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
4001Kaixhin/grokking-pytorchThe Hitchiker's Guide to PyTorch★ 1.2k—MITStale
4002kexinhuang12345/DeepPurposeA Deep Learning Toolkit for DTI, Drug Property, PPI, DDI, Protein Function Prediction (Bioinformatics)★ 1.2kJupyter NotebookBSD-3-ClauseStale
4003Oxen-AI/OxenLightning fast data version control system for large repositories of data. Feels like git, pushes and pulls like oxen.★ 1.2kRustApache-2.0Active
4004DeepRec-AI/DeepRecDeepRec is a high-performance recommendation deep learning framework based on TensorFlow. It is hosted in incubation in LF AI & Data Foundat★ 1.2kC++Apache-2.0Stale
4005NVIDIA-AI-IOT/jetracerAn autonomous AI racecar using NVIDIA Jetson Nano★ 1.2kJupyter NotebookMITStale
4006kennethleungty/Neural-Network-Architecture-DiagramsDiagrams for visualizing neural network architecture★ 1.2k—MITStale
4007a-r-j/grapheinProtein Graph Library★ 1.2kJupyter NotebookMITActive
4008paralleldrive/ritewaySimple, readable, helpful unit tests. Optimized for AI Driven Development.★ 1.2kJavaScriptMITActive
4009huggingface/hmtl🌊HMTL: Hierarchical Multi-Task Learning - A State-of-the-Art neural network model for several NLP tasks based on PyTorch and AllenNLP★ 1.2kPythonMITStale
4010VITA-Group/DeblurGANv2[ICCV 2019] "DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better" by Orest Kupyn, Tetiana Martyniuk, Junru Wu, Zhangyang Wang★ 1.2kPythonOtherStale
4011aitorzip/DeepGTAVA plugin for GTAV that transforms it into a vision-based self-driving car research environment.★ 1.2kC++GPL-3.0Stale
4012philipperemy/yolo-9000YOLO9000: Better, Faster, Stronger - Real-Time Object Detection. 9000 classes!★ 1.2k—Apache-2.0Stale
4013ScholarXIV/OpenScholarXIVOpenScholarXIV is an open-source, aesthetic, minimal and AI powered app that allows users to search, read, bookmark, share, download and vie★ 1.2kDartGPL-3.0Active
4014cloudflare/ai★ 1.2kTypeScriptMITActive
4015numerai/example-scriptsA collection of scripts and notebooks to help you get started quickly.★ 1.2kJupyter NotebookMITActive
4016kkyon/botflowPython Fast Dataflow programming framework for Data pipeline work( Web Crawler,Machine Learning,Quantitative Trading.etc)★ 1.2kPythonOtherSlowing
4017shallowdream204/DreamClear[NeurIPS 2024] DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation★ 1.2kPythonApache-2.0Stale
4018flow-project/flowComputational framework for reinforcement learning in traffic control★ 1.2kPythonMITStale
4019alexattia/Data-Science-ProjectsDataScience projects for learning : Kaggle challenges, Object Recognition, Parsing, etc.★ 1.2kJupyter Notebook—Stale
4020SpencerPark/IJavaA Jupyter kernel for executing Java code.★ 1.2kJavaMITStale
4021helblazer811/Diffusion-ExplorerInteractive visualizations of the geometric intuition behind diffusion models.★ 1.2kJavaScript—Active
4022markdtw/awesome-architecture-searchA curated list of awesome architecture search resources★ 1.2k——Stale
4023RubensZimbres/Repo-2017My first Python repo with codes in Machine Learning, NLP and Deep Learning with Keras and Theano★ 1.2kPython—Stale
4024peng-zhihui/A-Eyea spuer mini AI-camera project★ 1.2kC—Stale
4025hikariming/chat-dataset-baseline人工精调的中文对话数据集和一段chatglm的微调代码★ 1.2kJupyter Notebook—Stale
4026jankrepl/deepdowPortfolio optimization with deep learning.★ 1.2kPythonApache-2.0Stale
4027custom-components/pyscriptPyscript adds rich Python scripting to HASS★ 1.2kPythonApache-2.0Active
4028lightaime/deep_gcns_torchPytorch Repo for DeepGCNs (ICCV'2019 Oral, TPAMI'2021), DeeperGCN (arXiv'2020) and GNN1000(ICML'2021): https://www.deepgcns.org★ 1.2kPythonMITStale
4029hse-aml/natural-language-processingResources for "Natural Language Processing" Coursera course.★ 1.2kJupyter Notebook—Stale
4030elliottwu/unsup3d(CVPR'20 Oral) Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild★ 1.2kPythonMITStale
4031THUYimingLi/backdoor-learning-resourcesA list of backdoor learning resources★ 1.2k—MITStale
4032functime-org/functimeTime-series machine learning at scale. Built with Polars for embarrassingly parallel feature extraction and forecasts on panel data.★ 1.2kPythonApache-2.0Slowing
4033chakki-works/seqevalA Python framework for sequence labeling evaluation(named-entity recognition, pos tagging, etc...)★ 1.2kPythonMITStale
4034lartpang/PyTorchTricksSome tricks of pytorch... :star:★ 1.2k——Stale
4035vanhuyz/CycleGAN-TensorFlowAn implementation of CycleGan using TensorFlow★ 1.2kPythonMITStale
4036kavgan/nlp-in-practiceStarter code to solve real world text data problems. Includes: Gensim Word2Vec, phrase embeddings, Text Classification with Logistic Regress★ 1.2kJupyter Notebook—Stale
4037SHI-Labs/Neighborhood-Attention-TransformerNeighborhood Attention Transformer, arxiv 2022 / CVPR 2023. Dilated Neighborhood Attention Transformer, arxiv 2022★ 1.2kPythonMITStale
4038meta-pytorch/torchcodecMedia decoding and encoding for PyTorch: videos, images, and audio, on CPU and GPU.★ 1.2kPythonBSD-3-ClauseActive
4039Eternaldeath/AIProductHomeCollect various AI products | 搜集各种 AI 工具和产品★ 1.2k——Active
4040google/budouBudou is an automatic organizer tool for beautiful line breaking in CJK (Chinese, Japanese, and Korean).★ 1.2kPythonApache-2.0Archived
4041VladimirYugay/Gaussian-SLAMGaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting★ 1.2kPythonMITStale
4042HammerGPT/Hyper-Alpha-ArenaAI Trading platform for Hyperliquid & Binance Futures AI 自动交易平台，支持 Hyperliquid 和币安合约★ 1.2kPythonApache-2.0Slowing
4043machow/siubaPython library for using dplyr like syntax with pandas and SQL★ 1.2kPythonMITStale
4044lucidrains/performer-pytorchAn implementation of Performer, a linear attention-based transformer, in Pytorch★ 1.2kPythonMITStale
4045atinesh/Coursera-Machine-Learning-StanfordMachine learning-Stanford University★ 1.2kMATLAB—Slowing
4046facebookresearch/co3dTooling for the Common Objects In 3D dataset.★ 1.2kPythonOtherStale
4047whai362/PSENetOfficial Pytorch implementations of PSENet.★ 1.2kPythonApache-2.0Stale
4048Tencent-Hunyuan/MixGRPO[ECCV 2026] MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE★ 1.2kPythonOtherSlowing
4049HyperGAN/HyperGANComposable GAN framework with api and user interface★ 1.2kPythonMITActive
4050harvitronix/five-video-classification-methodsCode that accompanies my blog post outlining five video classification methods in Keras and TensorFlow★ 1.2kPythonMITStale