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 |
|---|---|---|---|
| biubug6/Pytorch_Retinaface A PyTorch implementation of the RetinaFace single-stage face detection model, supporting mobilenet0.25 and resnet50 backbones with pretrain… | 32 | 2976 | maintenance |
| Tencent/FaceDetection-DSFD DSFD (Dual Shot Face Detector) is Tencent Youtu's high-accuracy face detection network, released with PyTorch inference code and pretrained… | 52 | 2975 | maintenance |
| Cartucho/mAP A Python library and script that computes mean Average Precision (mAP) for object detection models, adapted from the official PASCAL VOC 20… | 23 | 2970 | maintenance |
| johnma2006/mamba-minimal A single-file, readable PyTorch implementation of the Mamba selective state space model architecture. It produces numerically equivalent ou… | 27 | 2968 | maintenance |
| NVIDIA/MinkowskiEngine Minkowski Engine is an auto-differentiation neural network library for high-dimensional sparse tensors, built on PyTorch with CUDA accelera… | 23 | 2960 | maintenance |
| xiaofengShi/CHINESE-OCR An end-to-end Chinese scene-text OCR pipeline combining CTPN for text detection, a VGG16-based orientation classifier, and CRNN with CTC fo… | 73 | 2956 | maintenance |
| pytorch/audio TorchAudio is PyTorch's audio library providing data manipulation, transforms, and dataset loaders for audio and speech machine learning. I… | 83 | 2946 | maintenance |
| ajbrock/BigGAN-PyTorch A PyTorch implementation of BigGAN for large-scale high-fidelity image synthesis, written by the paper's first author. It supports multi-GP… | 32 | 2928 | maintenance |
| facebookresearch/XLM PyTorch implementation of Cross-lingual Language Model Pretraining (XLM) from Facebook AI Research, covering MLM, CLM, and TLM objectives p… | 10 | 2922 | maintenance |
| AudioLDM AudioLDM is a Python library and research model for text-to-audio generation using latent diffusion models conditioned on CLAP embeddings. … | 41 | 2916 | maintenance |
| Tencent/PocketFlow PocketFlow is an open-source AutoML framework from Tencent AI Lab for automatically compressing and accelerating deep learning models. Deve… | 32 | 2910 | maintenance |
| Conchylicultor/DeepQA DeepQA is a TensorFlow implementation of Google's 'A Neural Conversational Model', a seq2seq RNN-based deep learning chatbot. It supports t… | 32 | 2906 | maintenance |
| Luolc/AdaBound AdaBound is a PyTorch implementation of the AdaBound optimizer from an ICLR 2019 paper, which behaves like Adam early in training and gradu… | 23 | 2905 | maintenance |
| alibaba/euler Euler is a distributed graph deep learning framework developed by Alibaba for running graph neural network algorithms on large-scale graphs… | 23 | 2899 | maintenance |
| shouxieai/tensorRT_Pro A C++ library built on NVIDIA TensorRT that provides a high-level interface for high-performance deep learning inference, with Python bindi… | 23 | 2895 | maintenance |
| PlayVoice/whisper-vits-svc A PyTorch-based singing voice conversion and voice cloning engine built on VITS with Whisper, BigVGAN, and diffusion components. It lets us… | 23 | 2868 | maintenance |
| tensorflow/lingvo Lingvo is a TensorFlow-based framework for building neural networks, particularly sequence models, with a focus on speech recognition, mach… | 68 | 2864 | maintenance |
| kpzhang93/MTCNN_face_detection_alignment Reference MATLAB/Caffe implementation of MTCNN, a multi-task cascaded convolutional neural network for joint face detection and facial land… | 32 | 2863 | maintenance |
| gwding/draw_convnet A Python script that generates illustrations of Convolutional Neural Network (ConvNet) architectures using matplotlib. It produces publicat… | 32 | 2861 | maintenance |
| IDEA-Research/DINO Official PyTorch implementation of DINO, a state-of-the-art end-to-end object detection model based on DETR with improved denoising anchor … | 32 | 2852 | maintenance |
| cybertronai/gradient-checkpointing A Python library that reduces GPU memory usage when training very deep neural networks via gradient checkpointing, trading computation for … | 32 | 2847 | maintenance |
| kzl/decision-transformer Official codebase for the Decision Transformer paper, which frames reinforcement learning as sequence modeling with transformers. It contai… | 32 | 2842 | maintenance |
| rosinality/stylegan2-pytorch A PyTorch implementation of StyleGAN 2, the image-quality-improved version of the StyleGAN generative adversarial network, including traini… | 32 | 2833 | maintenance |
| jina-ai/dalle-flow DALL·E Flow is a client-server workflow for generating high-definition images from text prompts using DALL·E-Mega, GLID-3 XL, and Stable Di… | 32 | 2831 | maintenance |
| huggingface/knockknock A small Python library that sends notifications when machine learning training completes or crashes, requiring only a decorator on your mai… | 32 | 2825 | maintenance |
| SCUTlihaoyu/open-chat-video-editor An open-source Python tool that automatically generates short videos from a short text prompt or a web URL, producing narration, background… | 30 | 2816 | maintenance |
| ai-forever/Kandinsky-2 Kandinsky 2 is a multilingual text-to-image latent diffusion model library from Sber AI, supporting text2img, img2img, inpainting, outpaint… | 32 | 2810 | maintenance |
| philipperemy/keras-attention A Keras layer implementing attention mechanisms with Luong (multiplicative) and Bahdanau (additive) score functions for TensorFlow 2.x. It … | 51 | 2808 | maintenance |
| roytseng-tw/Detectron.pytorch A PyTorch reimplementation of Facebook's Detectron object detection framework, supporting Mask R-CNN, keypoint/pose estimation, and instanc… | 10 | 2808 | maintenance |
| kwea123/nerf_pl An unofficial PyTorch implementation of NeRF (Neural Radiance Fields) and NeRF in the Wild built on pytorch-lightning, supporting multi-GPU… | 23 | 2800 | maintenance |
| Alpha-VLLM/LLaMA2-Accessory LLaMA2-Accessory is an open-source Python toolkit for pretraining, finetuning, and deploying large language models and multimodal LLMs, inc… | 29 | 2796 | maintenance |
| PhoebusSi/Alpaca-CoT Alpaca-CoT is an instruction-tuning platform that unifies interfaces for instruction data collection, parameter-efficient fine-tuning metho… | 31 | 2788 | maintenance |
| microsoft/NUWA Microsoft's official research repository for the NUWA family of multimodal generative models, a unified 3D transformer pipeline for visual … | 10 | 2788 | maintenance |
| ethereon/caffe-tensorflow A Python tool that converts Caffe-trained neural network models into TensorFlow format, producing a NumPy parameter file and a Python class… | 32 | 2786 | maintenance |
| henrywoo/pyllama A Python library that is a modified version of Meta's LLaMA implementation, making it easy to download model weights and run LLaMA models o… | 22 | 2778 | maintenance |
| apple/ml-ane-transformers A reference PyTorch implementation of the Transformer architecture optimized for Apple's Neural Engine (ANE), including optimized Hugging F… | 65 | 2745 | maintenance |
| kyegomez/OpenMythos OpenMythos is an open-source, theoretical PyTorch implementation of a Recurrent-Depth Transformer (RDT) architecture inspired by speculatio… | 49 | 14910 | experimental |
| MAML (Model-Agnostic Meta-Learning) Reference implementation of Model-Agnostic Meta-Learning (MAML) from Finn et al., ICML 2017, for fast adaptation of deep networks. It inclu… | 32 | 2723 | maintenance |
| carpedm20/ENAS-pytorch A PyTorch implementation of Efficient Neural Architecture Search (ENAS), which reduces NAS GPU-hours by 1000x via parameter sharing between… | 32 | 2721 | maintenance |
| torch-points3d/torch-points3d A PyTorch-based framework for deep learning on 3D point clouds, supporting models like PointNet, KPConv, and MinkowskiEngine sparse convolu… | 64 | 2717 | maintenance |
| zllrunning/video-object-removal A PyTorch application that removes objects from videos by drawing a bounding box around them. It combines SiamMask for object tracking and … | 32 | 2714 | maintenance |
| microsoft/pai OpenPAI is an open-source AI platform from Microsoft that provides resource scheduling and cluster management for machine learning workload… | 10 | 2700 | maintenance |
| junyanz/interactive-deep-colorization A deep learning application for interactively colorizing black and white images with user-guided hints, based on the SIGGRAPH 2017 paper 'R… | 32 | 2693 | maintenance |
| mahyarnajibi/SNIPER SNIPER is an efficient multi-scale training algorithm for object detection and instance segmentation that processes only context regions (c… | 32 | 2692 | maintenance |
| pengzhiliang/MAE-pytorch An unofficial PyTorch implementation of the MAE (Masked Autoencoders Are Scalable Vision Learners) paper, providing pretraining and finetun… | 32 | 2691 | maintenance |
| JIA-Lab-research/LongLoRA LongLoRA is an efficient fine-tuning approach and codebase that extends the context length of pre-trained LLMs (Llama2 7B/13B/70B) using sh… | 28 | 2687 | maintenance |
| graphdeeplearning/benchmarking-gnns An open-source benchmarking framework for graph neural networks (GNNs) published as a JMLR 2023 paper. It provides reproducible pipelines, … | 32 | 2671 | maintenance |
| HypoX64/DeepMosaics DeepMosaics is a Python application that automatically removes or adds mosaics in images and videos using semantic segmentation and image-t… | 23 | 2659 | maintenance |
| yerfor/GeneFace GeneFace is the official PyTorch implementation of an ICLR 2023 paper on generalized, high-fidelity audio-driven 3D talking face synthesis … | 22 | 2656 | maintenance |
| KupynOrest/DeblurGAN A PyTorch implementation of the DeblurGAN paper for blind motion deblurring using conditional adversarial networks. It uses a Conditional W… | 32 | 2639 | maintenance |
| sanghyun-son/EDSR-PyTorch Official PyTorch implementation of EDSR (Enhanced Deep Residual Networks for Single Image Super-Resolution, CVPRW 2017). It provides traini… | 32 | 2630 | maintenance |
| PeterH0323/Smart_Construction A YOLOv5-based object detection application for detecting people, heads, and safety helmets on construction sites, including pretrained wei… | 23 | 2628 | maintenance |
| knazeri/edge-connect EdgeConnect is a PyTorch implementation of a two-stage generative adversarial model for image inpainting, published at ICCV 2019. It first … | 32 | 2622 | maintenance |
| yangxy/GPEN GPEN (GAN Prior Embedded Network) is a deep learning library for blind face restoration of low-quality, in-the-wild photos. It also support… | 61 | 2613 | maintenance |
| baaivision/Painter Painter and SegGPT are vision foundation models from BAAI for in-context visual learning, where a single generalist model performs diverse … | 32 | 2598 | maintenance |
| ShawnBIT/UNet-family A curated collection of UNet-family semantic segmentation models with PyTorch implementations and links to original papers and third-party … | 32 | 2592 | maintenance |
| lucidrains/big-sleep Big Sleep is a Python command line tool that generates images from natural language text prompts by combining OpenAI's CLIP with a BigGAN g… | 23 | 2575 | maintenance |
| MaybeShewill-CV/lanenet-lane-detection An unofficial TensorFlow implementation of the LaneNet deep neural network for real-time lane detection, based on the IEEE IV paper 'Toward… | 32 | 2570 | maintenance |
| s3prl/s3prl S3PRL is a PyTorch toolkit for self-supervised speech pre-training and representation learning, bundling many upstream models like wav2vec … | 51 | 2567 | maintenance |
| tg-bomze/Face-Depixelizer A Jupyter Notebook-based tool that turns low-resolution pixelated face images into realistic high-resolution faces using the PULSE method, … | 32 | 2562 | maintenance |
| jcjohnson/torch-rnn torch-rnn provides high-performance, reusable RNN and LSTM modules for the Torch7 deep learning framework, used for character-level languag… | 32 | 2562 | maintenance |
| onnx/tensorflow-onnx tf2onnx is a tool that converts TensorFlow, Keras, TensorFlow.js, and TFLite models into the ONNX format via a command-line interface or Py… | 73 | 2556 | maintenance |
| taesungp/contrastive-unpaired-translation A PyTorch implementation of Contrastive Unpaired Translation (CUT), an ECCV 2020 method for unpaired image-to-image translation using patch… | 32 | 2555 | maintenance |
| LiyuanLucasLiu/RAdam RAdam is a Python implementation of Rectified Adam, a variant of the Adam optimizer that analytically reduces the large variance of adaptiv… | 32 | 2550 | maintenance |
| automl/Auto-PyTorch Auto-PyTorch is an AutoML framework that jointly performs neural architecture search and hyperparameter optimization for PyTorch models, us… | 23 | 2540 | maintenance |
| dmlc/gluon-nlp GluonNLP is a Python toolkit built on Apache MXNet that provides text data loading, processing tools, pretrained model zoos, and training u… | 10 | 2538 | maintenance |
| google-deepmind/dnc A TensorFlow implementation of the Differentiable Neural Computer (DNC), a recurrent neural network architecture with an external memory pu… | 32 | 2535 | maintenance |
| znxlwm/UGATIT-pytorch Official PyTorch implementation of U-GAT-IT, an unsupervised image-to-image translation model using attention modules and adaptive layer-in… | 32 | 2533 | maintenance |
| dmlc/decord Decord is a C++ library with Python bindings that provides efficient video and audio decoding for deep learning pipelines. It wraps hardwar… | 23 | 2525 | maintenance |
| cure-lab/LTSF-Linear Official PyTorch implementation of LTSF-Linear (Linear, DLinear, NLinear) from the AAAI-23 paper 'Are Transformers Effective for Time Serie… | 32 | 2520 | maintenance |
| young-geng/EasyLM EasyLM is a JAX/Flax-based framework for pre-training, finetuning, evaluating, and serving large language models like LLaMA. It scales trai… | 32 | 2515 | maintenance |
| zzh8829/yolov3-tf2 A clean implementation of YOLOv3 and YOLOv3-tiny object detection in TensorFlow 2.0, with pre-trained Darknet weight conversion, inference,… | 32 | 2513 | maintenance |
| meijieru/crnn.pytorch A PyTorch implementation of the Convolutional Recurrent Neural Network (CRNN) for scene text recognition, based on the 2016 paper by Shi et… | 32 | 2495 | maintenance |
| galeone/tfgo tfgo is a Go library that wraps TensorFlow's Go bindings with a friendlier, method-chaining API for building and executing computation grap… | 32 | 2495 | maintenance |
| dragen1860/MAML-Pytorch A PyTorch implementation of Model-Agnostic Meta-Learning (MAML) for few-shot supervised learning, supporting MiniImagenet and Omniglot benc… | 32 | 2482 | maintenance |
| microsoft/Graphormer Graphormer is a deep learning library from Microsoft providing a graph transformer backbone for molecular modeling tasks. It ships pre-trai… | 66 | 2481 | maintenance |
| CASIA-IVA-Lab/DANet DANet is the official PyTorch implementation of 'Dual Attention Network for Scene Segmentation' (CVPR 2019), which uses position and channe… | 32 | 2463 | maintenance |
| XifengGuo/CapsNet-Keras A Keras implementation of CapsNet, the capsule network architecture from the NIPS 2017 paper 'Dynamic Routing Between Capsules', achieving … | 23 | 2455 | maintenance |
| Zhongdao/Towards-Realtime-MOT A PyTorch codebase for the Joint Detection and Embedding (JDE) model, a fast multiple-object tracker that learns object detection and appea… | 32 | 2446 | maintenance |
| HobbitLong/RepDistiller RepDistiller is a PyTorch research codebase implementing Contrastive Representation Distillation (CRD) from ICLR 2020. It also benchmarks 1… | 32 | 2444 | maintenance |
| CyberZHG/keras-bert A Keras implementation of BERT that can load official Google pre-trained checkpoints for feature extraction and prediction. It includes a t… | 10 | 2419 | maintenance |
| igul222/improved_wgan_training Reference implementation of the 'Improved Training of Wasserstein GANs' (WGAN-GP) paper, providing TensorFlow code to reproduce its experim… | 32 | 2415 | maintenance |
| deepcam-cn/yolov5-face YOLOv5-Face is a real-time, high-accuracy face detector built on the YOLOv5 object detection framework in PyTorch, with TensorRT deployment… | 32 | 2411 | maintenance |
| OpenBMB/CPM-Bee CPM-Bee is a fully open-source, commercially usable 10-billion-parameter bilingual (Chinese-English) foundation large language model traine… | 68 | 2408 | maintenance |
| mravanelli/pytorch-kaldi PyTorch-Kaldi is a toolkit for developing state-of-the-art DNN/HMM hybrid speech recognition systems, combining PyTorch-managed neural netw… | 32 | 2406 | maintenance |
| danielegrattarola/spektral Spektral is a Python library for graph deep learning built on the Keras API and TensorFlow 2. It provides popular graph neural network laye… | 23 | 2396 | maintenance |
| iPERDance/iPERCore Impersonator++ (iPERCore) is a PyTorch implementation of Liquid Warping GAN with Attention, a unified framework for human image synthesis. … | 32 | 2393 | maintenance |
| Texar Texar is a modularized Python toolkit for machine learning, especially natural language processing and text generation, built on TensorFlow… | 61 | 2390 | maintenance |
| IST-DASLab/gptq Reference implementation of GPTQ, a one-shot post-training weight quantization method for large generative transformer models based on appr… | 32 | 2386 | maintenance |
| BrikerMan/Kashgari Kashgari is a Keras/TensorFlow 2-based NLP transfer learning framework for building text labeling (NER, PoS) and text classification models… | 23 | 2380 | maintenance |
| nbei/Deep-Flow-Guided-Video-Inpainting A PyTorch implementation of the CVPR 2019 paper 'Deep Flow-Guided Video Inpainting', which fills missing regions in videos by completing op… | 32 | 2376 | maintenance |
| r9y9/wavenet_vocoder A PyTorch implementation of the WaveNet vocoder that generates high-quality raw speech waveforms conditioned on acoustic features like mel-… | 23 | 2374 | maintenance |
| princeton-vl/CornerNet Official research code for CornerNet, an object detection model that detects objects as paired keypoints, reproducing results from the ECCV… | 32 | 2369 | maintenance |
| google-research/electra ELECTRA is a research library from Google for self-supervised pre-training of transformer text encoders using a discriminator-based objecti… | 10 | 2364 | maintenance |
| michuanhaohao/reid-strong-baseline A PyTorch implementation of the 'Bag of Tricks and A Strong Baseline for Deep Person Re-identification' paper (CVPRW 2019), providing end-t… | 32 | 2357 | maintenance |
| moskomule/senet.pytorch A PyTorch implementation of Squeeze-and-Excitation Networks (SENet), the ILSVRC 2017 classification winner, including SE-ResNet and SE-Ince… | 23 | 2345 | maintenance |
| smallcorgi/Faster-RCNN_TF A TensorFlow implementation of Faster R-CNN, a convolutional neural network for object detection with a region proposal network. It include… | 32 | 2341 | maintenance |
| NVIDIA/waveglow WaveGlow is a PyTorch implementation of a flow-based generative network that synthesizes high-quality speech audio from mel-spectrograms, c… | 32 | 2338 | maintenance |
| salesforce/decaNLP decaNLP is a PyTorch research framework and benchmark for the Natural Language Decathlon, a multitask NLP challenge spanning ten tasks from… | 10 | 2336 | maintenance |
| Rayhane-mamah/Tacotron-2 A TensorFlow implementation of DeepMind's Tacotron-2 neural text-to-speech architecture, including both the Tacotron spectrogram predictor … | 32 | 2321 | maintenance |