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
351elder-plinius/G0DM0D3LIBERATED AI CHAT★ 11.8kTypeScriptAGPL-3.0Slowing
352hua1995116/awesome-ai-paintingAI绘画资料合集（包含国内外可使用平台、使用教程、参数教程、部署教程、业界新闻等等） Stable diffusion、AnimateDiff、Stable Cascade 、Stable SDXL Turbo★ 11.8k——Stale
353qubvel-org/segmentation_models.pytorchSemantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.★ 11.8kPythonMITActive
354NielsRogge/Transformers-TutorialsThis repository contains demos I made with the Transformers library by HuggingFace.★ 11.8kJupyter NotebookMITActive
355ctgk/PRMLPRML algorithms implemented in Python★ 11.7kJupyter NotebookMITStale
356milesial/Pytorch-UNetPyTorch implementation of the U-Net for image semantic segmentation with high quality images★ 11.7kPythonGPL-3.0Stale
357cleanlab/cleanlabCleanlab's open-source library is the standard data-centric AI package for data quality and machine learning with messy, real-world data and★ 11.7kPythonApache-2.0Slowing
358statsmodels/statsmodelsStatsmodels: statistical modeling and econometrics in Python★ 11.7kPythonBSD-3-ClauseActive
359rerun-io/rerunVisualize, query, and stream to train on multimodal robotics data.★ 11.6kRustApache-2.0Active
360facebookresearch/dinov3Reference PyTorch implementation and models for DINOv3★ 11.6kJupyter NotebookOtherSlowing
361open-jarvis/OpenJarvisPersonal AI, On Personal Devices★ 11.5kPythonApache-2.0Active
362kornia/kornia🐍 Geometric Computer Vision Library for Spatial AI★ 11.4kPythonApache-2.0Active
363data-privacy-stack/presidioAn open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. S★ 11.4kPythonMITActive
364hoya012/deep_learning_object_detectionA paper list of object detection using deep learning.★ 11.4kPython—Stale
365perspective-dev/perspectiveA data visualization and analytics component, especially well-suited for large and/or streaming datasets.★ 11.3kRustApache-2.0Active
366rhasspy/piperA fast, local neural text to speech system★ 11.3kC++MITArchived
367lucidrains/DALLE2-pytorchImplementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch★ 11.3kPythonMITStale
368wandb/wandbThe AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.★ 11.3kPythonMITActive
369kyutai-labs/moshiMoshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio c★ 11.3kPythonApache-2.0Active
370salesforce/LAVISLAVIS - A One-stop Library for Language-Vision Intelligence★ 11.3kJupyter NotebookBSD-3-ClauseArchived
371moonshine-ai/moonshineVery low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces★ 11.3kC++OtherActive
372karpathy/convnetjsDeep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.★ 11.2kJavaScriptMITStale
373voxel51/fiftyoneRefine high-quality datasets and visual AI models★ 11.2kTypeScriptApache-2.0Active
374NVlabs/stylegan2StyleGAN2 - Official TensorFlow Implementation★ 11.2kPythonOtherStale
375rushter/MLAlgorithmsMinimal and clean examples of machine learning algorithms implementations★ 11.2kPythonMITActive
376NVIDIA/FastPhotoStyleStyle transfer, deep learning, feature transform★ 11.2kPythonOtherStale
377PointCloudLibrary/pclPoint Cloud Library (PCL)★ 11.2kC++OtherActive
378apple/turicreateTuri Create simplifies the development of custom machine learning models.★ 11.2kC++BSD-3-ClauseArchived
379QuentinFuxa/WhisperLiveKitReal-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.★ 11.2kPythonApache-2.0Active
380triton-inference-server/serverThe Triton Inference Server provides an optimized cloud and edge inferencing solution. ★ 11.1kPythonBSD-3-ClauseActive
381vipstone/faceai一款入门级的人脸、视频、文字检测以及识别的项目.★ 11.1kPythonMITStale
382thu-ml/tianshouAn elegant PyTorch deep reinforcement learning library.★ 11kPythonMITSlowing
383alibaba/spring-ai-alibabaAgentic AI Framework for Java Developers★ 11kJavaApache-2.0Active
384openvinotoolkit/openvinoOpenVINO™ is an open source toolkit for optimizing and deploying AI inference★ 11kC++Apache-2.0Active
385Engineer1999/A-Curated-List-of-ML-System-Design-Case-StudiesThis repository contains a curated collection of 300+ case studies from over 80 companies, detailing practical applications and insights int★ 11k——Stale
386aws/amazon-sagemaker-examplesExample 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker. ★ 11kJupyter NotebookApache-2.0Active
387lengstrom/fast-style-transferTensorFlow CNN for fast style transfer ⚡🖥🎨🖼★ 11kPython—Stale
388bmild/nerfCode release for NeRF (Neural Radiance Fields)★ 11kJupyter NotebookMITStale
389google/dopamineDopamine is a research framework for fast prototyping of reinforcement learning algorithms. ★ 10.9kJupyter NotebookApache-2.0Slowing
390pymupdf/PyMuPDFPyMuPDF is a high performance Python library for data extraction, analysis, conversion & manipulation of PDF (and other) documents.★ 10.9kPythonAGPL-3.0Active
391magic-research/magic-animate[CVPR 2024] Official repository for "MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model"★ 10.9kPythonBSD-3-ClauseStale
392WasmEdge/WasmEdgeWasmEdge is a lightweight, high-performance, and extensible WebAssembly runtime for cloud native, edge, and decentralized applications. It p★ 10.8kC++Apache-2.0Active
393cumulo-autumn/StreamDiffusionStreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation★ 10.8kPythonApache-2.0Stale
394openai/DALL-EPyTorch package for the discrete VAE used for DALL·E.★ 10.8kPythonOtherArchived
395huggingface/ml-internArchived — ML Intern is no longer maintained. Continue with HuggingChat.★ 10.8kPythonApache-2.0Archived
396doccano/doccanoOpen source annotation tool for machine learning practitioners.★ 10.8kPythonMITSlowing
397autogluon/autogluonFast and Accurate ML in 3 Lines of Code★ 10.8kPythonApache-2.0Active
398codota/TabNineAI Code Completions★ 10.8kShellMITArchived
399esimov/caireContent aware image resize library★ 10.8kGoMITStale
400Acly/krita-ai-diffusionStreamlined interface for generating images with AI in Krita. Inpaint and outpaint with optional text prompt, no tweaking required.★ 10.7kPythonGPL-3.0Active