇总，欢迎一起补全这个仓库，欢迎star★ 1.8k——Stale
2760deepset-ai/FARM:house_with_garden: Fast & easy transfer learning for NLP. Harvesting language models for the industry. Focus on Question Answering.★ 1.8kPythonApache-2.0Archived
2761Lightning-Universe/lightning-boltsToolbox of models, callbacks, and datasets for AI/ML researchers.★ 1.8kPythonApache-2.0Archived
2762protectai/ai-exploitsA collection of real world AI/ML exploits for responsibly disclosed vulnerabilities ★ 1.8kPythonOtherStale
2763VertaAI/modeldbOpen Source ML Model Versioning, Metadata, and Experiment Management★ 1.8kJavaApache-2.0Stale
2764mahmoodlab/CLAMOpen source tools for computational pathology - Nature BME★ 1.8kPythonGPL-3.0Stale
2765ThioJoe/Auto-Synced-Translated-DubsAutomatically translates the text of a video based on a subtitle file, and then uses AI voice services to create a new dubbed & translated a★ 1.8kPythonAGPL-3.0Slowing
2766antirez/voxtral.cPure C inference of Mistral Voxtral Realtime 4B speech to text model★ 1.8kCMITSlowing
2767lit26/finvizfinanceFinviz analysis python library.★ 1.7kPythonMITActive
2768libfann/fannOfficial github repository for Fast Artificial Neural Network Library (FANN)★ 1.7kC++LGPL-2.1Slowing
2769rusty1s/pytorch_scatterPyTorch Extension Library of Optimized Scatter Operations★ 1.7kPythonMITSlowing
2770justmarkham/scikit-learn-tips:robot::zap: 50 scikit-learn tips★ 1.7kJupyter Notebook—Stale
2771TencentARC/BrushNet[ECCV 2024] The official implementation of paper "BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion"★ 1.7kPythonOtherStale
2772dog-qiuqiu/MobileNet-YoloMobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops 420KB:fire::fire::fire:★ 1.7kCOtherStale
2773tkipf/gaeImplementation of Graph Auto-Encoders in TensorFlow★ 1.7kPythonMITStale
2774facebookresearch/multimodalTorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.★ 1.7kPythonBSD-3-ClauseActive
2775elder-plinius/V3SP3RAI Flipper control★ 1.7kJavaAGPL-3.0Slowing
277614790897/paper-ai搜索真实文献并生成引用对应文献的AI论文★ 1.7kTypeScriptMITSlowing
2777googlecreativelab/teachablemachine-communityExample code snippets and machine learning code for Teachable Machine★ 1.7kTypeScriptApache-2.0Slowing
2778natethegreate/hent-AIAutomation of censor bar detection★ 1.7kPythonMITStale
2779cszn/DnCNNBeyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (TIP, 2017)★ 1.7kMATLAB—Stale
2780stas00/the-art-of-debuggingThe Art of Debugging Open Book★ 1.7kPythonCC-BY-SA-4.0Active
2781birdnet-team/BirdNET-AnalyzerBirdNET analyzer for scientific audio data processing.★ 1.7kPythonMITActive
2782bearpaw/pytorch-classificationClassification with PyTorch.★ 1.7kPythonMITStale
2783jupyterhub/repo2dockerTurn repositories into Jupyter-enabled Docker images★ 1.7kPythonBSD-3-ClauseActive
2784NVlabs/PWC-NetPWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume, CVPR 2018 (Oral)★ 1.7kPythonOtherStale
2785ranahanocka/MeshCNNConvolutional Neural Network for 3D meshes in PyTorch★ 1.7kPythonMITStale
2786Xiaojiu-z/EasyControlImplementation of "EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer"(ICCV2025)★ 1.7kPythonApache-2.0Stale
2787alkaline-ml/pmdarimaA statistical library designed to fill the void in Python's time series analysis capabilities, including the equivalent of R's auto.arima fu★ 1.7kPythonMITActive
2788egoist/sitefetchFetch an entire site and save it as a text file (to be used with AI models).★ 1.7kTypeScriptMITStale
2789zijundeng/pytorch-semantic-segmentationPyTorch for Semantic Segmentation★ 1.7kPythonMITStale
2790narwhals-dev/narwhalsLightweight and extensible compatibility layer between dataframe libraries!★ 1.7kPythonMITActive
2791opendatacam/opendatacamAn open source tool to quantify the world★ 1.7kJavaScriptMITSlowing
2792justLV/onju-voiceA hackable AI home assistant platform★ 1.7kJupyter NotebookMITSlowing
2793openai/requests-for-researchA living collection of deep learning problems★ 1.7kHTML—Archived
2794Roshanson/TextInfoExp自然语言处理实验（sougou数据集），TF-IDF，文本分类、聚类、词向量、情感识别、关系抽取等★ 1.7kPython—Stale
2795experiencor/keras-yolo2Easy training on custom dataset. Various backends (MobileNet and SqueezeNet) supported. A YOLO demo to detect raccoon run entirely in brower★ 1.7kJupyter NotebookMITStale
2796njvisionpower/Safety-Helmet-Wearing-DatasetSafety helmet wearing detect dataset, with pretrained model★ 1.7kPythonMITStale
2797Qihoo360/hboxAI on Hadoop★ 1.7kJavaApache-2.0Stale
2798NVIDIA/Cosmos-TokenizerA suite of image and video neural tokenizers★ 1.7kJupyter NotebookApache-2.0Archived
2799google-research/torchsdeDifferentiable SDE solvers with GPU support and efficient sensitivity analysis. ★ 1.7kPythonApache-2.0Archived
2800sihyun-yu/REPA[ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think★ 1.7kPythonMITStale