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 |
|---|---|---|---|
| FoundationVision/LlamaGen LlamaGen is a family of autoregressive image generation models that apply next-token prediction, as in Llama-style LLMs, to visual generati… | 25 | 1970 | maintenance |
| ml-jku/hopfield-layers A PyTorch library implementing modern Hopfield networks with continuous states, whose update rule is equivalent to transformer attention. I… | 32 | 1966 | maintenance |
| mit-han-lab/once-for-all Once-for-All (OFA) is a PyTorch library implementing the ICLR 2020 Once-for-All network, which trains a single supernet that can be special… | 23 | 1953 | maintenance |
| Named Entity Recognition with Tensorflow A TensorFlow implementation of a Bi-LSTM + CRF model with character embeddings for named entity recognition and sequence tagging. It trains… | 32 | 1952 | maintenance |
| hukaixuan19970627/yolov5_obb A PyTorch implementation of YOLOv5 extended for oriented (rotated) object detection using Circular Smooth Label (CSL) angle encoding. It pr… | 32 | 1949 | maintenance |
| carefree-creator carefree-creator is a Python library and CLI that serves AI image generation endpoints built on Stable Diffusion and related models, poweri… | 32 | 1936 | maintenance |
| danieldjohnson/biaxial-rnn-music-composition A Python implementation of a biaxial recurrent neural network (LSTM-based) trained to generate classical music from MIDI data. It includes … | 32 | 1929 | maintenance |
| s9xie/hed Reference implementation of Holistically-Nested Edge Detection (HED), a deep learning edge and boundary detection model built on a modified… | 23 | 1928 | maintenance |
| S-LoRA/S-LoRA S-LoRA is a serving system for large language models that scales to thousands of concurrent LoRA adapters on one or more GPUs. It uses Unif… | 10 | 1926 | maintenance |
| Tencent/NeuralNLP-NeuralClassifier NeuralClassifier is a PyTorch-based open-source toolkit for neural text classification, with a focus on hierarchical multi-label classifica… | 52 | 1924 | maintenance |
| black0017/MedicalZooPytorch A PyTorch-based open-source library implementing state-of-the-art 3D (and some 2D) deep neural networks for multi-modal medical image segme… | 32 | 1920 | maintenance |
| appvision-ai/fast-bert Fast-Bert is a Python deep learning library for training and deploying BERT, RoBERTa, and XLNet based models for NLP tasks, starting with m… | 23 | 1915 | maintenance |
| snap-stanford/GraphGym GraphGym is a platform for designing and evaluating Graph Neural Networks (GNNs), built around a highly modularized pipeline covering data … | 23 | 1908 | maintenance |
| WongKinYiu/PyTorch_YOLOv4 A PyTorch implementation of the YOLOv4 real-time object detection model, based on ultralytics/yolov3. It includes research extensions such … | 23 | 1907 | maintenance |
| Pyramid Vision Transformer Official PyTorch implementation of the Pyramid Vision Transformer (PVTv1 and PVTv2) model series, providing pretrained backbone networks fo… | 23 | 1905 | maintenance |
| astorfi/lip-reading-deeplearning A TensorFlow implementation of coupled 3D convolutional neural networks for cross audio-visual matching recognition, accompanying an IEEE A… | 23 | 1902 | maintenance |
| ronghuaiyang/arcface-pytorch A PyTorch implementation of ArcFace, a deep metric learning approach for face recognition that adds angular margin penalties to face embedd… | 32 | 1901 | maintenance |
| NCRF++ NCRF++ is a PyTorch-based toolkit for neural sequence labeling tasks such as NER, POS tagging, and word segmentation. Model architectures c… | 32 | 1901 | maintenance |
| ChenyangSi/FreeU FreeU is a research codebase implementing a training-free method that improves diffusion model sample quality by re-weighting U-Net backbon… | 28 | 1901 | maintenance |
| junshutang/Make-It-3D Make-It-3D is a research codebase from an ICCV 2023 paper that creates high-fidelity 3D content from a single image using a 2D diffusion mo… | 31 | 1898 | maintenance |
| uber/petastorm Petastorm is a Python data access library from Uber that enables single-machine or distributed training and evaluation of deep learning mod… | 52 | 1894 | maintenance |
| zjhuang22/maskscoring_rcnn Official PyTorch implementation of Mask Scoring R-CNN (CVPR 2019), built on maskrcnn-benchmark. It adds a network block that learns the qua… | 32 | 1893 | maintenance |
| TreB1eN/InsightFace_Pytorch A PyTorch reimplementation of InsightFace/ArcFace for face recognition, including backbone models (IR-SE50, MobileFacenet) and pretrained w… | 32 | 1893 | maintenance |
| Ucas-HaoranWei/Vary Official ECCV 2024 implementation of Vary, a method for scaling up the vision vocabulary of large vision-language models. It provides train… | 27 | 1890 | maintenance |
| hexiangnan/neural_collaborative_filtering Reference implementation of the WWW'17 Neural Collaborative Filtering paper, providing GMF, MLP, and NeuMF models for implicit-feedback rec… | 32 | 1887 | maintenance |
| Duankaiwen/CenterNet Official PyTorch implementation of CenterNet, a one-stage keypoint-triplet-based object detector built on CornerNet. It trains from scratch… | 32 | 1886 | maintenance |
| zhoubolei/CAM Reference implementation of Class Activation Mapping (CAM), a CVPR'16 technique that visualizes which image regions a CNN attends to when p… | 32 | 1884 | maintenance |
| salesforce/ctrl CTRL is a 1.63 billion-parameter conditional Transformer language model from Salesforce that generates text controllable via control codes … | 10 | 1877 | maintenance |
| open-mmlab/mmaction MMAction is an open-source PyTorch toolbox for video action understanding, covering action recognition, temporal action detection, and spat… | 32 | 1875 | maintenance |
| Sierkinhane/CRNN_Chinese_Characters_Rec A PyTorch implementation of a CRNN (convolutional recurrent neural network) model for recognizing Chinese characters in images. It includes… | 32 | 1871 | maintenance |
| SSD Keras Implementation A Keras implementation of the Single Shot MultiBox Detector (SSD) object detection architecture, with ports of the original trained weights… | 23 | 1868 | maintenance |
| waleedka/hiddenlayer A lightweight Python library for rendering readable neural network architecture graphs and plotting training metrics for PyTorch, TensorFlo… | 23 | 1867 | maintenance |
| raminmh/liquid_time_constant_networks Official code repository for Liquid Time-Constant Networks (LTCs), a class of continuous-time recurrent neural networks with varying time-c… | 32 | 1865 | maintenance |
| xiaolai-sqlai/mobilenetv3 A PyTorch implementation of the MobileNetV3 architecture with retrained pre-trained weights that outperform the original paper and torchvis… | 32 | 1865 | maintenance |
| magicleap/Atlas Atlas is a PyTorch-based deep learning model from Magic Leap that performs end-to-end 3D scene reconstruction from posed RGB images, produc… | 32 | 1859 | maintenance |
| MrNothing/AI-Blocks AI-Blocks is a WYSIWYG desktop application for visually building machine learning models by dragging objects with attached scripts in a sce… | 23 | 1857 | maintenance |
| ermongroup/ddim Official PyTorch implementation of Denoising Diffusion Implicit Models (DDIM), a faster sampling method for diffusion probabilistic models.… | 32 | 1852 | maintenance |
| nlpodyssey/spago Spago is a self-contained machine learning and NLP library written in pure Go, featuring an asynchronous computation graph with automatic d… | 26 | 1849 | maintenance |
| WangYueFt/dgcnn Author's reference implementation of Dynamic Graph CNN (DGCNN), a neural network module called EdgeConv for learning on 3D point clouds. It… | 32 | 1848 | maintenance |
| Score-Based Generative Modeling through SDEs Official PyTorch implementation of the ICLR 2021 paper 'Score-Based Generative Modeling through Stochastic Differential Equations', unifyin… | 32 | 1848 | maintenance |
| google/gemmlowp gemmlowp is a small, self-contained, headers-only C++ library for low-precision (quantized) general matrix multiplication (GEMM). It provid… | 32 | 1846 | maintenance |
| zetane/viewer Zetane Viewer is a free desktop application that visualizes machine learning models and their internal tensors in 3D, showing architecture,… | 23 | 1846 | maintenance |
| cubiq/ComfyUI_InstantID A ComfyUI custom node providing native InstantID support for identity-preserving image generation with SDXL, implemented without diffusers.… | 30 | 1844 | maintenance |
| microsoft/Cream A collection of Microsoft research projects on neural architecture search (NAS) and efficient Vision Transformers, including AutoFormer, Ti… | 10 | 1844 | maintenance |
| AlexeyAB/Yolo_mark A Windows and Linux GUI application for drawing bounding boxes around objects in images to create labeled training data for YOLO v2/v3 obje… | 32 | 1842 | maintenance |
| Kyubyong/tacotron A heavily documented TensorFlow implementation of Tacotron, a fully end-to-end text-to-speech synthesis model. It includes training, prepro… | 32 | 1835 | maintenance |
| Janspiry/Palette-Image-to-Image-Diffusion-Models An unofficial PyTorch implementation of the Palette paper on image-to-image diffusion models, supporting tasks like inpainting, uncropping,… | 32 | 1833 | maintenance |
| Silent Face Anti-Spoofing An open-source silent face anti-spoofing (liveness detection) project by MiniVision, providing model training code, data preprocessing, tes… | 32 | 1833 | maintenance |
| bubbliiiing/faster-rcnn-pytorch A PyTorch implementation of the Faster R-CNN two-stage object detection model, supporting training on VOC-format datasets with ResNet or VG… | 23 | 1832 | maintenance |
| NVIDIA/semantic-segmentation NVIDIA's PyTorch monorepo implementing the paper 'Hierarchical Multi-Scale Attention for Semantic Segmentation', with pretrained weights an… | 32 | 1831 | maintenance |
| NVlabs/stylegan2-ada NVIDIA's official TensorFlow implementation of StyleGAN2 with adaptive discriminator augmentation (ADA), enabling high-quality GAN training… | 32 | 1829 | maintenance |
| OpenPPL/ppq PPQ (PPL Quantization Tool) is an extensible, high-performance offline neural network quantization framework written in Python. It parses a… | 23 | 1822 | maintenance |
| THUDM/CogDL CogDL is a Python/PyTorch toolkit for graph deep learning that lets researchers train and compare GNN and graph embedding models on tasks l… | 23 | 1820 | maintenance |
| yassouali/pytorch-segmentation A PyTorch library implementing multiple semantic segmentation models (DeepLab V3+, PSPNet, U-Net, SegNet, FCN, ENet, and others) with datas… | 23 | 1818 | maintenance |
| shunsukesaito/PIFu PyTorch implementation of PIFu (Pixel-Aligned Implicit Function), a deep learning method that reconstructs high-resolution 3D surfaces and … | 32 | 1817 | maintenance |
| sshaoshuai/PointRCNN PyTorch implementation of PointRCNN, a two-stage 3D object detector that generates 3D box proposals directly from raw LiDAR point clouds. I… | 32 | 1817 | maintenance |
| google/compare_gan A TensorFlow library from Google Research providing configurable implementations of GAN components: losses, penalties, normalization techni… | 10 | 1815 | maintenance |
| yongzhuo/Keras-TextClassification A Keras-based library for Chinese text classification supporting long/short text, multi-label classification, and sentence pair similarity.… | 23 | 1806 | maintenance |
| rosinality/vq-vae-2-pytorch A PyTorch implementation of VQ-VAE-2 for generating diverse high-fidelity images, including training scripts for the VQ-VAE and PixelSNAIL … | 32 | 1804 | maintenance |
| jquesnelle/yarn Reference implementation of YaRN, an efficient method for extending the context window of large language models, published as an ICLR 2024 … | 29 | 1801 | maintenance |
| zai-org/CogView CogView is a 4-billion-parameter pretrained transformer model for text-to-image image generation, released alongside a NeurIPS 2021 paper. … | 32 | 1799 | maintenance |
| harskish/ganspace GANSpace is a research codebase implementing the NeurIPS 2020 paper on discovering interpretable controls for GANs via PCA in activation sp… | 32 | 1796 | maintenance |
| jkjung-avt/tensorrt_demos A collection of Python demo programs showing how to optimize and run deep learning models (YOLOv4, YOLOv3, SSD, MTCNN, GoogLeNet, MODNet) w… | 46 | 1793 | maintenance |
| dreamoving/dreamoving-project DreaMoving is the official implementation of a diffusion-based controllable video generation framework from Alibaba that produces high-qual… | 27 | 1789 | maintenance |
| ali-vilab/dreamtalk DreamTalk is the official implementation of a diffusion-based framework for generating expressive, audio-driven talking head videos from a … | 27 | 1788 | maintenance |
| idiap/fast-transformers A PyTorch library providing fast transformer implementations with efficient attention mechanisms such as linear attention, designed to scal… | 32 | 1782 | maintenance |
| PANNs Audio Neural Networks PANNs is a collection of large-scale pretrained CNN audio neural networks trained on AudioSet (5000 hours, 527 classes) for audio pattern r… | 32 | 1782 | maintenance |
| wkentaro/pytorch-fcn A PyTorch implementation of Fully Convolutional Networks (FCN) for semantic segmentation, including training code that reproduces the origi… | 10 | 1777 | maintenance |
| princeton-vl/CornerNet-Lite CornerNet-Lite is the official PyTorch implementation of the paper 'CornerNet-Lite: Efficient Keypoint Based Object Detection', providing t… | 32 | 1770 | maintenance |
| facebookresearch/TensorComprehensions Tensor Comprehensions is a C++ library with a Python API that provides a domain-specific language for expressing machine learning workloads… | 10 | 1769 | maintenance |
| nywang16/Pixel2Mesh Pixel2Mesh is the official TensorFlow implementation of the ECCV 2018 paper that generates 3D mesh models from a single RGB image using a g… | 32 | 1768 | maintenance |
| CSAILVision/gandissect GANDissect is a PyTorch-based toolkit for visualizing and understanding the internal neurons of generative adversarial networks, showing ho… | 32 | 1765 | maintenance |
| facebookresearch/votenet VoteNet is the official PyTorch implementation of the ICCV 2019 paper 'Deep Hough Voting for 3D Object Detection in Point Clouds'. It provi… | 10 | 1762 | maintenance |
| huggingface/transfer-learning-conv-ai A clean, commented PyTorch codebase for training a dialog/chatbot agent by transfer learning from OpenAI GPT/GPT-2 language models. It repr… | 10 | 1757 | maintenance |
| Artistic Video Style Transfer A Torch (Lua) implementation of the paper 'Artistic style transfer for videos', which applies the style of a painting to an entire video wh… | 10 | 1753 | maintenance |
| deepset-ai/FARM FARM is a Python framework for fine-tuning and evaluating transformer-based language models for NLP tasks, with a focus on question answeri… | 10 | 1753 | maintenance |
| Lightning-Universe/lightning-bolts Lightning Bolts is a toolbox of pre-built models, callbacks, and datasets that extend PyTorch Lightning for AI/ML research and production. … | 10 | 1753 | maintenance |
| openai/Video-Pre-Training OpenAI's Video PreTraining (VPT) codebase for learning Minecraft agents by watching unlabeled online videos, including behavioral cloning a… | 37 | 1747 | maintenance |
| tkipf/gae A TensorFlow implementation of (Variational) Graph Auto-Encoders from Kipf & Welling's 2016 paper, supporting unsupervised learning, cluste… | 32 | 1743 | maintenance |
| google-research/robotics_transformer A Python library from Google Research implementing RT-1 (Robotics Transformer), a transformer model for end-to-end robotic control with an … | 10 | 1741 | maintenance |
| cszn/DnCNN DnCNN is the official implementation of the TIP 2017 paper 'Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising',… | 32 | 1740 | maintenance |
| DeepCluster DeepCluster is a research codebase from Facebook AI Research implementing the 'Deep Clustering for Unsupervised Learning of Visual Features… | 10 | 1740 | maintenance |
| NVlabs/PWC-Net Official NVIDIA implementation of PWC-Net, a CNN for optical flow estimation using pyramid, warping, and cost volume, released with CVPR 20… | 32 | 1737 | maintenance |
| zijundeng/pytorch-semantic-segmentation A PyTorch library providing implementations of popular semantic segmentation models such as FCN, U-Net, SegNet, PSPNet, GCN, and DUC/HDC. I… | 32 | 1736 | maintenance |
| natethegreate/hent-AI A Python application that automatically detects censor bars and mosaic blurs in illustrated adult content using deep learning (Mask R-CNN) … | 23 | 1734 | maintenance |
| ranahanocka/MeshCNN MeshCNN is a PyTorch library implementing a convolutional neural network that operates directly on 3D triangular meshes, with mesh-specific… | 32 | 1732 | maintenance |
| zhougr1993/DeepInterestNetwork A TensorFlow demo implementation of the Deep Interest Network (DIN) paper for click-through rate prediction, run on the Amazon electronics … | 32 | 1731 | maintenance |
| experiencor/keras-yolo2 A Keras/TensorFlow implementation of the YOLOv2 real-time object detection model with support for training on custom datasets. It offers mu… | 23 | 1731 | maintenance |
| NVIDIA/Cosmos-Tokenizer NVIDIA Cosmos Tokenizer is a suite of neural tokenizers for images and videos that convert visual data into continuous latents or discrete … | 10 | 1729 | maintenance |
| Qihoo360/hbox Hbox (formerly XLearning) is a scheduling platform that runs machine learning and deep learning frameworks like TensorFlow, MXNet, Caffe, a… | 43 | 1728 | maintenance |
| google-research/torchsde A PyTorch library providing differentiable stochastic differential equation (SDE) solvers with GPU support and efficient backpropagation vi… | 10 | 1727 | maintenance |
| DeepMotionEditing/deep-motion-editing A PyTorch-based end-to-end library for editing and rendering 3D character motion, built on SIGGRAPH 2020 research. It provides deep learnin… | 32 | 1726 | maintenance |
| bubbliiiing/unet-pytorch A PyTorch implementation of the U-Net semantic segmentation model with training, prediction, and mIoU evaluation scripts. It supports multi… | 23 | 1726 | maintenance |
| Franck-Dernoncourt/NeuroNER NeuroNER is a Python/TensorFlow program that performs named-entity recognition (NER) using neural networks, with pretrained models and an e… | 23 | 1726 | maintenance |
| Lightning-Universe/lightning-flash Lightning Flash is a high-level PyTorch library built on PyTorch Lightning that provides ready-made 'recipes' for over 15 AI tasks across 7… | 10 | 1726 | maintenance |
| svip-lab/impersonator A PyTorch implementation of Liquid Gating GAN (ICCV 2019) that performs human motion imitation, appearance transfer, and novel view synthes… | 32 | 1718 | maintenance |
| PyNET DPED is a Python/TensorFlow implementation of a deep convolutional network approach that translates ordinary smartphone photos into DSLR-qu… | 46 | 1710 | maintenance |
| Maratyszcza/NNPACK NNPACK is a C99 acceleration package providing high-performance SIMD and multi-core CPU implementations of neural network layers, especiall… | 32 | 1710 | maintenance |
| airaria/TextBrewer TextBrewer is a PyTorch-based knowledge distillation toolkit for NLP models. It provides an easy-to-use framework implementing state-of-the… | 23 | 1709 | maintenance |
| Fyusion/LLFF LLFF (Local Light Field Fusion) is a TensorFlow implementation of the SIGGRAPH 2019 paper for novel view synthesis from sparse input images… | 32 | 1708 | maintenance |