Open-source deep-learning software
2785 open-source libraries, tools and applications tagged deep-learning, ranked by how closely deep-learning is their primary purpose, then by adoption and maintenance health. Each entry links to a page with sources, use cases and when to choose or avoid it.
2785 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| MoCo A PyTorch implementation of MoCo v3, a self-supervised contrastive learning method for ResNet and Vision Transformer (ViT) models. It inclu… | 10 | 1322 | maintenance |
| aitorzip/PyTorch-CycleGAN A clean, readable PyTorch implementation of CycleGAN for unpaired image-to-image translation using cycle-consistent adversarial networks. I… | 32 | 1321 | maintenance |
| CSTR-Edinburgh/merlin Merlin is a toolkit from the University of Edinburgh's CSTR for building deep neural network models for statistical parametric speech synth… | 23 | 1321 | maintenance |
| msracver/Deep-Feature-Flow Official MXNet implementation of Deep Feature Flow (CVPR 2017), an end-to-end framework for video recognition such as object detection and … | 32 | 1314 | maintenance |
| szagoruyko/wide-residual-networks Reference implementation of Wide Residual Networks (WRN), a ResNet variant that trades depth for width to train faster and achieve state-of… | 32 | 1314 | maintenance |
| tysam-code/hlb-CIFAR10 A single-file PyTorch implementation that trains a neural network to 94% accuracy on CIFAR-10 in under 6.3 seconds on a single A100 GPU, fo… | 23 | 1310 | maintenance |
| d-li14/involution Official PyTorch implementation of the involution neural operator from the CVPR 2021 paper 'Involution: Inverting the Inherence of Convolut… | 32 | 1309 | maintenance |
| bert_seq2seq A lightweight PyTorch framework for fine-tuning pretrained language models (BERT, RoBERTa, Nezha, GPT2, T5, BART) on Chinese NLP tasks usin… | 32 | 1307 | maintenance |
| mit-han-lab/data-efficient-gans Official implementation of Differentiable Augmentation (DiffAugment), a NeurIPS 2020 method that improves GAN training data efficiency by a… | 32 | 1307 | maintenance |
| chengzeyi/stable-fast Stable Fast is an ultra lightweight performance optimization framework for HuggingFace Diffusers pipelines on NVIDIA GPUs. It achieves SOTA… | 21 | 1305 | maintenance |
| kakaobrain/pororo PORORO is a Python library from Kakao Brain that provides unified access to dozens of pretrained neural models for natural language process… | 10 | 1304 | maintenance |
| senlinuc/caffe_ocr An experimental research project built on Caffe implementing CNN+BLSTM+CTC text recognition architectures, with modifications for LSTM, war… | 32 | 1303 | maintenance |
| nlpyang/PreSumm PreSumm is the official PyTorch implementation of the EMNLP 2019 paper 'Text Summarization with Pretrained Encoders', providing BERT-based … | 32 | 1302 | maintenance |
| ShichenLiu/SoftRas SoftRas is a PyTorch-based differentiable renderer that treats rasterization as a differentiable aggregating process over mesh triangles, e… | 52 | 1300 | maintenance |
| foolwood/DaSiamRPN PyTorch implementation of DaSiamRPN, an ECCV 2018 distractor-aware Siamese network for visual object tracking, winner of the VOT-18 real-ti… | 32 | 1300 | maintenance |
| digantamisra98/Mish Official repository for the Mish activation function, a self-regularized non-monotonic neural activation function published at BMVC 2020. I… | 70 | 1299 | maintenance |
| NVlabs/DG-Net DG-Net is a PyTorch implementation of the CVPR 2019 (Oral) paper 'Joint Discriminative and Generative Learning for Person Re-identification… | 32 | 1298 | maintenance |
| tensorflow/text TensorFlow Text is a library of text-processing classes and ops for TensorFlow 2.x, providing tokenization, Unicode normalization, n-grams,… | 92 | 1294 | maintenance |
| bubbliiiing/deeplabv3-plus-pytorch A PyTorch implementation of the DeepLabv3+ semantic segmentation model with MobileNetV2 and Xception backbones. It includes scripts for tra… | 23 | 1290 | maintenance |
| google-research/multilingual-t5 Code and resources for mT5, a massively multilingual text-to-text transformer pretrained on the mC4 corpus covering 101 languages. It repro… | 10 | 1290 | maintenance |
| zeusees/License-Plate-Detector A YOLOv5-based license plate detection model trained on the CCPD dataset and proprietary data, supporting many Chinese plate types. It prov… | 32 | 1289 | maintenance |
| NVlabs/alias-free-gan The official project page and code for Alias-Free GAN, an NVIDIA research method for aliasing-free generative adversarial networks. The imp… | 32 | 1287 | maintenance |
| weihua916/powerful-gnns Official PyTorch implementation of the experiments from the ICLR 2019 paper 'How Powerful are Graph Neural Networks?', introducing the Grap… | 32 | 1287 | maintenance |
| Khrylx/PyTorch-RL A PyTorch library implementing deep reinforcement learning policy gradient algorithms (TRPO, PPO, A2C) and Generative Adversarial Imitation… | 32 | 1286 | maintenance |
| oscarknagg/few-shot A PyTorch repository with clean, tested implementations that reproduce few-shot learning and meta-learning research papers such as Prototyp… | 32 | 1286 | maintenance |
| YuanxunLu/LiveSpeechPortraits A PyTorch implementation of the SIGGRAPH Asia 2021 paper 'Live Speech Portraits', which generates photorealistic personalized talking-head … | 32 | 1283 | maintenance |
| NVIDIA-Merlin/Transformers4Rec Transformers4Rec is a Python library by NVIDIA for sequential and session-based recommendation using transformer architectures, bridging NL… | 63 | 1281 | maintenance |
| harvardnlp/seq2seq-attn A Torch (Lua) implementation of sequence-to-sequence models with LSTM encoder-decoders and optional attention for neural machine translatio… | 32 | 1280 | maintenance |
| MasterBin-IIAU/UNINEXT UNINEXT is the official PyTorch implementation of the CVPR 2023 paper 'Universal Instance Perception as Object Discovery and Retrieval'. It… | 31 | 1279 | maintenance |
| snap-research/articulated-animation Official research code for the CVPR 2021 paper 'Motion Representations for Articulated Animation' by Snap Research. It animates a static so… | 39 | 1278 | maintenance |
| j96w/DenseFusion DenseFusion is the official PyTorch implementation of the paper '6D Object Pose Estimation by Iterative Dense Fusion', which estimates the … | 32 | 1278 | maintenance |
| benedekrozemberczki/CapsGNN A PyTorch implementation of the Capsule Graph Neural Network (CapsGNN) from ICLR 2019, which uses capsule networks and routing mechanisms t… | 23 | 1278 | maintenance |
| pfnet/pfrl PFRL is a PyTorch-based deep reinforcement learning library implementing state-of-the-art algorithms such as DQN, Rainbow, PPO, SAC, and A3… | 51 | 1277 | maintenance |
| Autopilot TensorFlow A TensorFlow implementation of Nvidia's end-to-end self-driving steering angle prediction paper (arXiv 1604.07316) with some modifications.… | 32 | 1277 | maintenance |
| kaiyinzhou/BERT-NER A Python implementation that fine-tunes Google's BERT for named entity recognition using the CoNLL-2003 dataset, built on TensorFlow. It pr… | 32 | 1274 | maintenance |
| elanmart/cbp-translate A demo application that live-translates foreign-language speech in videos into subtitles, mimicking the Cyberpunk 2077 translation effect. … | 32 | 1274 | maintenance |
| kennymckormick/pyskl PYSKL is a PyTorch-based toolbox for skeleton-based human action recognition, built on MMAction2. It provides official implementations of P… | 50 | 1270 | maintenance |
| DeepGraphLearning/graphvite GraphVite is a general, high-performance graph embedding engine written in C++ with Python bindings, supporting node embedding, knowledge g… | 32 | 1270 | maintenance |
| TimoBolkart/voca VOCA is a speech-driven 3D facial animation framework that synthesizes realistic character face animations from an arbitrary speech signal … | 32 | 1267 | maintenance |
| HendrikStrobelt/LSTMVis LSTMVis is a visual analysis toolbox for inspecting hidden state dynamics of LSTM (and other RNN) networks. It provides a browser-based int… | 23 | 1267 | maintenance |
| kuleshov/audio-super-res A Python/TensorFlow implementation of neural network models for audio super resolution, upsampling low-resolution audio to higher sampling … | 32 | 1266 | maintenance |
| tensorlayer/HyperPose HyperPose is a library for building high-performance custom human pose estimation applications. It combines a C++ inference engine with Ten… | 23 | 1264 | maintenance |
| salesforce/pytorch-qrnn A PyTorch implementation of the Quasi-Recurrent Neural Network (QRNN) from Salesforce Research, offering LSTM-like accuracy with 2-17x fast… | 10 | 1263 | maintenance |
| OpenPifPaf OpenPifPaf is a PyTorch library implementing Composite Fields for semantic keypoint detection and spatio-temporal association, primarily fo… | 23 | 1262 | maintenance |
| GoGoDuck912/Self-Correction-Human-Parsing A deep learning toolkit for human parsing (semantic segmentation of clothing and body parts in images), with pretrained models on LIP, ATR,… | 32 | 1259 | maintenance |
| ARM-software/ML-KWS-for-MCU TensorFlow models and training scripts for keyword spotting (wake-word detection) on Arm Cortex-M microcontrollers, accompanying the 'Hello… | 32 | 1258 | maintenance |
| DrSleep/tensorflow-deeplab-resnet A TensorFlow re-implementation of the DeepLab-ResNet model for semantic image segmentation, trained and evaluated on the PASCAL VOC dataset… | 10 | 1257 | maintenance |
| harvardnlp/im2markup A deep learning system (built on Torch) that converts images of rendered text into presentational markup such as LaTeX or HTML, using a CNN… | 32 | 1256 | maintenance |
| davidmrau/mixture-of-experts A PyTorch re-implementation of the sparsely-gated Mixture-of-Experts layer from the paper 'Outrageously Large Neural Networks' by Shazeer e… | 32 | 1255 | maintenance |
| Fantasy-Studio/Paint-by-Example Paint by Example is a PyTorch implementation of exemplar-based image editing with diffusion models, letting users fill masked regions of an… | 32 | 1254 | maintenance |
| uclaml/SPIN Official implementation of Self-Play Fine-Tuning (SPIN), a method that improves language models by having them iteratively generate and dis… | 26 | 1254 | maintenance |
| leftthomas/SRGAN A PyTorch implementation of SRGAN, the CVPR 2017 generative adversarial network for photo-realistic single-image super-resolution. It inclu… | 32 | 1251 | maintenance |
| kamalkraj/BERT-NER A PyTorch library for training and running named entity recognition (NER) models based on Google's BERT, evaluated on the CoNLL-2003 datase… | 32 | 1250 | maintenance |
| XiangLi1999/Diffusion-LM Diffusion-LM is the official research code for the paper 'Diffusion-LM Improves Controllable Text Generation', implementing a diffusion-bas… | 32 | 1250 | maintenance |
| NeymarL/ChineseChess-AlphaZero An open-source implementation of AlphaZero/AlphaGo Zero reinforcement learning methods applied to Chinese chess (Xiangqi). It includes self… | 23 | 1249 | maintenance |
| RedaOps/ann-visualizer A Python library that generates presentable graph diagrams of Keras neural network architectures using Graphviz. It supports visualizing bo… | 10 | 1248 | maintenance |
| R-FCN MATLAB implementation of R-FCN, a region-based fully convolutional object detection framework described in a NIPS 2016 paper. It builds on … | 32 | 1247 | maintenance |
| KMnP/vpt Official PyTorch implementation of Visual Prompt Tuning (VPT), an ECCV 2022 method for parameter-efficient fine-tuning of vision transforme… | 32 | 1247 | maintenance |
| ranahanocka/point2mesh Point2Mesh is a PyTorch implementation of a SIGGRAPH 2020 technique that reconstructs watertight surface meshes from input point clouds by … | 32 | 1245 | maintenance |
| VeritasYin/STGCN_IJCAI-18 Reference implementation of Spatio-Temporal Graph Convolutional Networks (STGCN) from the IJCAI 2018 paper, a deep learning framework for t… | 68 | 1244 | maintenance |
| mravanelli/SincNet SincNet is a PyTorch neural architecture that processes raw audio waveforms using parametrized sinc band-pass filters in the first convolut… | 32 | 1243 | maintenance |
| lfz/DSB2017 The winning solution of team 'grt123' for the 2017 Data Science Bowl (DSB2017), a deep learning pipeline for detecting lung cancer from CT … | 32 | 1242 | maintenance |
| ShannonAI/service-streamer Service Streamer is a Python middleware that queues discrete web service requests into mini-batches for deep learning model inference, impr… | 32 | 1241 | maintenance |
| ultralytics/JSON2YOLO A legacy Python toolkit that converts JSON-format annotation datasets (COCO, LabelMe, Labelbox, VoTT, INFOLKS, ATH) into the YOLO format fo… | 64 | 1240 | maintenance |
| otaha178/Emotion-recognition A Python application that performs real-time facial emotion recognition from a webcam feed using a convolutional neural network. It display… | 32 | 1239 | maintenance |
| autonomousvision/giraffe Official PyTorch implementation of GIRAFFE, a CVPR 2021 (oral, best paper award) generative model that represents scenes as compositional g… | 32 | 1238 | maintenance |
| openseg-group/openseg.pytorch Official PyTorch implementations of semantic segmentation models OCNet, OCRNet, and SegFix, achieving state-of-the-art results on benchmark… | 23 | 1237 | maintenance |
| AGI-Edgerunners/LLM-Adapters LLM-Adapters is a Python framework extending HuggingFace's PEFT library that integrates various adapter types (LoRA, series/parallel adapte… | 31 | 1236 | maintenance |
| BR-IDL/PaddleViT PaddleViT is a collection of state-of-the-art Vision Transformer and MLP model implementations for PaddlePaddle 2.1+, covering image classi… | 23 | 1236 | maintenance |
| facebookresearch/simsiam A PyTorch implementation of SimSiam, a simple Siamese-based self-supervised representation learning method from Facebook AI Research (CVPR … | 10 | 1236 | maintenance |
| jakesnell/prototypical-networks Reference PyTorch implementation of Prototypical Networks for few-shot classification from the NeurIPS 2017 paper. It includes training and… | 32 | 1235 | maintenance |
| jfzhang95/pytorch-video-recognition A PyTorch library implementing C3D, R3D, and R2Plus1D models for video action recognition, with training scripts for UCF101 and HMDB51 data… | 32 | 1234 | maintenance |
| huoyijie/AdvancedEAST AdvancedEAST is a deep learning algorithm for detecting text in scene images, built on the EAST architecture with improvements for more acc… | 32 | 1229 | maintenance |
| qubvel/classification_models A Keras/TensorFlow Keras library providing ImageNet-pretrained image classification model architectures such as ResNet, SE-ResNet, DenseNet… | 23 | 1229 | maintenance |
| google-research/fixmatch Official research code for FixMatch, a semi-supervised learning method that combines consistency regularization with confidence-based pseud… | 10 | 1222 | maintenance |
| xvjiarui/GCNet Official PyTorch implementation of GCNet (Global Context Networks), a paper combining ideas from Non-Local Networks and Squeeze-Excitation … | 32 | 1220 | maintenance |
| GeekAlexis/FastMOT FastMOT is a high-performance multiple object tracking system combining YOLO/SSD detection, Deep SORT with OSNet ReID, and KLT optical flow… | 23 | 1219 | maintenance |
| xingyizhou/CenterNet2 CenterNet2 is a research implementation of probabilistic two-stage object detection built on detectron2, where a class-agnostic one-stage C… | 32 | 1218 | maintenance |
| awslabs/sockeye Sockeye is an open-source sequence-to-sequence framework for Neural Machine Translation built on PyTorch, with distributed training and opt… | 23 | 1216 | maintenance |
| The-AI-Summer/self-attention-cv A PyTorch library implementing various self-attention mechanisms and transformer building blocks for computer vision, including multi-head … | 23 | 1216 | maintenance |
| Shikhargupta/Spiking-Neural-Network A pure Python implementation of a hardware-efficient spiking neural network (SNN) trained with Spike-Time Dependent Plasticity (STDP). It i… | 32 | 1215 | maintenance |
| imfing/keras-flask-deploy-webapp A minimal, customizable Flask web app template for deploying Keras/TensorFlow image classification models. It ships with a mobile-friendly … | 32 | 1211 | maintenance |
| mouna99/dien A TensorFlow implementation of the Deep Interest Evolution Network (DIEN) for click-through rate prediction, based on the Alibaba research … | 32 | 1209 | maintenance |
| Alexander-H-Liu/End-to-end-ASR-Pytorch A PyTorch implementation of end-to-end automatic speech recognition (ASR), formerly known as Listen, Attend and Spell. It supports seq2seq … | 32 | 1206 | maintenance |
| bckenstler/CLR A Keras callback implementing cyclical learning rate (CLR) policies from Leslie Smith's paper, with built-in triangular, triangular2, and e… | 32 | 1206 | maintenance |
| lessw2020/Ranger-Deep-Learning-Optimizer Ranger is a PyTorch deep learning optimizer that synergistically combines RAdam (Rectified Adam), LookAhead, and Gradient Centralization in… | 32 | 1205 | maintenance |
| facebookresearch/ToMe ToMe (Token Merging) is a PyTorch library from Meta AI that speeds up existing Vision Transformers by merging similar tokens inside the net… | 10 | 1204 | maintenance |
| chainer/chainerrl ChainerRL is a deep reinforcement learning library implementing state-of-the-art algorithms like DQN, Rainbow, PPO, SAC, and A3C in Python … | 23 | 1203 | maintenance |
| RKNN RKNN-Toolkit2 is Rockchip's software development kit for converting trained AI models to RKNN format and deploying them on Rockchip NPU chi… | 23 | 1203 | maintenance |
| aigamedev/scikit-neuralnetwork A Python library providing deep neural network classifiers and regressors with a scikit-learn-compatible API, wrapping Lasagne and Theano. … | 10 | 1203 | maintenance |
| google-research/tapas TAPAS is Google Research's implementation of transformer-based models for question answering over tables, including pretrained checkpoints … | 10 | 1202 | maintenance |
| enazoe/yolo-tensorrt A C++ wrapper around NVIDIA TensorRT for running YOLO object detection models (YOLOv3, YOLOv4, YOLOv5) with support for FP32, FP16, and INT… | 53 | 1201 | maintenance |
| lucidrains/CoCa-pytorch A Pytorch implementation of CoCa (Contrastive Captioners), an image-text foundation model that combines contrastive learning with an encode… | 23 | 1201 | maintenance |
| henrywoo/chatllama An open-source Python library implementing RLHF-based fine-tuning of Meta's LLaMA models to build ChatGPT-style chat assistants, runnable o… | 22 | 1201 | maintenance |
| KaihuaTang/Scene-Graph-Benchmark.pytorch A PyTorch codebase for Scene Graph Generation (SGG) built on maskrcnn-benchmark, implementing methods from the CVPR 2020 paper 'Unbiased Sc… | 56 | 1199 | maintenance |
| DeepWisdom/AutoDL AutoDL is a fully automated deep learning framework from DeepWisdom that won the NeurIPS AutoDL challenge. It performs automatic feature en… | 23 | 1199 | maintenance |
| rotemtzaban/STIT STIT (Stitch it in Time) is a research implementation of a GAN-based framework for semantic editing of faces in real videos, based on the p… | 32 | 1196 | maintenance |
| huggingface/hmtl HMTL is a Hierarchical Multi-Task Learning model for NLP that jointly trains Named Entity Recognition, Entity Mention Detection, Relation E… | 32 | 1196 | maintenance |
| ROCm/MIOpen MIOpen is AMD's open-source library providing high-performance GPU kernels for machine learning primitives (convolutions, normalization, ac… | 89 | 1195 | maintenance |
| rinongal/StyleGAN-nada Official PyTorch implementation of StyleGAN-NADA, a CLIP-guided method for adapting pre-trained StyleGAN image generators to new domains us… | 32 | 1195 | maintenance |