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.

	Repository	Stars	Language	License	Activity
1451	PixArt-alpha/PixArt-alphaPixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis	★ 3.3k	Python	Apache-2.0	Stale
1452	resemble-ai/ResemblyzerA python package to analyze and compare voices with deep learning	★ 3.3k	Python	Apache-2.0	Stale
1453	open-mmlab/mmselfsupOpenMMLab Self-Supervised Learning Toolbox and Benchmark	★ 3.3k	Python	Apache-2.0	Stale
1454	tensorforce/tensorforceTensorforce: a TensorFlow library for applied reinforcement learning	★ 3.3k	Python	Apache-2.0	Active
1455	op7418/NanoBanana-PPT-SkillsNanoBanana PPT Skills 基于 AI 自动生成高质量 PPT 图片和视频的强大工具，支持智能转场和交互式播放	★ 3.3k	Python	—	Slowing
1456	mljar/mljar-supervisedPython package for AutoML on Tabular Data with Feature Engineering, Hyper-Parameters Tuning, Explanations and Automatic Documentation	★ 3.3k	Python	MIT	Active
1457	arielf/weight-lossMachine Learning meets ketosis: how to effectively lose weight	★ 3.3k	Python	Other	Stale
1458	google-deepmind/dm-haikuJAX-based neural network library	★ 3.3k	Python	Apache-2.0	Active
1459	rsxdalv/TTS-WebUIA single Gradio + React WebUI with extensions for ACE-Step, OmniVoice, Kimi Audio, Piper TTS, GPT-SoVITS, CosyVoice, XTTSv2, DIA, Kokoro, Op	★ 3.3k	TypeScript	MIT	Active
1460	NVIDIA/flownet2-pytorchPytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks	★ 3.3k	Python	Other	Slowing
1461	lucidrains/musiclm-pytorchImplementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch	★ 3.3k	Python	MIT	Stale
1462	microsoft/ResearchStudioResearchStudio: Our AI co-author, from research problem to final publication.	★ 3.3k	Python	MIT	Active
1463	tkarim45/Beginner-Data-Science-ProjectsThis repository is a curated collection of hands-on data science projects tailored for beginners. Whether you're just starting your journey	★ 3.3k	Jupyter Notebook	MIT	Active
1464	teddylee777/machine-learning머신러닝 입문자 혹은 스터디를 준비하시는 분들에게 도움이 되고자 만든 repository입니다. (This repository is intented for helping whom are interested in machine learning study	★ 3.3k	Jupyter Notebook	—	Stale
1465	Sakura-gh/ML-notesnotes about machine learning	★ 3.3k	HTML	GPL-2.0	Stale
1466	pydata/pandas-datareaderExtract data from a wide range of Internet sources into a pandas DataFrame.	★ 3.3k	Python	Other	Active
1467	breezedeus/Pix2TextAn Open-Source Python3 tool with SMALL models for recognizing layouts, tables, math formulas (LaTeX), and text in images, converting them in	★ 3.3k	Jupyter Notebook	MIT	Active
1468	deepdoctection/deepdoctectionA Repo For Document AI	★ 3.3k	Python	Apache-2.0	Active
1469	MAIF/shapash🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models	★ 3.3k	Jupyter Notebook	Apache-2.0	Active
1470	Pointcept/PointceptPointcept: Perceive the world with sparse points, a codebase for point cloud perception research. Latest works: Utonia (ICML'26), Concerto (	★ 3.3k	Python	MIT	Active
1471	zhanghang1989/ResNeStResNeSt: Split-Attention Networks	★ 3.3k	Python	Apache-2.0	Active
1472	lakesoul-io/LakeSoulLakeSoul is an end-to-end, realtime cloud-native Lakehouse framework for fast data ingestion, concurrent updates, incremental analytics, mul	★ 3.3k	Rust	Apache-2.0	Active
1473	adamerose/PandasGUIA GUI for Pandas DataFrames	★ 3.3k	Python	MIT-0	Stale
1474	google/braxMassively parallel rigidbody physics simulation on accelerator hardware.	★ 3.2k	Jupyter Notebook	Apache-2.0	Active
1475	LeelaChessZero/lc0Open source neural network chess engine with GPU acceleration and broad hardware support.	★ 3.2k	C++	GPL-3.0	Active
1476	Nerogar/OneTrainerOneTrainer is a one-stop solution for all your Diffusion training needs.	★ 3.2k	Python	AGPL-3.0	Active
1477	determined-ai/determinedDetermined is an open-source machine learning platform that simplifies distributed training, hyperparameter tuning, experiment tracking, and	★ 3.2k	Go	Apache-2.0	Stale
1478	oslook/cursor-ai-downloadsAll Cursor AI's official download links for both the latest and older versions, making it easy for you to update, downgrade, and choose any	★ 3.2k	TypeScript	MIT	Active
1479	MisoLabsAI/MisoTTSMiso TTS is an 8 billion, highly emotive text-to-speech model	★ 3.2k	Python	Other	Slowing
1480	prs-eth/Marigold[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation	★ 3.2k	Python	Apache-2.0	Active
1481	onnx/onnx-tensorrtONNX-TensorRT: TensorRT backend for ONNX	★ 3.2k	C++	Apache-2.0	Active
1482	seungeunrho/minimalRLImplementations of basic RL algorithms with minimal lines of codes! (pytorch based)	★ 3.2k	Python	MIT	Stale
1483	Jittor/jittorJittor is a high-performance deep learning framework based on JIT compiling and meta-operators.	★ 3.2k	Python	Apache-2.0	Active
1484	google-agentic-commerce/AP2Building a Secure and Interoperable Future for AI-Driven Payments.	★ 3.2k	Python	Apache-2.0	Slowing
1485	mit-han-lab/bevfusion[ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation	★ 3.2k	Python	Apache-2.0	Archived
1486	DamRsn/NeuralNoteAudio Plugin for Audio to MIDI transcription using deep learning.	★ 3.2k	C++	Apache-2.0	Active
1487	openvinotoolkit/openvino_notebooks📚 Jupyter notebook tutorials for OpenVINO™	★ 3.2k	Jupyter Notebook	Apache-2.0	Active
1488	patrickloeber/ml-study-planThe Ultimate FREE Machine Learning Study Plan	★ 3.2k	—	—	Stale
1489	mujocolab/mjlabIsaac Lab API, powered by MuJoCo-Warp, for RL and robotics research	★ 3.2k	Python	Apache-2.0	Active
1490	echohive42/AI-reads-books-page-by-pageAI reads books: Page-by-Page PDF Knowledge Extractor & Summarizer. script performs an intelligent page-by-page analysis of PDF books, method	★ 3.2k	Python	MIT	Slowing
1491	rmurai0610/MASt3R-SLAM[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors	★ 3.2k	Python	Other	Slowing
1492	mkocabas/VIBEOfficial implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"	★ 3.2k	Python	Other	Stale
1493	kerlomz/captcha_trainer[验证码识别-训练] This project is based on CNN/ResNet/DenseNet+GRU/LSTM+CTC/CrossEntropy to realize verification code identification. This project	★ 3.2k	Python	Apache-2.0	Slowing
1494	JoePenna/Dreambooth-Stable-DiffusionImplementation of Dreambooth (https://arxiv.org/abs/2208.12242) by way of Textual Inversion (https://arxiv.org/abs/2208.01618) for Stable Di	★ 3.2k	Jupyter Notebook	MIT	Stale
1495	Simple-XX/SimpleKernelInterface-Driven OS Kernel for AI-Assisted Learning \| 面向 AI 的操作系统学习项目	★ 3.2k	C++	Other	Slowing
1496	Djdefrag/QualityScalerQualityScaler - image/video AI upscaler app	★ 3.2k	Python	MIT	Active
1497	tomgoldstein/loss-landscapeCode for visualizing the loss landscape of neural nets	★ 3.2k	Python	MIT	Stale
1498	webdataset/webdatasetA high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.	★ 3.2k	Python	BSD-3-Clause	Slowing
1499	matthartman/ghost-pepper100% private on-device voice models for speech-to-text and meeting transcription on macOS	★ 3.2k	Swift	—	Active
1500	liyown/ai-trend-publishTrendPublish: 全自动 AI 内容生成与发布系统 \| 微信公众号自动化 \| 多源数据抓取 (Twitter/X、网站) \| DeepseekAI、千问、讯飞模型 \| 智能内容分析排序 \| 定时发布 \| 多模板支持 \| Node.js \| TypeScript \| AI	★ 3.2k	TypeScript	MIT	Active