domain: deep-learning
2771 products, primary matches first, then adoption-weighted; health v2 shown.
| Product | Health v2 | Stars | Maturity |
|---|---|---|---|
| google-ai-edge/litert-torch LiteRT Torch is a Python library that converts PyTorch models into .tflite format for running with LiteRT on Android, iOS, and IoT devices.… | 87 | 1091 | active |
| lucidrains/tab-transformer-pytorch A PyTorch implementation of the TabTransformer architecture, an attention-based neural network for tabular data, also including the FT Tran… | 70 | 1091 | stable |
| geoopt/geoopt Geoopt is a PyTorch library providing manifold-aware optimizers and manifold tensor containers for Riemannian optimization. It implements R… | 59 | 1091 | active |
| yerfor/Real3DPortrait Official PyTorch implementation of Real3D-Portrait, an ICLR 2024 Spotlight paper for one-shot realistic 3D talking portrait synthesis. It g… | 26 | 1091 | active |
| localai-org/depth-anything.cpp A from-scratch C++17/ggml port of ByteDance's Depth Anything 2 and 3 models for dependency-free monocular metric depth and camera pose infe… | 58 | 1090 | active |
| flagos-ai/FlagGems FlagGems is a high-performance operator library for large language models written in the Triton language, providing backend-neutral GPU ker… | 89 | 1089 | active |
| mymusise/ChatGLM-Tuning A Python toolkit for fine-tuning the ChatGLM-6B large language model using LoRA (Low-Rank Adaptation) with the Alpaca dataset. It provides … | 10 | 3740 | maintenance |
| rhymes-ai/Aria Aria is an open multimodal native Mixture-of-Experts (MoE) model with 25.3B total parameters (3.9B activated per token) and a 64K multimoda… | 23 | 1087 | active |
| ndif-team/nnsight nnsight is a Python library for interpreting and intervening on the internals of deep learning models, built on PyTorch. It lets researcher… | 88 | 1085 | active |
| DSE-MSU/DeepRobust DeepRobust is a PyTorch library for adversarial robustness research, providing implementations of attack and defense methods for both image… | 45 | 1085 | active |
| Alpha-VLLM/Lumina-mGPT-2.0 Lumina-mGPT 2.0 is a stand-alone decoder-only autoregressive model trained from scratch that unifies a broad range of image generation task… | 42 | 1084 | active |
| GraphSAGE Reference implementation of the GraphSAGE algorithm for inductive representation learning on large graphs using stochastic graph convolutio… | 32 | 3719 | maintenance |
| bytedance/byteps BytePS is a high-performance parameter server framework for distributed deep neural network training, supporting TensorFlow, Keras, PyTorch… | 10 | 3717 | maintenance |
| vladmandic/face-api FaceAPI is a JavaScript library built on TensorFlow/JS that provides AI-powered face detection, rotation tracking, face description and rec… | 10 | 1083 | active |
| kimiyoung/transformer-xl Official implementation of Transformer-XL, an attention-based language model architecture that extends context beyond a fixed length via se… | 32 | 3714 | maintenance |
| agi-brain/xuance XuanCe is an open-source Python library of deep reinforcement learning (DRL) and multi-agent reinforcement learning (MARL) algorithm implem… | 95 | 1082 | active |
| NVlabs/Fast-dLLM NVIDIA's official implementation of Fast-dLLM, a family of training-free and fine-tuning-based acceleration techniques for diffusion-based … | 57 | 1082 | active |
| charlesq34/pointnet2 Official TensorFlow implementation of PointNet++, a deep neural network that learns hierarchical features on 3D point clouds using metric-s… | 32 | 3700 | maintenance |
| Stonesjtu/pytorch_memlab A Python library providing line-level CUDA memory profiling and tensor inspection tools for PyTorch. It helps debug out-of-memory errors by… | 94 | 1077 | active |
| Geekgineer/YOLOs-CPP YOLOs-CPP is a production-ready, cross-platform C++ inference library for the YOLO model family (v5 through YOLO26), built on ONNX Runtime … | 88 | 1076 | active |
| facebookresearch/hiera Hiera is the official PyTorch implementation of a hierarchical vision transformer from Meta AI (ICML 2023 Oral). It achieves state-of-the-a… | 20 | 1074 | active |
| cleardusk/3DDFA A PyTorch implementation of the TPAMI 2017 paper 'Face Alignment in Full Pose Range: A 3D Total Solution' (3DDFA). It fits a 3D Morphable M… | 23 | 3677 | maintenance |
| meta-pytorch/monarch Monarch is a distributed programming framework for PyTorch built on scalable actor messaging, with actors grouped into meshes, supervision-… | 80 | 1073 | active |
| zju3dv/InfiniDepth InfiniDepth is a CVPR 2026 research library for monocular depth estimation that represents depth as neural implicit fields, allowing depth … | 53 | 1073 | active |
| facebookresearch/CutLER CutLER is a research codebase from Meta FAIR for training object detection and instance segmentation models without human annotations, usin… | 66 | 1072 | active |
| open-gigaai/giga-train GigaTrain is an efficient and scalable Python training framework for large AI models, supporting distributed multi-GPU/multi-node execution… | 62 | 1072 | active |
| mert-kurttutan/torchview torchview is a Python library that visualizes PyTorch models as visual graphs, showing tensors, modules, torch functions, and input/output … | 54 | 1072 | active |
| AILab-CVC/UniRepLKNet UniRepLKNet is a large-kernel ConvNet architecture (CVPR 2024, TPAMI 2025) that provides universal perception across image, audio, video, p… | 43 | 1072 | stable |
| NVIDIA-Merlin/HugeCTR HugeCTR is a GPU-accelerated deep learning framework from NVIDIA designed for training and inference of large recommender models, especiall… | 77 | 1071 | active |
| memoavatar/memo MEMO is an open-weight diffusion model for generating expressive, identity-consistent talking videos from a single reference image and an a… | 40 | 1070 | active |
| juntang-zhuang/Adabelief-Optimizer AdaBelief is a deep learning optimizer that adapts step sizes based on the 'belief' in observed gradients, combining Adam's fast convergenc… | 32 | 1070 | stable |
| yeates/PromptFix PromptFix is a PyTorch implementation of a diffusion-model-based image restoration model that follows natural language instructions to fix … | 24 | 1070 | active |
| princeton-nlp/SimCSE SimCSE is a Python library and research codebase implementing simple contrastive learning for sentence embeddings, with pre-trained unsuper… | 23 | 3654 | maintenance |
| guochengqian/PointNeXt PointNeXt is the official PyTorch implementation of the NeurIPS'22 paper that improves PointNet++ via better training and model scaling str… | 93 | 1067 | stable |
| THUDM/GLM GLM is a general language model pretrained with an autoregressive blank-filling objective, released with pretrained checkpoints and fine-tu… | 32 | 3652 | maintenance |
| microsoft/Biodiversity Microsoft AI for Good Lab's biodiversity research hub providing open-source AI models and tools for wildlife monitoring and conservation, i… | 88 | 1066 | active |
| hujie-frank/SENet Official Caffe/CUDA implementation of Squeeze-and-Excitation Networks (SENet), channel-attention building blocks for convolutional neural n… | 32 | 3646 | maintenance |
| gangweix/pixel-perfect-depth Pixel-Perfect Depth is a monocular depth estimation model based on pixel-space diffusion transformers that produces flying-pixel-free depth… | 49 | 1064 | active |
| lucidrains/mlp-mixer-pytorch A PyTorch implementation of Google AI's MLP-Mixer, an all-MLP architecture for image classification that uses neither convolutions nor atte… | 48 | 1064 | active |
| abertsch72/unlimiformer Unlimiformer is a method and official implementation for augmenting pretrained encoder-decoder transformers with retrieval-based attention,… | 30 | 1062 | stable |
| vijishmadhavan/ArtLine ArtLine is a deep learning project that converts portrait photos into line art portraits, with a ControlNet-based variant that adjusts styl… | 32 | 3630 | maintenance |
| NVlabs/SegFormer Official PyTorch implementation of SegFormer, a transformer-based semantic segmentation framework with a hierarchical encoder and lightweig… | 32 | 3629 | maintenance |
| InternRobotics/InternNav InternNav is an open-source PyTorch-based toolbox for building embodied navigation foundation models, supporting vision-language navigation… | 58 | 1061 | active |
| LeCAR-Lab/human2humanoid Official implementation of H2O and OmniH2O, reinforcement-learning-based systems for real-time whole-body teleoperation of full-sized human… | 25 | 1060 | active |
| NVIDIA/DreamDojo NVIDIA's official PyTorch codebase for DreamDojo, a generalist robot world model pretrained on 44k hours of human egocentric video and post… | 48 | 1059 | active |
| mgsalem/Tensorflow-Project-Template A Python project template that provides a recommended folder structure and object-oriented skeleton (base model, base trainer, data loader,… | 32 | 3616 | maintenance |
| NousResearch/DisTrO DisTrO is a family of low-latency distributed optimizers that reduce inter-GPU communication requirements by three to four orders of magnit… | 44 | 1058 | active |
| YunYang1994/tensorflow-yolov3 A TensorFlow 1.x implementation of the YOLOv3 real-time object detector, reproducing the 'YOLOv3: An Incremental Improvement' paper. It sup… | 23 | 3614 | maintenance |
| open-gigaai/giga-models GigaModels is an open-source Python framework providing pipelines for training, inference, deployment, and compression of multi-modal, gene… | 62 | 1057 | active |
| henry123-boy/SpaTracker SpatialTracker is the official PyTorch implementation of a CVPR 2024 Highlight paper that tracks any 2D pixels in 3D space from RGB or RGBD… | 41 | 1057 | active |
| danijar/dreamerv2 A TensorFlow 2 implementation of the DreamerV2 model-based reinforcement learning agent that learns world models from high-dimensional imag… | 32 | 1056 | stable |
| apache/singa Apache SINGA is a distributed deep learning platform for training neural networks across multiple devices and machines. It provides a C++ c… | 64 | 3606 | maintenance |
| yoyo-nb/Thin-Plate-Spline-Motion-Model The official PyTorch implementation of the CVPR 2022 paper 'Thin-Plate Spline Motion Model for Image Animation'. It animates a source image… | 32 | 3604 | maintenance |
| williamyang1991/VToonify Official PyTorch implementation of VToonify, a SIGGRAPH Asia 2022 framework for controllable high-resolution portrait video style transfer … | 32 | 3584 | maintenance |
| showlab/MotionDirector MotionDirector is a research library for customizing text-to-video diffusion models to generate videos with desired motions from a small se… | 27 | 1050 | active |
| drprojects/superpoint_transformer Official PyTorch implementation of Superpoint Transformer (ICCV'23), SuperCluster (3DV'24), and EZ-SP (ICRA'26) for efficient semantic and … | 64 | 1049 | active |
| zhuzilin/ring-flash-attention A Python library implementing RingAttention on top of FlashAttention for distributed long-context transformer training. It provides varlen … | 44 | 1049 | active |
| qqlu/Entity EntitySeg is an open-source PyTorch toolbox for open-world, high-quality image segmentation, built on Detectron2. It aggregates multiple re… | 32 | 1048 | active |
| arcee-ai/DistillKit DistillKit is an open-source Python toolkit for knowledge distillation of large language models, supporting both online and offline distill… | 60 | 1047 | active |
| Xilinx/finn FINN is an open-source dataflow compiler from AMD/Xilinx that generates highly efficient FPGA accelerators for quantized neural network (QN… | 68 | 1046 | active |
| facebookresearch/pytorchvideo PyTorchVideo is a deep learning library from Facebook Research focused on video understanding research, built on PyTorch. It provides reusa… | 59 | 3566 | maintenance |
| 3DTopia/3DTopia-XL 3DTopia-XL is a 3D diffusion transformer model that generates high-quality 3D assets with PBR materials from a single image or text prompt … | 37 | 1045 | active |
| Tencent-Hunyuan/InstantCharacter InstantCharacter is a tuning-free framework built on diffusion transformers that generates character-consistent images from a single refere… | 29 | 1045 | active |
| Shawn1993/cnn-text-classification-pytorch A PyTorch implementation of Kim's CNN architecture for sentence classification, reproducing results from the paper 'Convolutional Neural Ne… | 65 | 1043 | active |
| ZhengYinan-AIR/Diffusion-Planner Official PyTorch implementation of Diffusion Planner, an ICLR 2025 Oral paper using a DiT-based diffusion model for closed-loop autonomous … | 53 | 1043 | active |
| zai-org/SCAIL SCAIL is the official inference implementation of a 14B diffusion transformer model that generates studio-grade character animation videos … | 52 | 1043 | active |
| jiachenzhu/DyT Official PyTorch implementation of DynamicTanh (DyT), a learnable element-wise tanh operation that replaces normalization layers in Transfo… | 26 | 1043 | active |
| Xiaoqi-Zhao-DLUT/MSNet-M2SNet Official PyTorch implementations of MSNet and M2SNet, multi-scale subtraction networks for medical image segmentation such as polyp, lung i… | 74 | 1042 | active |
| zju3dv/EfficientLoFTR Efficient LoFTR is a PyTorch implementation of a semi-dense local feature matching model that matches keypoints between image pairs with sp… | 40 | 1042 | active |
| PetarV-/GAT Reference implementation of Graph Attention Networks (GAT), the ICLR 2018 model by Veličković et al., written in TensorFlow 1.x with a mini… | 32 | 3548 | maintenance |
| thuiar/MMSA MMSA is a unified Python framework for multimodal sentiment analysis, supporting 15 MSA models and datasets like MOSI, MOSEI, and CH-SIMS. … | 23 | 1041 | active |
| foolwood/SiamMask Official PyTorch implementation of SiamMask, a deep learning framework for fast online visual object tracking and video object segmentation… | 35 | 3547 | maintenance |
| tonbistudio/turboquant-pytorch A from-scratch PyTorch implementation of Google's TurboQuant (ICLR 2026) algorithm for compressing LLM key-value caches, including an impro… | 50 | 1040 | active |
| TorchEnsemble-Community/Ensemble-Pytorch A unified ensemble learning framework for PyTorch that implements strategies like voting, bagging, and gradient boosting to improve deep le… | 23 | 1037 | active |
| pytorch/tensordict TensorDict is a PyTorch library providing a batched, nested dict-like tensor container where operations like slicing, stacking, and arithme… | 99 | 1036 | active |
| google/ml_collections ML Collections is a Python library providing dict-like data structures (ConfigDict and FrozenConfigDict) for managing ML experiment and mod… | 67 | 1036 | stable |
| tensorflow/hub TensorFlow Hub is a Python library for reusing parts of trained TensorFlow models (SavedModels) for transfer learning, wrapping them as Ker… | 24 | 3523 | maintenance |
| NVlabs/DiffusionNFT DiffusionNFT is a research library implementing an online reinforcement learning paradigm for diffusion models that optimizes policy direct… | 47 | 1034 | active |
| OpenMined/TenSEAL TenSEAL is a Python library (with a C++ core) for performing homomorphic encryption operations on tensors, built on top of Microsoft SEAL. … | 87 | 1033 | active |
| thu-ml/SpargeAttn SpargeAttn is the official implementation of a training-free sparse and quantized attention method that accelerates inference for language,… | 51 | 1033 | active |
| podgorskiy/ALAE Official PyTorch implementation of Adversarial Latent Autoencoders (ALAE/StyleALAE), a CVPR 2020 paper combining autoencoders with GAN trai… | 32 | 3511 | maintenance |
| Jumpat/SegmentAnythingin3D SA3D is a research framework that lifts 2D Segment Anything (SAM) masks into 3D segmentation of objects within a NeRF or 3D Gaussian Splatt… | 40 | 1030 | active |
| awentzonline/image-analogies A Python library implementing neural image analogies using VGG16 feature maps with PatchMatch-based matching and blending, based on the 'Im… | 23 | 3502 | maintenance |
| szagoruyko/pytorchviz A small Python package (torchviz) that generates visualizations of PyTorch execution graphs and autograd traces using Graphviz. It renders … | 32 | 3500 | maintenance |
| kuleshov-group/bd3lms BD3-LMs is a research implementation of Block Discrete Denoising Diffusion Language Models that interpolate between autoregressive and diff… | 34 | 1029 | active |
| kuprel/min-dalle min(DALL·E) is a fast, minimal PyTorch port of DALL·E Mini/Mega stripped down for text-to-image inference, with only numpy, requests, pillo… | 31 | 3494 | maintenance |
| EchoMimic EchoMimic is a series of open-source models (V1-V3) from Ant Group for audio-driven human animation, generating lifelike talking-head, port… | 50 | 1027 | active |
| soCzech/TransNetV2 TransNet V2 is a deep neural network for shot boundary detection in videos, achieving state-of-the-art results on benchmarks like ClipShots… | 32 | 1027 | stable |
| fudan-zvg/4d-gaussian-splatting Official PyTorch/CUDA implementation of 4D Gaussian Splatting (ICLR 2024), which represents and renders dynamic scenes in real time using 4… | 57 | 1025 | active |
| DingXiaoH/RepVGG RepVGG is a PyTorch implementation of the VGG-style ConvNet architecture from the CVPR 2021 paper, achieving over 84% top-1 ImageNet accura… | 32 | 3478 | maintenance |
| aim-uofa/AdelaiDet AdelaiDet is an open-source Python toolbox built on Detectron2 that implements multiple instance-level detection and recognition algorithms… | 32 | 3478 | maintenance |
| microsoft/tensorwatch TensorWatch is a Python library from Microsoft Research for debugging, monitoring, and visualizing machine learning training in real time, … | 66 | 3471 | maintenance |
| open-mmlab/mmyolo MMYOLO is the OpenMMLab toolbox and benchmark for the YOLO series of object detection models, implemented on PyTorch. It provides unified i… | 23 | 3468 | maintenance |
| TencentARC/SEED-Voken SEED-Voken is a collection of visual tokenizers (Open-MAGVIT2 and IBQ) that convert images and videos into discrete tokens for autoregressi… | 48 | 1021 | active |
| JiahuiYu/generative_inpainting An open-source implementation of DeepFill v1/v2 generative image inpainting models, featuring Contextual Attention (CVPR 2018) and Gated Co… | 32 | 3466 | maintenance |
| tensorlayer/SRGAN Reference implementation of SRGAN, a generative adversarial network for photo-realistic single image super-resolution, built on TensorLayer… | 23 | 3466 | maintenance |
| TJU-DRL-LAB/AI-Optimizer AI-Optimizer is a deep reinforcement learning toolkit from TJU's DRL lab offering algorithm libraries spanning model-free, model-based, off… | 32 | 3465 | maintenance |
| fla-org/native-sparse-attention Efficient Triton kernel implementations of Native Sparse Attention (NSA), a hardware-aligned, natively trainable sparse attention mechanism… | 49 | 1020 | active |
| richzhang/colorization A Python library implementing automatic colorization of grayscale photos using deep neural networks from the ECCV 2016 'Colorful Image Colo… | 32 | 3461 | maintenance |
| zai-org/GLM-Image GLM-Image is an open-source image generation model combining a 9B autoregressive generator with a 7B diffusion decoder, excelling at text r… | 48 | 1019 | active |