domain: machine-learning
3991 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| jfkirk/tensorrec TensorRec is a Python framework built on TensorFlow for developing and customizing recommendation algorithms. It handles data manipulation,… | 32 | 1299 | abandoned |
| hunkim/word-rnn-tensorflow A TensorFlow implementation of multi-layer recurrent neural networks (LSTM/RNN) for training word-level language models, adapted from char-… | 32 | 1294 | abandoned |
| mitsuba-renderer/enoki Enoki is a C++17 header-only template library for structured vectorization and automatic differentiation of numerical code, compiling the s… | 10 | 1290 | abandoned |
| pluskid/Mocha.jl Mocha.jl is a deep learning framework for Julia, inspired by Caffe, providing modular layers, solvers, and support for training convolution… | 32 | 1284 | abandoned |
| rosejn/cortex Cortex is a Clojure machine learning library providing neural networks, regression, and feature learning on the JVM, with optional GPU acce… | 32 | 1271 | abandoned |
| kakaobrain/nerf-factory A PyTorch library collecting reimplementations of seven popular NeRF (Neural Radiance Fields) models such as NeRF, Mip-NeRF, DVGO, and Ref-… | 10 | 1271 | abandoned |
| chaoming0625/SentimentPolarityAnalysis A Python library for Chinese sentiment polarity analysis offering both lexicon-based scoring and classic ML classifiers (k-NN, Bayes, maxim… | 32 | 1267 | abandoned |
| reiinakano/xcessiv Xcessiv is a web-based Python application for building, tuning, and managing stacked machine learning ensembles. It provides a GUI for defi… | 23 | 1265 | abandoned |
| AtheMathmo/rusty-machine Rusty-machine is a general-purpose machine learning library written entirely in Rust, offering algorithms like regression, SVMs, neural net… | 10 | 1265 | abandoned |
| hollance/Forge Forge is a Swift library that wraps Apple's MPSCNN (Metal Performance Shaders CNN) framework to make it easier to build and run deep neural… | 32 | 1264 | abandoned |
| gnes-ai/gnes GNES (Generic Neural Elastic Search) is a cloud-native framework for building semantic search systems over text, images, and video using de… | 10 | 1263 | abandoned |
| ray-project/ray-llm RayLLM was a library for serving and deploying large language models on top of Ray, providing LLM APIs built on Ray Serve. It has been arch… | 10 | 1261 | abandoned |
| yahoo/CaffeOnSpark CaffeOnSpark is a Spark package that brings the Caffe deep learning framework to Hadoop and Spark clusters, enabling distributed neural net… | 10 | 1261 | abandoned |
| ivan-vasilev/neuralnetworks A Java library implementing deep learning algorithms and deep neural network architectures (MLPs, CNNs, RBMs, autoencoders, DBNs) with GPU … | 23 | 1236 | abandoned |
| atpaino/deep-text-corrector A TensorFlow research project that trains sequence-to-sequence deep learning models to correct small grammatical errors in short conversati… | 32 | 1235 | abandoned |
| Tencent/FeatherCNN FeatherCNN is a high-performance, lightweight CNN inference library developed by Tencent, targeting ARM CPUs on mobile (iOS/Android), embed… | 23 | 1227 | abandoned |
| google/prettytensor Pretty Tensor is a Python library providing a fluent, chainable builder API on top of TensorFlow for defining multi-layer neural networks. … | 10 | 1226 | abandoned |
| xiph/LPCNet LPCNet is a low-complexity C implementation of the WaveRNN-based LPCNet neural vocoder for efficient speech synthesis and compression. It a… | 32 | 1221 | abandoned |
| wagenaartje/neataptic Neataptic is a JavaScript neural network library supporting architecture-free networks trained via neuro-evolution (NEAT) and fast backprop… | 23 | 1221 | abandoned |
| aesara-devs/aesara Aesara is a Python library for defining, optimizing, and efficiently evaluating mathematical expressions over multi-dimensional arrays, for… | 10 | 1220 | abandoned |
| maum-ai/voicefilter An unofficial PyTorch implementation of Google AI's VoiceFilter system, which isolates a target speaker's voice from noisy mixed audio give… | 32 | 1219 | abandoned |
| annoviko/pyclustering pyclustering is a Python and C++ data mining library providing clustering algorithms, oscillatory network models, and neural networks, with… | 23 | 1216 | abandoned |
| facebookarchive/C3D C3D is a modified fork of BVLC Caffe that adds support for 3D convolution and pooling layers, enabling training and fine-tuning of 3D ConvN… | 10 | 1181 | abandoned |
| gpleiss/temperature_scaling A small PyTorch module implementing temperature scaling, a post-processing technique that calibrates the overconfident probability outputs … | 47 | 1175 | abandoned |
| glample/tagger A Named Entity Recognition (NER) tool implementing a state-of-the-art LSTM-CRF model that works across languages without gazetteers. It shi… | 32 | 1175 | abandoned |
| muricoca/crab Crab is a Python recommender engine library integrating classic collaborative filtering and information filtering algorithms with the scien… | 32 | 1175 | abandoned |
| Jai-wei/YOLOv8-PySide6-GUI YoloSide is a desktop GUI application built with PySide6 for running YOLOv8 object detection models. Users can load trained .pt model files… | 30 | 1171 | abandoned |
| hannes-brt/hebel Hebel is a GPU-accelerated deep learning library in Python built on PyCUDA, implementing feed-forward neural networks for classification an… | 23 | 1169 | abandoned |
| kootenpv/neural_complete Neural Complete is a generative LSTM-based autocomplete system trained on Python Keras source code to help write neural network code. It co… | 32 | 1159 | abandoned |
| mila-iqia/blocks Blocks is a Python framework for building and training neural network models on top of Theano. It provides parametrized operations called '… | 23 | 1152 | abandoned |
| NVIDIA/tensorflow NVIDIA's fork of TensorFlow 1.15 providing GPU support for newer NVIDIA hardware and CUDA libraries after Google stopped maintaining the TF… | 10 | 1148 | abandoned |
| linkedlist771/SoraWatermarkCleaner A deep learning tool that detects and removes the Sora2 watermark from AI-generated videos using a YOLO-based detector plus a restoration m… | 10 | 1148 | abandoned |
| eldar/pose-tensorflow A TensorFlow implementation of the DeeperCut and ArtTrack algorithms for human body pose estimation, supporting both single-person and mult… | 32 | 1141 | abandoned |
| mateogianolio/ocr A JavaScript library that trains a multi-layer perceptron neural network to perform optical character recognition on digits and characters.… | 32 | 1132 | abandoned |
| omoindrot/tensorflow-triplet-loss A TensorFlow implementation of triplet loss with online triplet mining strategies (batch all and batch hard), for training embedding models… | 32 | 1126 | abandoned |
| nv-tlabs/ASE ASE (Adversarial Skill Embeddings) is a research codebase from NVIDIA for training reusable low-level skill controllers for physically simu… | 57 | 1118 | abandoned |
| da03/Attention-OCR A Python/TensorFlow implementation of a visual attention-based OCR model that combines a sliding CNN, an LSTM, and an attention decoder to … | 32 | 1117 | abandoned |
| pbloem/former A minimal, from-scratch implementation of the transformer architecture in PyTorch, accompanying a tutorial blog post on how modern transfor… | 37 | 1097 | abandoned |
| carpedm20/DiscoGAN-pytorch A PyTorch implementation of DiscoGAN, a generative adversarial network that discovers cross-domain relations in an unsupervised manner. It … | 32 | 1095 | abandoned |
| MarvinTeichmann/tensorflow-fcn A single-file TensorFlow implementation of Fully Convolutional Networks (FCN) for semantic segmentation, using VGG16 weights loaded from a … | 32 | 1094 | abandoned |
| spragunr/deep_q_rl A Theano/Lasagne-based implementation of the Deep Q-Network (DQN) algorithm from DeepMind's Atari reinforcement learning papers. It trains … | 32 | 1094 | abandoned |
| dmlc/minpy MinPy is a Python library providing a pure NumPy interface backed by MXNet, automatically dispatching operators to GPU when available and f… | 10 | 1094 | abandoned |
| facebookarchive/iTorch iTorch is an IPython kernel for the Torch machine learning framework, providing notebook support with autocomplete and inline help. It adds… | 10 | 1092 | abandoned |
| kubernetes-retired/kube-batch kube-batch is a batch scheduler for Kubernetes designed for high-performance workloads such as AI/ML, Big Data, and HPC jobs. It was the pr… | 10 | 1090 | abandoned |
| neuronika/neuronika Neuronika is a machine learning framework written in pure Rust providing tensors and dynamic neural networks with reverse-mode automatic di… | 32 | 1085 | abandoned |
| databricks/spark-sklearn A deprecated Python library from Databricks that integrates scikit-learn with Apache Spark, primarily to distribute grid-search cross-valid… | 10 | 1071 | abandoned |
| openai/InfoGAN Official research code from OpenAI for reproducing results of the InfoGAN paper, an information-theoretic extension to GANs that learns dis… | 10 | 1069 | abandoned |
| isl-org/MultiObjectiveOptimization Source code for the NeurIPS 2018 paper 'Multi-Task Learning as Multi-Objective Optimization', implementing the MGDA_UB algorithm for multi-… | 10 | 1068 | abandoned |
| NVIDIA/sentiment-discovery A deprecated PyTorch codebase from NVIDIA for large-scale unsupervised language model pretraining and transfer to sentiment and emotion cla… | 23 | 1065 | abandoned |
| google/jaxopt JAXopt is a Python library providing hardware-accelerated, batchable, and differentiable optimizers built on JAX, including implicit differ… | 72 | 1061 | abandoned |
| DeepLearningKit/DeepLearningKit DeepLearningKit is an open-source deep learning framework for Apple's iOS, OS X and tvOS, written in Swift and using Metal for GPU-accelera… | 32 | 1059 | abandoned |
| facebookarchive/fbcunn Facebook AI Research's CUDA-accelerated deep learning extension modules for the Torch-7 framework, including fast FFT-based convolutions, m… | 10 | 1059 | abandoned |
| tensorflow/tfjs-node tfjs-node was the Node.js native binding for TensorFlow.js, providing accelerated training and inference of ML models in JavaScript server … | 10 | 1055 | abandoned |
| shiyybua/NER A Chinese named entity recognition (NER) system built with TensorFlow, using a bidirectional RNN combined with a CRF layer for sequence lab… | 32 | 1054 | abandoned |
| tangjianpku/LINE LINE is a C++ toolkit for embedding very large-scale information networks into low-dimensional vectors, supporting directed, undirected, bi… | 32 | 1053 | abandoned |
| basveeling/wavenet A Keras implementation of DeepMind's WaveNet, a generative neural network model for raw audio synthesis. It supports training on datasets l… | 32 | 1052 | abandoned |
| facebookresearch/VMZ VMZ is a model zoo from Facebook AI's Computer Vision team providing Caffe2 and PyTorch implementations of video classification models such… | 10 | 1052 | abandoned |
| leng-yue/Lengyue-Vcode A library for recognizing and solving CAPTCHA challenges from Tencent, Yidun (NetEase), and Vaptcha verification systems. The project has b… | 10 | 1051 | abandoned |
| carpedm20/NTM-tensorflow A TensorFlow implementation of the Neural Turing Machine (NTM) architecture with an LSTM controller and support for multiple read/write hea… | 32 | 1047 | abandoned |
| openai/supervised-reptile Official research code for the Reptile meta-learning algorithm from the paper 'On First-Order Meta-Learning Algorithms'. It trains and eval… | 10 | 1044 | abandoned |
| digital-standard/ThreeDPoseTracker A Unity-based Windows application that estimates 3D human pose from video or webcam input using an ONNX neural network model via Unity Barr… | 23 | 1042 | abandoned |
| andrewgordonwilson/bayesgan TensorFlow implementation of the Bayesian GAN from the NIPS 2017 paper by Saatchi and Wilson, which places conditional posteriors over gene… | 32 | 1013 | abandoned |
| coreylynch/async-rl A TensorFlow + Keras implementation of asynchronous 1-step Q-learning from the DeepMind 'Asynchronous Methods for Deep Reinforcement Learni… | 32 | 1003 | abandoned |
| deepseek-ai/DeepSeek-V3 Official repository for DeepSeek-V3, a 671B-parameter Mixture-of-Experts language model (37B activated per token) with open weights, infere… | 29 | 104437 | active |
| facebookresearch/segment-anything Segment Anything Model (SAM) from Meta AI is a promptable image segmentation foundation model that produces high-quality object masks from … | 30 | 54794 | stable |
| pandas-dev/pandas pandas is a fast, flexible Python library providing labeled data structures like the DataFrame for practical, real-world data analysis and … | 93 | 49630 | stable |
| Julia Julia is a high-level, high-performance dynamic programming language designed for technical computing, combining scripting-language ergonom… | 99 | 49064 | stable |
| photoprism/photoprism PhotoPrism is an AI-powered, privacy-first web application for browsing, organizing, and sharing personal photo and video collections. It a… | 94 | 40133 | active |
| huggingface/pytorch-image-models PyTorch Image Models (timm) is a Python library offering the largest collection of PyTorch image encoder/backbone architectures with 700+ p… | 95 | 37123 | active |
| junyanz/pytorch-CycleGAN-and-pix2pix Official PyTorch implementations of CycleGAN and pix2pix for paired and unpaired image-to-image translation. It includes training and testi… | 48 | 25237 | stable |
| Dao-AILab/flash-attention Official implementation of FlashAttention, FlashAttention-2, -3, and -4: fast and memory-efficient exact attention kernels for GPUs. It acc… | 95 | 24839 | active |
| plotly/dash Dash is an open-source Python framework for building reactive analytical web apps and dashboards without writing JavaScript, built on Flask… | 98 | 24394 | stable |
| comet-ml/opik Opik is an open-source LLM observability and evaluation platform by Comet for tracing, evaluating, and monitoring LLM applications, RAG pip… | 93 | 21769 | active |
| jundot/omlx oMLX is a native macOS menu bar application and LLM inference server built on Apple's MLX framework, featuring continuous batching and two-… | 78 | 21371 | active |
| dagster-io/dagster Dagster is an open-source Python data orchestration platform for developing, producing, and observing data assets, with integrated lineage,… | 96 | 16097 | active |
| k2-fsa/sherpa-onnx sherpa-onnx is an offline speech processing toolkit built on next-gen Kaldi and onnxruntime, supporting speech-to-text, text-to-speech, spe… | 95 | 14593 | active |
| Dask Dask is a flexible parallel and distributed computing library for Python that scales pandas, NumPy, scikit-learn, and other PyData tools to… | 98 | 13910 | stable |
| LangChain4j LangChain4j is an open-source Java library for building LLM-powered applications on the JVM, providing a unified API over 20+ LLM providers… | 97 | 13012 | active |
| zai-org/CogVideo CogVideo/CogVideoX is an open-source family of text-to-video and image-to-video generation models from Zhipu AI (THUDM), with inference and… | 45 | 12998 | active |
| sapientinc/HRM Official PyTorch implementation of the Hierarchical Reasoning Model (HRM), a 27M-parameter recurrent architecture with high-level and low-l… | 52 | 12631 | active |
| taskflow/taskflow Taskflow is a header-only C++ library for building task-parallel programs using task dependency graphs, with a work-stealing executor for C… | 86 | 12140 | stable |
| milesial/Pytorch-UNet A PyTorch implementation of the U-Net architecture for semantic segmentation of high-resolution images, originally built for Kaggle's Carva… | 23 | 11626 | active |
| kornia/kornia Kornia is a differentiable computer vision library built on PyTorch, offering GPU-accelerated image processing, augmentations, and geometri… | 86 | 11342 | active |
| Arize-ai/phoenix Arize Phoenix is an open-source AI observability and evaluation platform for tracing, debugging, and evaluating LLM applications. It suppor… | 96 | 11311 | active |
| salesforce/LAVIS LAVIS is a Python library from Salesforce AI Research providing a unified toolkit for language-vision (multimodal) intelligence, including … | 61 | 11261 | active |
| OpenGVLab/InternVL InternVL is a family of open-source multimodal large language models (vision-language models) that combine vision transformers with LLMs to… | 36 | 10148 | active |
| facebookresearch/pytorch3d PyTorch3D is Facebook AI Research's library of efficient, reusable components for deep learning with 3D data, built on PyTorch. It provides… | 74 | 9963 | active |
| open-mmlab/mmsegmentation MMSegmentation is a PyTorch-based toolbox and benchmark for semantic segmentation, part of the OpenMMLab ecosystem. It provides implementat… | 23 | 9938 | stable |
| dusty-nv/jetson-inference A C++/Python DNN inference library and tutorial guide ('Hello AI World') for deploying deep learning vision models on NVIDIA Jetson devices… | 44 | 8980 | stable |
| apache/beam Apache Beam is an open-source unified programming model and SDK set (Java, Python, Go, SQL, TypeScript) for defining batch and streaming da… | 94 | 8658 | stable |
| XPixelGroup/BasicSR BasicSR is an open-source PyTorch toolbox for image and video restoration tasks such as super-resolution, denoising, deblurring, and JPEG a… | 23 | 8371 | stable |
| exadel-inc/CompreFace Exadel CompreFace is a free, open-source face recognition system that provides REST APIs for face recognition, verification, detection, lan… | 23 | 8291 | stable |
| isaac-sim/IsaacLab Isaac Lab is a GPU-accelerated open-source framework for robot learning built on NVIDIA Isaac Sim, unifying workflows like reinforcement le… | 92 | 8033 | active |
| AI4Finance-Foundation/FinRobot FinRobot is an open-source AI agent platform for financial applications built on large language models, unifying LLMs, reinforcement learni… | 81 | 7907 | active |
| deepseek-ai/DeepGEMM DeepGEMM is a high-performance CUDA BLAS kernel library for NVIDIA tensor cores, providing FP8, FP4, and BF16 GEMMs plus fused MoE and othe… | 85 | 7772 | active |
| PaddlePaddle/ERNIE Official repository for Baidu's ERNIE 4.5 family of large multimodal models and ERNIEKit, an industrial-grade training toolkit built on Pad… | 65 | 7735 | active |
| tile-ai/tilelang TileLang is a Pythonic domain-specific language and compiler (built on TVM) for writing high-performance GPU/CPU/accelerator kernels such a… | 90 | 7341 | active |
| PaddlePaddle/Paddle-Lite Paddle Lite is a high-performance, lightweight deep learning inference engine from Baidu's PaddlePaddle ecosystem, designed for mobile, emb… | 58 | 7273 | active |
| princeton-vl/infinigen Infinigen is a procedural generator of infinite photorealistic 3D worlds and scenes, built on Blender by the Princeton Vision & Learning La… | 94 | 7247 | active |
| vespa-engine/vespa Vespa is an open-source, distributed AI search platform and serving engine that combines full-text search, vector/tensor search, and machin… | 96 | 7075 | stable |