Open-source deep-learning software
2663 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.
2663 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| facebookarchive/fb.resnet.torch A Torch (Lua) implementation of ResNet residual networks for image classification, with training scripts for ImageNet and pretrained models… | 10 | 2361 | abandoned |
| achillesrasquinha/bulbea A Python library for stock market prediction and modelling using deep learning, built on TensorFlow with RNN models for price forecasting a… | 32 | 2334 | abandoned |
| openai/improved-gan Reference implementation of the techniques from the OpenAI paper 'Improved Techniques for Training GANs' (arXiv:1606.03498), including semi… | 10 | 2332 | abandoned |
| isl-org/DPT DPT (Dense Prediction Transformers) is Intel's implementation of Vision Transformers for dense prediction tasks, providing pretrained model… | 10 | 2330 | abandoned |
| openai/finetune-transformer-lm Reference code and model for OpenAI's paper 'Improving Language Understanding by Generative Pre-Training' (the original GPT-1), implemented… | 10 | 2307 | abandoned |
| gluon-api/gluon-api Gluon API is a clear, concise, and efficient interface for building deep learning models with an imperative programming style, originally d… | 10 | 2293 | abandoned |
| samjabrahams/tensorflow-on-raspberry-pi A repository providing pre-built TensorFlow wheels and installation scripts for the Raspberry Pi, created before official support existed. … | 23 | 2257 | abandoned |
| Pointer-Generator Networks (Get To The Point) Reference implementation of the pointer-generator network from the ACL 2017 paper 'Get To The Point: Summarization with Pointer-Generator N… | 32 | 2191 | abandoned |
| andersbll/neural_artistic_style A Python command-line implementation of the Neural Algorithm of Artistic Style (Gatys et al., 2015) that transfers the style of one image o… | 32 | 2169 | abandoned |
| paarthneekhara/text-to-image An experimental TensorFlow implementation of text-to-image synthesis using Skip Thought Vectors and the GAN-CLS algorithm from the Generati… | 32 | 2164 | abandoned |
| facebookresearch/SparseConvNet A PyTorch library for training Submanifold Sparse Convolutional Networks, providing spatially-sparse convolutions that operate efficiently … | 10 | 2145 | abandoned |
| neuralmagic/sparseml SparseML is a Python library for applying sparsification recipes (pruning, quantization, sparsity) to neural networks with a few lines of c… | 10 | 2144 | abandoned |
| facebookresearch/darkforestGo DarkForest is a computer Go game engine developed at Facebook AI Research, powered by deep neural networks and Monte Carlo tree search. It … | 10 | 2096 | abandoned |
| openai/image-gpt OpenAI's official code and pre-trained models for iGPT (image GPT), a GPT-2-style transformer adapted to generate and classify images as pi… | 10 | 2094 | abandoned |
| LantaoYu/SeqGAN A Python/TensorFlow implementation of SeqGAN, the Sequence Generative Adversarial Nets with Policy Gradient model from the AAAI-17 paper. I… | 32 | 2092 | abandoned |
| ajbrock/Neural-Photo-Editor A GUI application for editing natural photos using generative neural networks (GANs/VAEs), implementing the Introspective Adversarial Netwo… | 32 | 2076 | abandoned |
| intel/intel-extension-for-pytorch A Python package extending official PyTorch with Intel-specific optimizations for CPUs and GPUs, including quantization and LLM inference a… | 10 | 2012 | abandoned |
| facebookresearch/video-nonlocal-net A research codebase from Facebook AI implementing Non-local Neural Networks for video classification, built on the Caffe2 framework. It rep… | 10 | 1990 | abandoned |
| keras-team/keras-applications Keras Applications provides reference implementations of popular deep learning models (e.g., ResNet, VGG, MobileNet) for use with Keras. Th… | 10 | 1989 | abandoned |
| openai/pixel-cnn A Python/TensorFlow implementation of PixelCNN++, an autoregressive generative model for images with discretized logistic mixture likelihoo… | 10 | 1957 | abandoned |
| facebookresearch/ResNeXt A Torch (Lua) implementation of the ResNeXt architecture from the paper 'Aggregated Residual Transformations for Deep Neural Networks', bui… | 10 | 1927 | abandoned |
| U-Net Tensorflow implementation A generic U-Net implementation built on TensorFlow 1.x for training image segmentation models on arbitrary imaging data. Originally develop… | 23 | 1909 | abandoned |
| notadamking/RLTrader RLTrader is a Python library providing a cryptocurrency trading environment built on OpenAI's gym, using deep reinforcement learning to tra… | 23 | 1867 | abandoned |
| jiesutd/LatticeLSTM A PyTorch implementation of Lattice LSTM for Chinese Named Entity Recognition, accompanying an ACL 2018 paper. It combines character-based … | 32 | 1832 | abandoned |
| kuz/DeepMind-Atari-Deep-Q-Learner The original DQN 3.0 source code published by DeepMind alongside the 2015 Nature paper 'Human-level control through deep reinforcement lear… | 32 | 1830 | abandoned |
| zjy-ucas/ChineseNER A TensorFlow demo implementing a bidirectional LSTM-CRF model for Chinese named entity recognition. It includes training and evaluation scr… | 32 | 1823 | abandoned |
| tensorflow/fold TensorFlow Fold is a Python library for building TensorFlow models that consume structured data, where the computation graph structure depe… | 10 | 1816 | abandoned |
| erikwijmans/Pointnet2_PyTorch A PyTorch implementation of Pointnet2/Pointnet++ for deep learning on point clouds, including custom CUDA ops for GPU-only execution. It su… | 56 | 1812 | abandoned |
| ruotianluo/pytorch-faster-rcnn A PyTorch 1.0 implementation of the Faster R-CNN object detection framework, based on Xinlei Chen's tf-faster-rcnn, supporting VGG16, ResNe… | 23 | 1810 | abandoned |
| NVlabs/few-shot-vid2vid A PyTorch implementation of few-shot photorealistic video-to-video translation from NVIDIA Research (NeurIPS 2019), generating realistic vi… | 32 | 1795 | abandoned |
| keplr-io/quiver Quiver is a Python library (quiver_engine) that launches an interactive web dashboard to visualize layer activations of Keras convolutional… | 32 | 1784 | abandoned |
| longcw/faster_rcnn_pytorch A PyTorch re-implementation of Faster R-CNN for object detection, based on the original py-faster-rcnn and TFFRCNN projects. It supports tr… | 32 | 1779 | abandoned |
| traveller59/second.pytorch A PyTorch implementation of the SECOND 3D object detector for LiDAR point clouds, supporting KITTI and NuScenes datasets with sparse convol… | 32 | 1777 | abandoned |
| tomlepaine/fast-wavenet A Python/TensorFlow library implementing an efficient O(L) generation algorithm for Wavenet-style autoregressive models using dynamic progr… | 32 | 1769 | abandoned |
| gram-ai/capsule-networks A barebones CUDA-enabled PyTorch implementation of the CapsNet architecture from the NIPS 2017 paper 'Dynamic Routing Between Capsules' by … | 32 | 1757 | abandoned |
| TuSimple/mx-maskrcnn An MXNet implementation of the Mask R-CNN instance segmentation model, built on top of the mx-rcnn Faster R-CNN codebase. It includes train… | 32 | 1753 | abandoned |
| facebookarchive/MemNN Facebook AI Research's reference implementations of memory-augmented neural networks (MemN2N, Key-Value Memory Networks, Entity Networks) w… | 10 | 1753 | abandoned |
| facebookresearch/TransCoder TransCoder is a PyTorch implementation of an unsupervised neural model that translates source code between Java, C++, and Python 3. It is a… | 10 | 1729 | abandoned |
| lukalabs/cakechat CakeChat is a Python backend for building emotional generative chatbots using a hierarchical recurrent encoder-decoder (seq2seq) architectu… | 10 | 1708 | abandoned |
| ramprs/grad-cam Official Torch (Lua) implementation of Grad-CAM, the ICCV 2017 gradient-weighted class activation mapping technique for producing visual ex… | 32 | 1671 | abandoned |
| ry/tensorflow-resnet An implementation of the ResNet deep residual learning model in TensorFlow, including a tool to convert Kaiming He's published Caffe pretra… | 10 | 1665 | abandoned |
| Zehaos/MobileNet A TensorFlow implementation of Google's MobileNets, efficient convolutional neural networks for mobile vision applications, including Image… | 32 | 1657 | abandoned |
| NNVM NNVM was a computation-graph intermediate representation and compiler front-end for deep learning frameworks, serving as the graph-level op… | 10 | 1649 | abandoned |
| openai/sparse_attention A Python library of sparse attention primitives from OpenAI's Sparse Transformers paper, including fused normal attention and strided/fixed… | 10 | 1612 | abandoned |
| facebookresearch/ClassyVision Classy Vision is an end-to-end PyTorch framework for image and video classification, offering a modular API for computer vision research wi… | 10 | 1607 | abandoned |
| jcjohnson/densecap DenseCap is a Torch implementation of a fully convolutional localization network that performs dense captioning: detecting objects in image… | 32 | 1599 | abandoned |
| keras-team/keras-contrib Keras-contrib is the official community extension repository for the Keras deep learning library, providing additional layers, activations,… | 10 | 1586 | abandoned |
| carpedm20/deep-rl-tensorflow A TensorFlow implementation of several Deep Reinforcement Learning papers, including DQN, Double DQN, and Dueling networks, for training ag… | 32 | 1580 | abandoned |
| rwightman/gen-efficientnet-pytorch A PyTorch library providing generic implementations and pretrained weights for compute-efficient image classification models such as Effici… | 32 | 1576 | abandoned |
| xunhuang1995/AdaIN-style Torch (Lua) implementation of the ICCV 2017 paper 'Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization'. It applies … | 32 | 1569 | abandoned |
| longcw/yolo2-pytorch A PyTorch implementation of the YOLOv2 real-time object detection model, based on darknet and darkflow. It includes training and inference … | 32 | 1561 | abandoned |
| NVIDIA/OpenSeq2Seq OpenSeq2Seq is a TensorFlow-based toolkit for building and training sequence-to-sequence models for neural machine translation, speech reco… | 10 | 1559 | abandoned |
| wizyoung/YOLOv3_TensorFlow A pure TensorFlow implementation of the YOLOv3 real-time object detection model, including weight conversion from darknet, training, and ev… | 23 | 1550 | abandoned |
| fzliu/style-transfer A Python implementation of the Gatys et al. neural style transfer algorithm built on Caffe, applying the artistic style of one image onto a… | 32 | 1534 | abandoned |
| openai/generating-reviews-discovering-sentiment Research code accompanying the OpenAI paper 'Learning to Generate Reviews and Discovering Sentiment', providing a byte-level multiplicative… | 10 | 1520 | abandoned |
| chenriwei/DeepFace A deep learning face analysis toolkit built on Caffe, implementing face detection, facial keypoint (alignment) detection, and face verifica… | 32 | 1507 | abandoned |
| soumith/dcgan.torch A Torch (Lua) implementation of the DCGAN paper for training deep convolutional generative adversarial networks that generate images. It su… | 32 | 1488 | abandoned |
| Bittensor The Bittensor Python SDK and btcli CLI for interacting with the Bittensor decentralized machine intelligence network, where subnets produce… | 10 | 1469 | abandoned |
| dhwajraj/deep-siamese-text-similarity A TensorFlow implementation of a deep siamese LSTM network that learns phrase and sentence similarity using character-level and word-level … | 32 | 1414 | abandoned |
| seathiefwang/FaceRecognition-tensorflow A face recognition neural network trained with TensorFlow, implemented in Python. It provides a model for identifying faces in images using… | 32 | 1405 | abandoned |
| raghakot/keras-resnet A Keras implementation of Residual Networks (ResNet) using the Keras 1.0 functional API, supporting both Theano and TensorFlow backends. It… | 32 | 1389 | abandoned |
| bonlime/keras-deeplab-v3-plus A Keras implementation of the DeepLab v3+ semantic image segmentation model with pretrained weights imported from the original TensorFlow c… | 23 | 1374 | abandoned |
| NiftyNet NiftyNet is a TensorFlow-based open-source convolutional neural networks platform for research in medical image analysis and image-guided t… | 10 | 1374 | abandoned |
| TorchSSL/TorchSSL TorchSSL is a PyTorch-based toolbox for semi-supervised learning that implements popular SSL algorithms like FixMatch, FlexMatch, MixMatch,… | 32 | 1371 | abandoned |
| andersbll/deeppy DeepPy is a Pythonic deep learning framework built on top of NumPy, with optional CUDA acceleration via the cudarray library. It provides a… | 32 | 1371 | abandoned |
| MIC-DKFZ/medicaldetectiontoolkit A PyTorch framework providing 2D and 3D implementations of object detectors like Mask R-CNN, Retina Net, and Retina U-Net, tailored for med… | 32 | 1361 | abandoned |
| reiinakano/fast-style-transfer-deeplearnjs A browser-based demo of Fast Neural Style Transfer running entirely client-side with the deeplearn.js library, letting users stylize images… | 32 | 1350 | abandoned |
| NervanaSystems/ngraph nGraph is a C++ deep learning graph compiler that accelerates neural network workloads from frameworks like TensorFlow, ONNX, MXNet, and Py… | 10 | 1344 | abandoned |
| isl-org/PhotorealismEnhancement Research code and data from Intel Labs for the paper 'Enhancing Photorealism Enhancement', a neural network that makes rendered images (e.g… | 10 | 1335 | abandoned |
| facebookresearch/multipathnet A Torch-7 implementation of the MultiPath Network for object detection from the BMVC 2016 paper by Facebook AI Research, also supporting Fa… | 10 | 1331 | abandoned |
| trailbehind/DeepOSM DeepOSM is a Python application that trains neural networks with TensorFlow to classify roads and features in satellite imagery using OpenS… | 32 | 1330 | abandoned |
| IDSIA/brainstorm Brainstorm is a Python neural network library designed to be fast, flexible, and fun, supporting multiple computing backends. The project h… | 32 | 1326 | abandoned |
| bamos/dcgan-completion.tensorflow A TensorFlow implementation of semantic image inpainting using DCGANs, based on the paper 'Semantic Image Inpainting with Perceptual and Co… | 32 | 1317 | abandoned |
| happynear/caffe-windows A Windows-specific fork of the Caffe deep learning framework with preconfigured Visual Studio project files, enabling users to build Caffe … | 23 | 1310 | abandoned |
| haarnoja/sac The original reference implementation of Soft Actor-Critic (SAC), a deep reinforcement learning algorithm for training maximum entropy poli… | 32 | 1308 | abandoned |
| piiswrong/deep3d Deep3D is a CNN-based research project that automatically converts 2D images and videos into 3D by estimating per-pixel depth maps and gene… | 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 |
| tianzhi0549/CTPN Reference implementation of CTPN (Connectionist Text Proposal Network) for detecting text lines in natural images, from the ECCV 2016 paper… | 32 | 1286 | abandoned |
| leehomyc/Faster-High-Res-Neural-Inpainting Research code implementing the CVPR 2017 paper 'High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis', written in Lua … | 32 | 1286 | 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 |
| Prinsphield/Wechat_AutoJump A Python bot that automatically plays the WeChat 'Jump Jump' mini-game using computer vision and a CNN coarse-to-fine model to locate the p… | 32 | 1280 | 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 | 1272 | 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 | 1272 | 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 | 1265 | 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 | 1262 | abandoned |
| shekkizh/FCN.tensorflow A TensorFlow implementation of Fully Convolutional Networks (FCN) for semantic segmentation, based on the reference code from the original … | 32 | 1248 | 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 |
| 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 | 1226 | 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 |
| DmitryUlyanov/texture_nets Research code implementing the 'Texture Networks' paper for fast feed-forward texture synthesis and neural style transfer using Torch7. Onc… | 32 | 1224 | 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 |
| 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 | 1182 | abandoned |
| gpleiss/temperature_scaling A small PyTorch module implementing temperature scaling, a post-processing technique that calibrates the overconfident probability outputs … | 44 | 1180 | 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 | 1176 | 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 |
| Blocks Blocks is a Python framework for building and training neural network models on top of Theano. It provides parametrized operations called '… | 23 | 1151 | 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 | 1147 | 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 | 1139 | 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 |