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 |
|---|---|---|---|
| patrick-kidger/torchtyping A Python library providing type annotations for PyTorch tensors' shape, dtype, layout, and dimension names, with optional runtime checking … | 37 | 1485 | maintenance |
| Sharpiless/Yolov5-deepsort-inference A Python library combining YOLOv5 object detection with DeepSort multi-object tracking to detect, track, and count vehicles and pedestrians… | 62 | 1483 | maintenance |
| Hironsan/anago anaGo is a Python library for sequence labeling tasks such as named entity recognition, part-of-speech tagging, and semantic role labeling,… | 23 | 1482 | maintenance |
| YuanGongND/ast Official PyTorch implementation of the Audio Spectrogram Transformer (AST) from the Interspeech 2021 paper, which applies a Vision Transfor… | 32 | 1481 | maintenance |
| chainer/chainercv ChainerCV is a Python library providing tools to train and run neural networks for computer vision tasks on top of the Chainer framework. I… | 10 | 1481 | maintenance |
| Image Captioning A PyTorch research codebase for image captioning, supporting self-critical sequence training, bottom-up features, transformer captioning mo… | 32 | 1477 | maintenance |
| Marian NMT Marian is an efficient Neural Machine Translation framework written in pure C++ with minimal dependencies, supporting fast multi-GPU traini… | 23 | 1475 | maintenance |
| google-deepmind/jraph Jraph is a lightweight Graph Neural Network library built on JAX, providing a GraphsTuple data structure, graph utilities, and a zoo of for… | 10 | 1475 | maintenance |
| lxztju/pytorch_classification A complete PyTorch image classification codebase built on torchvision, covering training, prediction, TTA, model ensembling, knowledge dist… | 32 | 1470 | maintenance |
| Up-Down Image Captioning System A bottom-up attention model based on Faster R-CNN with ResNet-101 trained on Visual Genome, producing features for salient image regions. T… | 32 | 1469 | maintenance |
| szagoruyko/attention-transfer PyTorch reference implementation of the ICLR 2017 paper 'Paying More Attention to Attention', which improves convolutional neural networks … | 32 | 1466 | maintenance |
| HRNet/HigherHRNet-Human-Pose-Estimation Official PyTorch implementation of HigherHRNet, a CVPR 2020 bottom-up multi-person human pose estimation model using scale-aware high-resol… | 32 | 1465 | maintenance |
| datitran/face2face-demo A pix2pix demo that learns from facial landmarks and translates them into a trained target face, with a real-time webcam application. It in… | 32 | 1461 | maintenance |
| una-dinosauria/3d-pose-baseline A TensorFlow implementation of a simple yet effective baseline for 3D human pose estimation from 2D keypoints, published at ICCV 2017. It i… | 32 | 1461 | maintenance |
| CStanKonrad/long_llama LongLLaMA is a large language model handling long contexts of 256k tokens or more, built on OpenLLaMA and fine-tuned with the Focused Trans… | 29 | 1461 | maintenance |
| buaacyw/GaussianEditor GaussianEditor is a research application for fast, controllable 3D scene editing built on Gaussian Splatting, released as CVPR 2024 code. I… | 27 | 1461 | maintenance |
| DLTK DLTK is a Python neural networks toolkit built on TensorFlow for deep learning on medical images. It provides reference model implementatio… | 32 | 1460 | maintenance |
| facebookresearch/MaskFormer MaskFormer is a PyTorch/Detectron2-based implementation of the NeurIPS 2021 paper 'Per-Pixel Classification is Not All You Need for Semanti… | 10 | 1459 | maintenance |
| pytorch/gloo Gloo is a C++ collective communications library providing primitives like barrier, broadcast, and allreduce for multi-machine machine learn… | 75 | 1456 | maintenance |
| microsoft/NeuronBlocks NeuronBlocks is an NLP deep learning modeling toolkit from Microsoft that lets users build end-to-end neural network training and inference… | 23 | 1456 | maintenance |
| xuannianz/EfficientDet A Keras/TensorFlow implementation of the EfficientDet object detection model with pretrained COCO and ImageNet weights. It supports trainin… | 32 | 1452 | maintenance |
| hysts/pytorch_image_classification A PyTorch library implementing many image classification architectures (ResNet, DenseNet, WRN, PyramidNet, SENet, etc.) and augmentation te… | 10 | 1451 | maintenance |
| HuwCampbell/grenade Grenade is a composable, dependently typed deep learning library for Haskell that lets users specify neural network architectures at the ty… | 23 | 1449 | maintenance |
| BigScience BigScience is a research project training large transformer language models (BERT, GPT-style) at scale, built on a fork of Megatron-LM inte… | 32 | 1448 | maintenance |
| liyaguang/DCRNN A TensorFlow implementation of the Diffusion Convolutional Recurrent Neural Network (DCRNN) from the ICLR 2018 paper on data-driven traffic… | 32 | 1448 | maintenance |
| bojone/attention A small Python library providing implementations of the attention mechanism from 'Attention is All You Need' for TensorFlow/Keras. It is no… | 32 | 1447 | maintenance |
| AshwinRJ/Federated-Learning-PyTorch A PyTorch implementation of the FedAvg algorithm from the paper 'Communication-Efficient Learning of Deep Networks from Decentralized Data'… | 32 | 1441 | maintenance |
| toandaominh1997/EfficientDet.Pytorch A PyTorch implementation of EfficientDet, a scalable and efficient object detection model from a 2019 Google Research paper. It supports Ef… | 10 | 1439 | maintenance |
| VDIGPKU/M2Det M2Det is a PyTorch implementation of a single-shot object detector based on a Multi-Level Feature Pyramid Network (MLFPN), published at AAA… | 32 | 1438 | maintenance |
| xuebinqin/BASNet BASNet is the official PyTorch implementation of the CVPR 2019 paper 'BASNet: Boundary-Aware Salient Object Detection', a deep learning mod… | 32 | 1436 | maintenance |
| yangyanli/PointCNN PointCNN is a deep learning framework for feature learning from 3D point clouds, applying convolution on X-transformed points to handle the… | 51 | 1434 | maintenance |
| pytorch/functorch functorch is a library providing JAX-like composable function transforms (vmap, grad, vjp, jvp) for PyTorch, enabling efficient per-sample … | 10 | 1434 | maintenance |
| KaiyangZhou/Dassl.pytorch Dassl is a PyTorch toolbox for research in domain adaptation, domain generalization, and semi-supervised learning. It provides modular comp… | 32 | 1431 | maintenance |
| Knet Knet (Koç University deep learning framework) is a deep learning library implemented in Julia with GPU support and automatic differentiatio… | 23 | 1431 | maintenance |
| SamLynnEvans/Transformer A PyTorch implementation of the Transformer seq2seq model designed to build language translators from parallel corpora. It accompanies a tu… | 32 | 1430 | maintenance |
| vlfeat/matconvnet MatConvNet is a MATLAB toolbox implementing convolutional neural networks (CNNs) for computer vision applications. It supports training and… | 32 | 1430 | maintenance |
| qfgaohao/pytorch-ssd A PyTorch implementation of the SSD (Single Shot MultiBox Detector) object detection algorithm with MobileNetV1, MobileNetV2, and VGG backb… | 32 | 1430 | maintenance |
| OpenLMLab/MOSS-RLHF MOSS-RLHF is the open-source companion code for the paper 'Secrets of RLHF in Large Language Models Part I: PPO', providing implementations… | 29 | 1430 | maintenance |
| nianticlabs/simplerecon SimpleRecon is the reference PyTorch implementation of an ECCV 2022 paper for multi-view stereo depth estimation and 3D reconstruction that… | 38 | 1429 | maintenance |
| theAIGuysCode/yolov4-deepsort A Python implementation of multi-object tracking that combines YOLOv4 object detection with the Deep SORT tracking algorithm using TensorFl… | 32 | 1427 | maintenance |
| gradslam/gradslam gradslam is a fully differentiable dense SLAM library built on PyTorch, providing differentiable building blocks such as nonlinear least sq… | 23 | 1427 | maintenance |
| open-mmlab/mmhuman3d MMHuman3D is an open-source PyTorch-based toolbox and benchmark for 3D human parametric models (e.g., SMPL, SMPL-X) in computer vision and … | 23 | 1426 | maintenance |
| google-research/disentanglement_lib disentanglement_lib is an open-source Python library for research on learning disentangled representations, supporting models like BetaVAE,… | 10 | 1425 | maintenance |
| rmokady/CLIP_prefix_caption Official implementation of ClipCap, a CLIP-based image captioning model that maps CLIP image encodings to a GPT-2 prefix to generate captio… | 32 | 1423 | maintenance |
| torchgan/torchgan TorchGAN is a PyTorch-based research framework for designing and training Generative Adversarial Networks. It provides modular building blo… | 23 | 1422 | maintenance |
| sfzhang15/RefineDet RefineDet is a C++/Caffe implementation of the CVPR 2018 single-shot object detection model that refines anchors to combine one-stage speed… | 32 | 1421 | maintenance |
| SKTBrain/KoBERT KoBERT is a Korean BERT language model pre-trained on Korean Wikipedia by SK Telecom, distributed as a Python package with PyTorch, ONNX, a… | 40 | 1420 | maintenance |
| BangguWu/ECANet Official PyTorch implementation of ECA-Net, an efficient channel attention module for deep convolutional neural networks published at CVPR … | 32 | 1418 | maintenance |
| thunlp/ERNIE ERNIE is a PyTorch toolkit and dataset for augmenting pre-trained language models like BERT with knowledge graph entity representations, fr… | 32 | 1417 | maintenance |
| GOATmessi8/RFBNet PyTorch implementation of RFBNet, a Receptive Field Block Net object detector presented at ECCV 2018. It enhances SSD-style detectors with … | 32 | 1416 | maintenance |
| cdpierse/transformers-interpret A Python library providing model explainability for Hugging Face Transformers models, built on Captum. It explains text classification, que… | 23 | 1416 | maintenance |
| ConnorJL/GPT2 A community Python/TensorFlow implementation of GPT-2 model training and text generation that supports both GPUs and TPUs. It includes scri… | 32 | 1414 | maintenance |
| chrischoy/3D-R2N2 3D-R2N2 is a PyTorch-based implementation of a recurrent neural network that reconstructs voxelized 3D models of objects from one or multip… | 32 | 1410 | maintenance |
| yu-changqian/TorchSeg A fast, modular PyTorch reference implementation for training and evaluating semantic segmentation models such as FCN, DFN, BiSeNet, PSPNet… | 23 | 1408 | maintenance |
| amazon-science/patchcore-inspection Official implementation of PatchCore, a deep-learning method for industrial image anomaly detection and localization from Roth et al. (2021… | 32 | 1407 | maintenance |
| advboxes/AdvBox AdvBox is a Baidu open-source toolbox for generating adversarial examples that fool neural networks across frameworks like PaddlePaddle, Py… | 32 | 1405 | maintenance |
| gotzmann/llama.go A pure-Go reimplementation of llama.cpp-style LLM inference, running LLaMA-family models on CPU without C++ dependencies. It includes tenso… | 21 | 1402 | maintenance |
| dbolya/tomesd ToMe for SD is a Python/PyTorch library that speeds up Stable Diffusion image generation by merging redundant tokens in the underlying tran… | 21 | 1400 | maintenance |
| facebookresearch/end-to-end-negotiator A PyTorch research codebase from Facebook AI Research implementing end-to-end learning for negotiation dialogues, including models for hier… | 10 | 1400 | maintenance |
| opendilab/DI-star DI-star is a large-scale distributed training platform for building StarCraft II game AI, including supervised and reinforcement learning t… | 34 | 1398 | maintenance |
| swz30/MPRNet MPRNet is a PyTorch implementation of a multi-stage progressive image restoration network published at CVPR 2021. It provides pretrained mo… | 32 | 1395 | maintenance |
| doonny/PipeCNN PipeCNN is an OpenCL-based FPGA accelerator for large-scale convolutional neural network inference, written in C with pipelined kernels. It… | 32 | 1393 | maintenance |
| yao8839836/text_gcn The official implementation of Text GCN, a Graph Convolutional Network approach for text classification published at AAAI 2019. It builds w… | 32 | 1390 | maintenance |
| wouterkool/attention-learn-to-route A PyTorch implementation of the attention-based neural model from the ICLR 2019 paper 'Attention, Learn to Solve Routing Problems!', traine… | 32 | 1387 | maintenance |
| DeepGraphLearning/KnowledgeGraphEmbedding A PyTorch toolkit implementing the RotatE knowledge graph embedding model along with TransE, ComplEx, DistMult, and pRotatE. It trains and … | 32 | 1385 | maintenance |
| jrieke/traingenerator Traingenerator is a Streamlit-based web app that generates custom template code for machine learning projects with PyTorch and scikit-learn… | 32 | 1384 | maintenance |
| chrisdonahue/wavegan Official TensorFlow implementation of WaveGAN, a generative adversarial network that learns to synthesize raw audio waveforms from examples… | 32 | 1382 | maintenance |
| PSPNet Reference implementation of the Pyramid Scene Parsing Network (PSPNet), a CVPR 2017 semantic segmentation model that won the ImageNet Scene… | 32 | 1382 | maintenance |
| nv-tlabs/lift-splat-shoot PyTorch implementation of Lift-Splat-Shoot (ECCV 2020), an end-to-end model that converts images from arbitrary multi-camera rigs into a bi… | 32 | 1378 | maintenance |
| tensorflow/ecosystem A collection of templates and connectors for integrating TensorFlow with other open-source frameworks such as Kubernetes, Kubeflow, Spark, … | 10 | 1377 | maintenance |
| open-mmlab/mmfashion MMFashion is an open-source PyTorch-based toolbox for visual fashion analysis from the OpenMMLab project. It provides modular implementatio… | 32 | 1373 | maintenance |
| nvidia-cosmos/cosmos-predict2.5 NVIDIA Cosmos-Predict2.5 is a family of world foundation models (WFMs) that generate video predictions of future world states for physical … | 67 | 1372 | maintenance |
| akamaster/pytorch_resnet_cifar10 A PyTorch implementation of ResNet architectures (ResNet20 through ResNet1202) for CIFAR10/CIFAR100 that faithfully matches the original pa… | 32 | 1371 | maintenance |
| Cysu/open-reid Open-ReID is a lightweight Python library for person re-identification built on PyTorch, providing a uniform dataset interface, models, and… | 32 | 1371 | maintenance |
| tensorboy/pytorch_Realtime_Multi-Person_Pose_Estimation A PyTorch implementation of the CVPR'17 Realtime Multi-Person 2D Pose Estimation (OpenPose/rtpose) model. It provides pretrained weights, d… | 32 | 1370 | maintenance |
| msracver/Deep-Image-Analogy Official C++/CUDA implementation of the SIGGRAPH 2017 'Visual Attribute Transfer through Deep Image Analogy' technique from Microsoft Resea… | 32 | 1369 | maintenance |
| zalandoresearch/pytorch-ts PyTorchTS is a PyTorch-based probabilistic time series forecasting library that uses GluonTS as its backend API for loading, transforming, … | 23 | 1369 | maintenance |
| JonasGeiping/cramming A research framework for pretraining BERT-type language models from scratch on a single consumer GPU in one day, replicating the paper 'Cra… | 23 | 1368 | maintenance |
| mdeff/cnn_graph Reference implementation of the NIPS 2016 paper 'Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering' (ChebNet),… | 32 | 1367 | maintenance |
| wzzheng/TPVFormer TPVFormer is a CVPR 2023 research implementation of a tri-perspective view transformer for vision-based 3D semantic occupancy prediction, s… | 32 | 1366 | maintenance |
| BorealisAI/advertorch AdverTorch is a Python toolbox for adversarial robustness research built on PyTorch. It provides modules for generating adversarial perturb… | 32 | 1365 | maintenance |
| sail-sg/poolformer PoolFormer is a PyTorch implementation of the CVPR 2022 paper 'MetaFormer Is Actually What You Need for Vision', which replaces attention i… | 23 | 1365 | maintenance |
| taoxugit/AttnGAN A PyTorch implementation of AttnGAN, a fine-grained text-to-image generative adversarial network with multi-stage attention mechanisms from… | 32 | 1363 | maintenance |
| MoyGcc/vid2avatar Vid2Avatar is the official PyTorch implementation of a CVPR 2023 method that reconstructs detailed 3D human avatars from monocular in-the-w… | 54 | 1361 | maintenance |
| atulapra/Emotion-detection A Python application that performs real-time facial emotion detection from a webcam feed using a CNN trained on the FER-2013 dataset. It us… | 32 | 1359 | maintenance |
| mayuelala/FollowYourPose Official PyTorch implementation of Follow-Your-Pose (AAAI 2024), a pose-guided text-to-video generation model that tunes a text-to-image mo… | 21 | 1356 | maintenance |
| dlunion/DBFace DBFace is a real-time, single-stage face detection model implemented in Python, offering small model sizes with high accuracy on the WiderF… | 32 | 1355 | maintenance |
| orobix/retina-unet A Python implementation of a U-Net convolutional neural network for segmenting blood vessels in retina fundus images. It performs binary pi… | 32 | 1355 | maintenance |
| ShuLiu1993/PANet A PyTorch re-implementation of PANet (Path Aggregation Network), the CVPR 2018 paper that won 1st place in the COCO 2017 Instance Segmentat… | 32 | 1345 | maintenance |
| dorarad/gansformer GANformer is a research implementation of a generative adversarial transformer that uses a bipartite attention structure for efficient high… | 23 | 1344 | maintenance |
| PeizeSun/SparseR-CNN Sparse R-CNN is a PyTorch implementation (built on Detectron2) of the CVPR 2021 / PAMI 2023 paper 'End-to-End Object Detection with Learnab… | 23 | 1344 | maintenance |
| kuaikuaikim/dface DFace is an open-source Python library implementing face detection and recognition with PyTorch, based on the MTCNN cascaded convolutional … | 23 | 1340 | maintenance |
| HobbitLong/CMC Official PyTorch implementation of Contrastive Multiview Coding (CMC), a self-supervised visual representation learning method that contras… | 32 | 1338 | maintenance |
| bloc97/CrossAttentionControl An unofficial Jupyter Notebook implementation of the 'Prompt-to-Prompt Image Editing with Cross Attention Control' paper adapted for Stable… | 32 | 1338 | maintenance |
| ikostrikov/pytorch-a3c A PyTorch implementation of the Asynchronous Advantage Actor Critic (A3C) reinforcement learning algorithm from the DeepMind paper 'Asynchr… | 32 | 1338 | maintenance |
| torrvision/crfasrnn Reference implementation of CRF-RNN, an ICCV 2015 semantic image segmentation method that integrates conditional random fields into a neura… | 23 | 1335 | maintenance |
| SHI-Labs/Versatile-Diffusion Versatile Diffusion is the official PyTorch implementation of a unified multi-flow multimodal diffusion model that handles text-to-image, i… | 32 | 1332 | maintenance |
| maudzung/Complex-YOLOv4-Pytorch A PyTorch implementation of Complex-YOLO, a YOLOv4-based model for real-time 3D object detection on LiDAR point clouds. It supports distrib… | 32 | 1332 | maintenance |
| CharlesShang/DCNv2 A PyTorch implementation of Deformable Convolutional Networks v2 (DCNv2), providing CUDA/CPU operators for deformable convolution as a drop… | 67 | 1324 | maintenance |
| WisconsinAIVision/yolact_edge YolactEdge is a PyTorch implementation of a real-time instance segmentation model optimized for edge devices like the NVIDIA Jetson AGX Xav… | 32 | 1322 | maintenance |