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 |
|---|---|---|---|
| NVIDIA/DeepRecommender A research library implementing deep autoencoders for collaborative filtering in recommender systems, based on the paper 'Training Deep Aut… | 10 | 1701 | maintenance |
| tensorflow/addons TensorFlow Addons is a collection of extra layers, optimizers, losses, metrics, activations, callbacks, and image ops that conform to Tenso… | 10 | 1698 | maintenance |
| ELS-RD/transformer-deploy A Python tool that optimizes Hugging Face transformer models for production inference using ONNX Runtime and NVIDIA TensorRT, deploying the… | 23 | 1695 | maintenance |
| VITA-Group/TransGAN Official PyTorch implementation of TransGAN, a NeurIPS 2021 paper that builds a GAN whose generator and discriminator are both pure transfo… | 32 | 1693 | maintenance |
| Graph4NLP Graph4NLP is a Python library for applying Graph Neural Networks to Natural Language Processing tasks, built on DGL and PyTorch. It provide… | 23 | 1690 | maintenance |
| lucidrains/lightweight-gan A PyTorch implementation of the 'lightweight' GAN from ICLR 2021, featuring skip-layer excitation in the generator and autoencoding self-su… | 34 | 1688 | maintenance |
| mit-han-lab/smoothquant SmoothQuant is a training-free post-training quantization (PTQ) method that enables W8A8 (8-bit weight, 8-bit activation) quantization for … | 32 | 1686 | maintenance |
| LoSealL/VideoSuperResolution A Python library (pip-installable as VSR) collecting reimplementation of state-of-the-art single-image and video super-resolution neural ne… | 23 | 1685 | maintenance |
| adobe/antialiased-cnns A PyTorch library providing antialiased CNN models and a BlurPool layer from the ICML 2019 paper 'Making Convolutional Networks Shift-Invar… | 23 | 1684 | maintenance |
| open-mmlab/mmrazor MMRazor is OpenMMLab's model compression toolbox and benchmark built on PyTorch. It provides implementations of neural architecture search,… | 23 | 1683 | maintenance |
| CuriousAI/mean-teacher Reference implementations (TensorFlow and PyTorch) of the Mean Teacher semi-supervised learning method from the NIPS 2017 paper by Tarvaine… | 32 | 1681 | maintenance |
| Lam1360/YOLOv3-model-pruning A PyTorch implementation of YOLOv3 channel pruning (network slimming) applied to hand detection on the Oxford Hand dataset. It provides spa… | 32 | 1676 | maintenance |
| argusswift/YOLOv4-pytorch A PyTorch re-implementation of YOLOv4 object detection with variants including attentive YOLOv4 (SEnet, CBAM, CoordAttention) and MobileNet… | 23 | 1674 | maintenance |
| Kaixhin/Rainbow A PyTorch implementation of the Rainbow deep reinforcement learning agent, combining DQN improvements like prioritized experience replay, d… | 23 | 1673 | maintenance |
| akanazawa/hmr HMR (Human Mesh Recovery) is a TensorFlow implementation of the CVPR 2018 paper 'End-to-end Recovery of Human Shape and Pose', which regres… | 32 | 1671 | maintenance |
| autonomousvision/occupancy_networks Official PyTorch implementation of the CVPR 2019 paper 'Occupancy Networks: Learning 3D Reconstruction in Function Space'. It learns contin… | 32 | 1667 | maintenance |
| natanielruiz/deep-head-pose Hopenet is a PyTorch deep learning model for fine-grained head pose estimation from images and video, without requiring facial keypoints. I… | 32 | 1666 | maintenance |
| hfawaz/dl-4-tsc Companion repository for the paper 'Deep learning for time series classification: a review', providing TensorFlow 2 implementations of nine… | 32 | 1660 | maintenance |
| NanoTrack A PyTorch collection of Siamese-based visual object tracking models including SiamFC, SiamRPN++, SiamMask, Ocean, LightTrack, and the light… | 32 | 1660 | maintenance |
| google-research/pegasus PEGASUS is Google Research's implementation of transformer encoder-decoder models pre-trained with the Gap Sentences Generation objective f… | 10 | 1658 | maintenance |
| rwightman/efficientdet-pytorch A PyTorch implementation of EfficientDet object detection, faithful to the original Google TensorFlow implementation with ported pretrained… | 23 | 1656 | maintenance |
| gnobitab/RectifiedFlow Official PyTorch implementation of Rectified Flow, an ICLR 2023 Spotlight method for learning transport maps between distributions via stra… | 32 | 1653 | maintenance |
| amir-abdi/keras_to_tensorflow A Python CLI tool that converts trained Keras models (.h5 or .h5 + .) into frozen, inference-ready TensorFlow protobuf (.pb) files. It free… | 32 | 1646 | maintenance |
| kan-bayashi/ParallelWaveGAN Unofficial PyTorch implementations of non-autoregressive neural vocoders including Parallel WaveGAN, MelGAN, Multi-band MelGAN, HiFi-GAN, a… | 23 | 1646 | maintenance |
| lucidrains/alphafold2 An unofficial PyTorch implementation of DeepMind's AlphaFold2 protein structure prediction network, built as a translation of the official … | 23 | 1640 | maintenance |
| autonomio/talos Talos is a Python library for automating hyperparameter experiments and model evaluation with TensorFlow (tf.keras), Keras, and PyTorch mod… | 98 | 1634 | maintenance |
| facebookresearch/consistent_depth A research library from Facebook AI Research implementing Consistent Video Depth Estimation (SIGGRAPH 2020). It reconstructs dense, flicker… | 10 | 1634 | maintenance |
| tensorflow/mesh Mesh TensorFlow is a Python library and embedded language for specifying distributed tensor computations, letting users define how model di… | 10 | 1629 | maintenance |
| facebookresearch/pytorch_GAN_zoo A PyTorch toolbox of GAN implementations including Progressive Growing GAN, DCGAN, and StyleGAN (beta), plus tools like GDPP, AC-GAN condit… | 10 | 1627 | maintenance |
| facebookresearch/higher higher is a PyTorch library that enables higher-order gradients over losses spanning entire training loops rather than individual steps. It… | 10 | 1624 | maintenance |
| lucidrains/PaLM-rlhf-pytorch A PyTorch library implementing Reinforcement Learning from Human Feedback (RLHF) on top of the PaLM transformer architecture, aiming to rep… | 77 | 7861 | experimental |
| allenai/bilm-tf A TensorFlow implementation of the bidirectional language model (biLM) used to compute ELMo deep contextualized word representations. It su… | 32 | 1609 | maintenance |
| divamgupta/stable-diffusion-tensorflow A TensorFlow/Keras implementation of Stable Diffusion with weights ported from the original implementation. It provides a Python API and Co… | 32 | 1608 | maintenance |
| experiencor/keras-yolo3 A Keras/TensorFlow implementation of YOLOv3 for object detection, supporting detection with pretrained weights, custom model training with … | 32 | 1608 | maintenance |
| ialhashim/DenseDepth Official Keras/TensorFlow implementation (with experimental PyTorch and TF2 code) of the DenseDepth paper for high-quality monocular depth … | 32 | 1607 | maintenance |
| wy1iu/sphereface Official implementation of SphereFace (Deep Hypersphere Embedding for Face Recognition, CVPR 2017), built on Caffe with a full face recogni… | 32 | 1606 | maintenance |
| Delta-ML/delta DELTA is a deep learning based end-to-end natural language and speech processing platform built on TensorFlow and Python 3. It provides one… | 10 | 1606 | maintenance |
| chandrikadeb7/Face-Mask-Detection A face mask detection system built with OpenCV and TensorFlow/Keras that uses deep learning (SSD MobileNetV2) to detect whether people are … | 23 | 1605 | maintenance |
| Fast AutoAugment Official PyTorch implementation of Fast AutoAugment (NeurIPS 2019), which learns image augmentation policies via density-matching search. I… | 32 | 1604 | maintenance |
| tensorflow/haskell Haskell bindings to the TensorFlow machine learning library, providing a typed API for building and training neural network models. It incl… | 10 | 1604 | maintenance |
| PeterWang512/FALdetector FALdetector is the official PyTorch implementation of the ICCV 2019 paper 'Detecting Photoshopped Faces by Scripting Photoshop'. It provide… | 32 | 1601 | maintenance |
| NVlabs/FUNIT FUNIT is NVIDIA's PyTorch implementation of a few-shot unsupervised image-to-image translation model (ICCV 2019) that can translate images … | 32 | 1586 | maintenance |
| PaddlePaddle/PGL Paddle Graph Learning (PGL) is an efficient and flexible graph learning framework built on PaddlePaddle. It supports heterogeneous graph le… | 23 | 1585 | maintenance |
| lufficc/SSD A high-quality, fast, modular reference implementation of the SSD (Single Shot MultiBox Detector) object detection model in PyTorch. It sup… | 23 | 1585 | maintenance |
| D-X-Y/AutoDL-Projects AutoDL-Projects is a PyTorch library implementing automated deep learning algorithms, including neural architecture search (NAS) methods li… | 32 | 1581 | maintenance |
| melodyguan/enas Authors' TensorFlow implementation of Efficient Neural Architecture Search (ENAS), which discovers neural network architectures via paramet… | 32 | 1579 | maintenance |
| KotlinDL KotlinDL is a high-level deep learning framework written in Kotlin and inspired by Keras, built on top of the TensorFlow Java API and ONNX … | 23 | 1579 | maintenance |
| vturrisi/solo-learn solo-learn is a Python library of state-of-the-art self-supervised methods for unsupervised visual representation learning, built on PyTorc… | 62 | 1578 | maintenance |
| xinntao/EDVR EDVR is the winning solution of the NTIRE19 video restoration challenges, built on enhanced deformable convolutional networks. The repo is … | 32 | 1578 | maintenance |
| OsciiArt/DeepAA DeepAA is a Python project that generates ASCII art from grayscale line images using convolutional neural networks built with TensorFlow an… | 32 | 1578 | maintenance |
| Temporal Segment Networks (TSN) Official code and pretrained models for Temporal Segment Networks (TSN), a deep learning framework for video action recognition published a… | 32 | 1577 | maintenance |
| kumar-shridhar/PyTorch-BayesianCNN A PyTorch library implementing Bayesian convolutional neural networks with variational inference via Bayes by Backprop. It provides drop-in… | 32 | 1574 | maintenance |
| maxpumperla/elephas Elephas is a Python library that extends Keras to run distributed deep learning training on Apache Spark. It serializes Keras models on the… | 23 | 1574 | maintenance |
| sniklaus/3d-ken-burns A PyTorch reference implementation of the 3D Ken Burns Effect from a Single Image paper, which animates a still photo with a virtual camera… | 67 | 1572 | maintenance |
| IDEA-Research/MaskDINO Official PyTorch implementation of Mask DINO, a unified transformer-based framework for object detection and segmentation, built on detectr… | 23 | 1571 | maintenance |
| HumanAIGC/EMO EMO (Emote Portrait Alive) is a research codebase from Alibaba's Institute for Intelligent Computing that generates expressive talking port… | 26 | 7580 | experimental |
| AlexHex7/Non-local_pytorch A PyTorch implementation of the Non-local Neural Block from the paper 'Non-local Neural Networks', providing multiple variants (concatenati… | 32 | 1566 | maintenance |
| vlawhern/arl-eegmodels A collection of well-validated convolutional neural network models (EEGNet, DeepConvNet, ShallowConvNet) for EEG signal classification, imp… | 32 | 1565 | maintenance |
| QingyongHu/RandLA-Net Official TensorFlow implementation of RandLA-Net, a neural architecture for efficient semantic segmentation of large-scale 3D point clouds,… | 32 | 1563 | maintenance |
| V2AI/Det3D Det3D is a PyTorch-based toolbox for 3D object detection from point clouds, offering implementations of models like PointPillars, SECOND, a… | 32 | 1562 | maintenance |
| genforce/interfacegan InterFaceGAN is a Python research library that interprets the latent space of pretrained GANs (PGGAN, StyleGAN) to find semantic subspaces … | 32 | 1561 | maintenance |
| msracver/FCIS FCIS is the official MXNet implementation of the CVPR 2017 paper 'Fully Convolutional Instance-aware Semantic Segmentation', which won firs… | 32 | 1560 | maintenance |
| bfelbo/DeepMoji DeepMoji is a deep learning model trained on 1.2 billion tweets with emojis to understand emotional language, with code for scoring texts, … | 32 | 1556 | maintenance |
| vt-vl-lab/FGVC FGVC is a PyTorch implementation of the ECCV 2020 paper 'Flow-edge Guided Video Completion'. It completes missing regions in videos by extr… | 32 | 1554 | maintenance |
| JingyunLiang/VRT VRT is the official PyTorch implementation of the paper 'VRT: A Video Restoration Transformer', a transformer-based model for video restora… | 65 | 1553 | maintenance |
| Tencent/TurboTransformers A fast, user-friendly C++/Python runtime for transformer model inference (BERT, ALBERT, RoBERTa, GPT2, decoders) on CPU and GPU. It works a… | 34 | 1551 | maintenance |
| JiaRenChang/PSMNet PSMNet is the official PyTorch implementation of the CVPR 2018 paper 'Pyramid Stereo Matching Network' for stereo depth estimation. It uses… | 32 | 1551 | maintenance |
| YoYo000/MVSNet MVSNet is a deep learning architecture for depth map inference from unstructured multi-view images, and R-MVSNet is its recurrent extension… | 32 | 1548 | maintenance |
| caogang/wgan-gp A PyTorch implementation of the 'Improved Training of Wasserstein GANs' (WGAN-GP) paper, covering toy datasets, MNIST, CIFAR-10, and charac… | 32 | 1546 | maintenance |
| google-research/big_transfer Official repository for the Big Transfer (BiT) paper, providing ResNet models pre-trained on ImageNet and ImageNet-21k for transfer learnin… | 10 | 1541 | maintenance |
| poloclub/ganlab GAN Lab is an interactive, browser-based visualization tool for learning and experimenting with Generative Adversarial Networks. Built with… | 52 | 1538 | maintenance |
| gpleiss/efficient_densenet_pytorch A memory-efficient PyTorch implementation of DenseNets that uses gradient checkpointing to reduce feature map memory consumption from quadr… | 32 | 1536 | maintenance |
| lucidrains/lambda-networks A PyTorch implementation of Lambda Networks, featuring the λ layer that models long-range interactions by transforming contexts into linear… | 23 | 1530 | maintenance |
| yu4u/age-gender-estimation A Keras/TensorFlow implementation of a convolutional neural network that estimates age and gender from face images, trained on the IMDB-WIK… | 23 | 1521 | maintenance |
| junyanz/BicycleGAN A PyTorch implementation of BicycleGAN, a model for multimodal image-to-image translation that generates diverse outputs from a single inpu… | 32 | 1516 | maintenance |
| shaoxiongji/federated-learning A PyTorch implementation of the FedAvg federated learning algorithm reproducing the McMahan et al. AISTATS 2017 paper. It includes experime… | 32 | 1516 | maintenance |
| maderix/ANE A research project demonstrating backpropagation and neural network training directly on Apple's Neural Engine using reverse-engineered pri… | 44 | 7275 | experimental |
| krasserm/super-resolution A TensorFlow 2.x implementation of EDSR, WDSR, and SRGAN models for single image super-resolution, with a high-level training API and DIV2K… | 32 | 1514 | maintenance |
| tanluren/yolov3-channel-and-layer-pruning A Python toolkit built on ultralytics/yolov3 that implements channel pruning, layer pruning, and knowledge distillation for YOLOv3/v4 (incl… | 32 | 1514 | maintenance |
| Eric-mingjie/rethinking-network-pruning A PyTorch research codebase reproducing the ICLR 2019 paper 'Rethinking the Value of Network Pruning', which shows pruned models trained fr… | 32 | 1513 | maintenance |
| marsauto/europilot Europilot is a Python toolkit that bridges Euro Truck Simulator 2 with deep-learning frameworks, enabling end-to-end self-driving research … | 32 | 1513 | maintenance |
| FudanNLP/fitlog fitlog (fast + git + log) is a Python tool that helps deep learning practitioners record training logs and manage experiment code, combinin… | 23 | 1511 | maintenance |
| yulunzhang/RCAN PyTorch implementation of RCAN, a very deep residual channel attention network for single image super-resolution from an ECCV 2018 paper. I… | 35 | 1510 | maintenance |
| sigsep/open-unmix-pytorch Open-Unmix is a PyTorch deep learning reference implementation for music source separation, with pre-trained models that split pop music in… | 23 | 1509 | maintenance |
| SOLIDER SOLIDER is a semantic-controllable self-supervised learning framework that learns general human representations from massive unlabeled huma… | 32 | 1508 | maintenance |
| nlpyang/BertSum BertSum is the official PyTorch implementation of the paper 'Fine-tune BERT for Extractive Summarization', providing preprocessing pipeline… | 32 | 1505 | maintenance |
| luuuyi/CBAM.PyTorch A non-official PyTorch re-implementation of the CBAM (Convolutional Block Attention Module) paper from ECCV 2018. It provides channel and s… | 32 | 1504 | maintenance |
| AITTSMD/MTCNN-Tensorflow A TensorFlow reproduction of MTCNN (Multi-task Cascaded Convolutional Networks) for joint face detection and facial landmark alignment. It … | 32 | 1502 | maintenance |
| jina-ai/finetuner Jina AI's Finetuner is a Python library for task-oriented fine-tuning of pretrained models like BERT and CLIP to produce better embeddings … | 10 | 1502 | maintenance |
| vacancy/Synchronized-BatchNorm-PyTorch A PyTorch library implementing Synchronized Batch Normalization, which computes batch statistics across all GPUs during multi-device traini… | 32 | 1501 | maintenance |
| mpezeshki/pytorch_forward_forward A PyTorch implementation of Geoffrey Hinton's forward-forward (FF) training algorithm, an alternative to back-propagation that computes gra… | 32 | 1500 | maintenance |
| CNN Image Retrieval A PyTorch toolbox for training and evaluating convolutional neural networks for image retrieval, implementing the authors' TPAMI 2018 and E… | 23 | 1500 | maintenance |
| NVIDIAGameWorks/kaolin-wisp NVIDIA Kaolin Wisp is a PyTorch library and engine for neural fields research, built on NVIDIA Kaolin Core. It provides differentiable rend… | 23 | 1500 | maintenance |
| facebookresearch/UnsupervisedMT The original implementation of phrase-based (PBSMT) and neural (NMT) unsupervised machine translation models from the EMNLP 2018 paper by F… | 10 | 1500 | maintenance |
| Swall0w/torchstat torchstat is a lightweight neural network analyzer for PyTorch that reports parameter counts, FLOPs, multiply-adds, and memory usage per la… | 23 | 1499 | maintenance |
| DeepVoltaire/AutoAugment An unofficial Python implementation of the AutoAugment data augmentation policies learned for ImageNet, CIFAR-10, and SVHN, built on Pillow… | 32 | 1493 | maintenance |
| thu-ml/unidiffuser UniDiffuser is a unified diffusion framework that fits marginal, conditional, and joint distributions across image and text modalities in a… | 31 | 1488 | maintenance |
| pathak22/noreward-rl TensorFlow implementation of the ICML 2017 paper 'Curiosity-driven Exploration by Self-supervised Prediction', training RL agents with an i… | 32 | 1487 | maintenance |
| chengdazhi/Deformable-Convolution-V2-PyTorch A PyTorch implementation of Deformable Convolution V2 (DCNv2) custom CUDA operators, ported from the original MXNet implementation. It prov… | 32 | 1486 | maintenance |
| speedinghzl/CCNet Official PyTorch implementation of CCNet, a Criss-Cross Attention network for semantic segmentation published at ICCV 2019 and TPAMI 2020. … | 32 | 1486 | maintenance |