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
1351foolwood/SiamMask[CVPR19/TPAMI23] SiamMask: A Framework for Fast Online Object Tracking and Segmentation★ 3.6kPythonMITStale
1352guandeh17/Self-ForcingOfficial codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)★ 3.6kPythonApache-2.0Stale
1353unitycatalog/unitycatalogOpen, Multi-modal Catalog for Data & AI★ 3.6kJavaApache-2.0Active
1354ml-tooling/ml-workspace🛠 All-in-one web-based IDE specialized for machine learning and data science.★ 3.5kJupyter NotebookApache-2.0Stale
1355pavelgonchar/colornetNeural Network to colorize grayscale images★ 3.5kPython—Stale
1356jmschrei/pomegranateFast, flexible and easy to use probabilistic modelling in Python.★ 3.5kPythonMITStale
1357fastai/fastpagesAn easy to use blogging platform, with enhanced support for Jupyter Notebooks.★ 3.5kJupyter NotebookApache-2.0Archived
1358Anttwo/SuGaR[CVPR 2024] Official PyTorch implementation of SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quali★ 3.5kC++OtherStale
1359Farama-Foundation/PettingZooA standard API for multi-agent reinforcement learning environments, with popular reference environments and related utilities★ 3.5kPythonMITActive
1360tensorflow/hubA library for transfer learning by reusing parts of TensorFlow models.★ 3.5kPythonApache-2.0Stale
1361Avik-Jain/100-Days-of-ML-Code-Chinese-VersionChinese Translation for Machine Learning Infographics★ 3.5kPythonMITStale
1362cszn/KAIRImage Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR★ 3.5kPythonMITStale
1363autorope/donkeycarOpen source hardware and software platform to build a small scale self driving car.★ 3.5kPythonMITActive
1364NELSONZHAO/zhihuThis repo contains the source code in my personal column (https://zhuanlan.zhihu.com/zhaoyeyu), implemented using Python 3.6. Including Natu★ 3.5kJupyter Notebook—Stale
1365helblazer811/ManimMLManimML is a project focused on providing animations and visualizations of common machine learning concepts with the Manim Community Library★ 3.5kPythonMITStale
1366visionml/pytrackingVisual tracking library based on PyTorch.★ 3.5kPythonGPL-3.0Stale
1367apache/incubator-kie-optaplannerOplaPlanner has moved to https://github.com/apache/incubator-kie-drools. This repository is archived. OptaPlanner is an AI constraint solver★ 3.5kJavaApache-2.0Archived
1368alicevision/AliceVision3D Computer Vision Framework★ 3.5kC++OtherActive
1369podgorskiy/ALAE[CVPR2020] Adversarial Latent Autoencoders ★ 3.5kPython—Stale
1370zjhellofss/KuiperInfer校招、秋招、春招、实习好项目！带你从零实现一个高性能的深度学习推理库，支持大模型 llama2 、Unet、Yolov5、Resnet等模型的推理。Implement a high-performance deep learning inference library step ★ 3.5kC++MITStale
1371huggingface/optimum🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tool★ 3.5kPythonApache-2.0Active
1372szagoruyko/pytorchvizA small package to create visualizations of PyTorch execution graphs★ 3.5kJupyter NotebookMITStale
1373ethen8181/machine-learning:earth_americas: machine learning tutorials (mainly in Python3) ★ 3.5kHTMLMITActive
1374PennyLaneAI/pennylanePennyLane is an open-source quantum software platform for quantum computing, quantum machine learning, and quantum chemistry. Create meaning★ 3.5kPythonApache-2.0Active
1375awentzonline/image-analogiesGenerate image analogies using neural matching and blending.★ 3.5kPythonMITStale
1376google-ai-edge/LiteRTLiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via effi★ 3.5kC++Apache-2.0Active
1377continue-revolution/sd-webui-segment-anythingSegment Anything for Stable Diffusion WebUI★ 3.5kPython—Stale
1378vietanhdev/anylabelingEffortless AI-assisted data labeling with AI support from YOLO, Segment Anything (SAM+SAM2/2.1+SAM3), MobileSAM!!★ 3.5kPythonGPL-3.0Active
1379sentient-agi/OML-1.0-FingerprintingOML 1.0 via Fingerprinting: Open, Monetizable, and Loyal AI★ 3.5kPythonApache-2.0Stale
1380antonycourtney/tadA desktop application for viewing and analyzing tabular data★ 3.5kTypeScriptMITStale
1381fastai/course-nlpA Code-First Introduction to NLP course★ 3.5kJupyter Notebook—Stale
1382matheusfacure/python-causality-handbookCausal Inference for the Brave and True. A light-hearted yet rigorous approach to learning about impact estimation and causality. ★ 3.5kJupyter NotebookMITActive
1383kuprel/min-dallemin(DALL·E) is a fast, minimal port of DALL·E Mini to PyTorch★ 3.5kPythonMITStale
1384guillaume-chevalier/LSTM-Human-Activity-RecognitionHuman Activity Recognition example using TensorFlow on smartphone sensors dataset and an LSTM RNN. Classifying the type of movement amongst ★ 3.5kJupyter NotebookMITStale
1385POSTECH-CVLab/PyTorch-StudioGANStudioGAN is a Pytorch library providing implementations of representative Generative Adversarial Networks (GANs) for conditional/unconditio★ 3.5kPythonOtherStale
1386bighuang624/AI-research-tools:hammer:AI 方向好用的科研工具★ 3.5k—MITStale
1387aim-uofa/AdelaiDetAdelaiDet is an open source toolbox for multiple instance-level detection and recognition tasks.★ 3.5kPythonOtherStale
1388open-mmlab/mmyoloOpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.★ 3.5kPythonGPL-3.0Stale
1389microsoft/tensorwatchDebugging, monitoring and visualization for Python Machine Learning and Data Science★ 3.5kJupyter NotebookMITSlowing
1390QData/TextAttackTextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/★ 3.5kPythonMITActive
1391JiahuiYu/generative_inpaintingDeepFill v1/v2 with Contextual Attention and Gated Convolution, CVPR 2018, and ICCV 2019 Oral★ 3.5kPythonOtherStale
1392shenweichen/DeepCTR-Torch【PyTorch】Easy-to-use,Modular and Extendible package of deep-learning based CTR models.★ 3.5kPythonApache-2.0Slowing
1393TJU-DRL-LAB/AI-OptimizerThe next generation deep reinforcement learning tookit★ 3.5kPython—Stale
1394tensorlayer/SRGANPhoto-Realistic Single Image Super-Resolution Using a Generative Adversarial Network★ 3.5kPython—Stale
1395richzhang/colorizationAutomatic colorization using deep neural networks. "Colorful Image Colorization." In ECCV, 2016.★ 3.5kPythonBSD-2-ClauseStale
1396PaddlePaddle/PARLA high-performance distributed training framework for Reinforcement Learning ★ 3.5kPythonApache-2.0Active
1397Azure-Samples/cognitive-services-speech-sdkSample code for the Microsoft Cognitive Services Speech SDK★ 3.5kC#MITActive
1398lakehq/sailDrop-in Apache Spark replacement written in Rust, unifying batch processing, stream processing, and compute-intensive AI workloads.★ 3.5kRustApache-2.0Active
1399ShangtongZhang/DeepRLModularized Implementation of Deep RL Algorithms in PyTorch★ 3.5kPythonMITStale
1400XinJingHao/DRL-PytorchClean, Robust, and Unified PyTorch implementation of popular Deep Reinforcement Learning (DRL) algorithms (Q-learning, Duel DDQN, PER, C51, ★ 3.5kPython—Stale