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 |
|---|---|---|---|
| FlagOpen/RoboBrain2.5 RoboBrain 2.5 is an open-source embodied AI foundation model from BAAI that combines multimodal large language model capabilities with 3D s… | 47 | 1150 | active |
| Being-H Being-H is a family of human-centric embodied foundation models, including VLA models (Being-H0.5, Being-H0) and latent world-action models… | 62 | 1148 | active |
| amazon-science/mm-cot Official PyTorch implementation of the paper 'Multimodal Chain-of-Thought Reasoning in Language Models', which adds vision features to a tw… | 31 | 3978 | maintenance |
| xzf-thu/Mega-ASR Mega-ASR is a foundation automatic speech recognition model trained on 2.6M samples spanning 7 atomic acoustic conditions and 54 compound r… | 56 | 1146 | active |
| HengyiWang/spann3r Spann3R is a transformer-based model for dense 3D reconstruction from ordered or unordered image collections, built on the DUSt3R paradigm.… | 23 | 1145 | active |
| ScorpioLea/AiCE AiCE is a Python tool that predicts high-fitness protein mutations by sampling sequences from protein inverse folding models such as Protei… | 37 | 1144 | active |
| noahcao/OC_SORT OC-SORT is a pure motion-model-based multi-object tracker for video, improving on SORT by fixing Kalman filter limitations to handle occlus… | 64 | 1143 | stable |
| rohitgandikota/sliders Official implementation of Concept Sliders, LoRA adaptors that enable precise, plug-and-play control of attributes in diffusion models like… | 49 | 1143 | active |
| THUMNLab/AutoGL AutoGL is an autoML framework and toolkit for machine learning on graphs, built on PyTorch with PyTorch Geometric and DGL backends. It prov… | 43 | 1142 | active |
| LLM-Pruner LLM-Pruner is a PyTorch library implementing structural pruning of large language models based on gradient information, as published at Neu… | 30 | 1142 | active |
| clovaai/deep-text-recognition-benchmark Official PyTorch implementation of a four-stage scene text recognition (OCR) framework from an ICCV 2019 paper, with training and evaluatio… | 32 | 3941 | maintenance |
| andabi/deep-voice-conversion A TensorFlow implementation of deep neural networks for voice conversion (voice style transfer) that converts a source speaker's voice into… | 32 | 3941 | maintenance |
| Kiteretsu77/APISR APISR is a deep-learning based super-resolution tool that restores and enhances low-quality, low-resolution anime images and videos using t… | 34 | 1138 | active |
| rhymes-ai/Allegro Allegro is an open-source text-to-video generation model that produces high-quality 720p videos up to 6 seconds at 15 FPS from text prompts… | 23 | 1138 | active |
| alibaba-damo-academy/RynnVLA-002 RynnVLA-002 is a unified autoregressive Vision-Language-Action and world model that generates robot actions from text and image observation… | 40 | 1136 | active |
| OpenDriveLab/UniVLA UniVLA is an open-source framework for training cross-embodiment vision-language-action (VLA) robot policies using task-centric latent acti… | 40 | 1134 | active |
| facebookresearch/watermark-anything Official PyTorch implementation and pretrained models for the paper 'Watermark Anything with Localized Messages', which embeds multiple loc… | 10 | 1134 | active |
| Janspiry/Image-Super-Resolution-via-Iterative-Refinement An unofficial PyTorch implementation of SR3 (Image Super-Resolution via Iterative Refinement), a diffusion-based model for image super-reso… | 32 | 3922 | maintenance |
| sooftware/conformer An unofficial PyTorch implementation of the Conformer architecture (convolution-augmented Transformer) from the INTERSPEECH 2020 paper, tar… | 65 | 1132 | active |
| OpenGVLab/VideoMamba VideoMamba is a state space model (Mamba-based) architecture for efficient video understanding, released with code and pretrained models fr… | 26 | 1130 | active |
| ikostrikov/pytorch-a2c-ppo-acktr-gail A PyTorch implementation of several deep reinforcement learning algorithms: A2C, PPO, ACKTR, and GAIL (imitation learning). It works with O… | 32 | 3907 | maintenance |
| Dobiasd/frugally-deep frugally-deep is a lightweight header-only C++ library for running inference (forward passes) on Keras/TensorFlow models without linking ag… | 79 | 1128 | active |
| princeton-vl/DPVO DPVO is a deep learning-based visual odometry and SLAM system that estimates camera trajectories from video or image sequences using patch-… | 75 | 1127 | active |
| nnsight nnsight is a Python library for interpreting and intervening on the internals of deep learning models, built on PyTorch. It lets researcher… | 96 | 1125 | active |
| THU-MIG/RepViT Official PyTorch implementation of RepViT, a family of lightweight CNNs designed by integrating efficient ViT architectural designs into Mo… | 20 | 1123 | stable |
| THUDM/SwissArmyTransformer SwissArmyTransformer (sat) is a PyTorch library for developing custom Transformer model variants where models like BERT, GPT, T5, GLM, and … | 23 | 1122 | active |
| MST (Spectral Compressive Imaging Toolbox) A Python toolbox for spectral compressive imaging reconstruction that implements over 15 algorithms including MST, CST, DAUHST, BiSCI, HDNe… | 49 | 1121 | active |
| FlagAI-Open/FlagAI FlagAI is a Python toolkit for training, fine-tuning, and deploying large-scale AI models across NLP, CV, and vision-language tasks. It int… | 61 | 3870 | maintenance |
| PaddlePaddle/PaddleHelix PaddleHelix is a bio-computing platform built on PaddlePaddle featuring large-scale representation learning and multi-task deep learning fo… | 52 | 1120 | active |
| yangxue0827/RotationDetection AlphaRotate is a TensorFlow-based benchmark and toolbox for rotated (oriented) object detection, implementing detectors such as R2CNN, Reti… | 23 | 1120 | active |
| yandex-research/tabm TabM is a PyTorch-based deep learning model for tabular data that efficiently imitates an ensemble of MLPs through parameter-efficient ense… | 32 | 1119 | active |
| HITsz-TMG/Uni-MoE Uni-MoE is a family of open-source Mixture-of-Experts (MoE) based omnimodal large language models that understand and generate across text,… | 65 | 1118 | active |
| Lasagne Lasagne is a lightweight Python library for building and training neural networks on top of Theano. It supports feed-forward, convolutional… | 23 | 3858 | maintenance |
| OpenMOSS/MOVA MOVA is an open-source foundation model and toolkit for joint video-audio generation, synthesizing synchronized video and audio in a single… | 59 | 1117 | active |
| MatchZoo MatchZoo is a Python toolkit for designing, comparing, and sharing deep text matching models. It provides a unified data pipeline, pre-buil… | 23 | 3849 | maintenance |
| openai/improved-diffusion The official codebase for OpenAI's Improved Denoising Diffusion Probabilistic Models paper, providing a Python package for training and sam… | 32 | 3848 | maintenance |
| yahoo/TensorFlowOnSpark TensorFlowOnSpark is a Python library that lets existing TensorFlow programs run distributed training and inference on Apache Spark and Had… | 23 | 3847 | maintenance |
| open-mmlab/PowerPaint PowerPaint is a versatile image inpainting model (ECCV 2024) built on diffusion models that handles text-guided object insertion, object re… | 67 | 1113 | active |
| LAMDA-CL/PyCIL PyCIL is a PyTorch-based Python toolbox for class-incremental learning, implementing the largest collection of CIL methods for reproducible… | 48 | 1112 | active |
| szymanowiczs/splatter-image Official PyTorch implementation of 'Splatter Image: Ultra-Fast Single-View 3D Reconstruction' (CVPR 2024), which uses an image-to-image net… | 27 | 1111 | active |
| baofff/U-ViT U-ViT is the official PyTorch implementation of a ViT-based backbone architecture for diffusion models from the CVPR 2023 paper 'All are Wo… | 32 | 1109 | stable |
| WangLibo1995/GeoSeg GeoSeg is an open-source PyTorch-based semantic segmentation toolbox focused on Vision Transformers for remote sensing imagery, featuring t… | 32 | 1109 | active |
| yzslab/gaussian-splatting-lightning A PyTorch Lightning implementation of 3D Gaussian Splatting with many derived algorithms (Mip-Splatting, LightGaussian, 2DGS, deformable Ga… | 56 | 1107 | active |
| PyABSA PyABSA is a PyTorch-based library providing state-of-the-art models for aspect-based sentiment analysis, including aspect term extraction, … | 66 | 1105 | active |
| google-research/multinerf Google Research's official code release for three NeRF papers: Mip-NeRF 360, Ref-NeRF, and RawNeRF, written in JAX. It trains neural radian… | 10 | 3805 | maintenance |
| PharMolix/OpenBioMed OpenBioMed is an open-source toolkit and agent platform for biomedicine and life science, offering multimodal models like BioMedGPT-Mol, 45… | 69 | 1104 | active |
| TencentARC/T2I-Adapter Official implementation of T2I-Adapter, lightweight adapter models that add controllable conditioning (sketch, canny, lineart, depth, pose)… | 31 | 3799 | maintenance |
| naturomics/CapsNet-Tensorflow A TensorFlow implementation of CapsNet (Capsule Networks) based on Geoffrey Hinton's paper 'Dynamic Routing Between Capsules'. It supports … | 32 | 3786 | maintenance |
| lucidrains/tab-transformer-pytorch A PyTorch implementation of the TabTransformer architecture, an attention-based neural network for tabular data, also including the FT Tran… | 64 | 1099 | stable |
| NVIDIA/DreamDojo NVIDIA's official PyTorch codebase for DreamDojo, a generalist robot world model pretrained on 44k hours of human egocentric video and post… | 45 | 1099 | active |
| lizhe00/AnimatableGaussians Official PyTorch implementation of the CVPR 2024 paper 'Animatable Gaussians', which learns pose-dependent Gaussian maps for high-fidelity … | 27 | 1099 | active |
| zai-org/CogView4 CogView4, CogView3-Plus and CogView3 are open-source text-to-image generation models from Zhipu AI, with CogView4 being a 6B-parameter DiT-… | 25 | 1099 | active |
| lucidrains/stylegan2-pytorch A simple PyTorch implementation of StyleGAN2, a state-of-the-art generative adversarial network, trainable entirely from the command line w… | 23 | 3779 | maintenance |
| Toni-SM/skrl skrl is an open-source modular Reinforcement Learning library written in Python, implemented in PyTorch, JAX, and NVIDIA Warp. It supports … | 86 | 1098 | active |
| microsoft/TimeCraft TimeCraft is a diffusion model-based framework for generating high-quality synthetic time series data across domains. It uses learned seman… | 66 | 1096 | active |
| Eyeline-Labs/Go-with-the-Flow Official implementation of the CVPR 2025 Oral paper 'Go-with-the-Flow', which controls motion in video diffusion models by replacing i.i.d.… | 39 | 1096 | active |
| Soul-AILab/SoulX-FlashHead SoulX-FlashHead is a 1.3B-parameter framework for high-fidelity, infinite-length, real-time streaming talking-head portrait video generatio… | 50 | 1093 | 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 … | 54 | 1090 | active |
| zju3dv/InfiniDepth InfiniDepth is a CVPR 2026 research library for monocular depth estimation that represents depth as neural implicit fields, allowing depth … | 59 | 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 | 3738 | 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 | 1088 | active |
| agi-brain/xuance XuanCe is an open-source Python library of deep reinforcement learning (DRL) and multi-agent reinforcement learning (MARL) algorithm implem… | 91 | 1087 | active |
| k2-fsa/ZipVoice ZipVoice is a series of fast, high-quality zero-shot text-to-speech models based on flow matching, with a compact 123M-parameter Zipformer-… | 40 | 1087 | 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 | 1087 | active |
| PointNeXt PointNeXt is the official PyTorch implementation of the NeurIPS'22 paper that improves PointNet++ via better training and model scaling str… | 87 | 1086 | stable |
| DSE-MSU/DeepRobust DeepRobust is a PyTorch library for adversarial robustness research, providing implementations of attack and defense methods for both image… | 41 | 1086 | active |
| GraphSAGE Reference implementation of the GraphSAGE algorithm for inductive representation learning on large graphs using stochastic graph convolutio… | 32 | 3728 | maintenance |
| mlc-ai/web-stable-diffusion A project that compiles and runs Stable Diffusion text-to-image models entirely inside web browsers using WebGPU and WebAssembly, with no s… | 31 | 3724 | maintenance |
| 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… | 39 | 1084 | 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 | 3717 | maintenance |
| bytedance/byteps BytePS is a high-performance parameter server framework for distributed deep neural network training, supporting TensorFlow, Keras, PyTorch… | 10 | 3717 | maintenance |
| charlesq34/pointnet2 Official TensorFlow implementation of PointNet++, a deep neural network that learns hierarchical features on 3D point clouds using metric-s… | 32 | 3712 | maintenance |
| HannesStark/boltzgen BoltzGen is an open-source all-atom generative diffusion model for designing protein and peptide binders against arbitrary biomolecular tar… | 75 | 1081 | 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 | 1077 | active |
| arcee-ai/DistillKit DistillKit is an open-source Python toolkit for knowledge distillation of large language models, supporting both online and offline distill… | 57 | 1076 | active |
| EchoMimic EchoMimic is a series of open-source models (V1-V3) from Ant Group for audio-driven human animation, generating lifelike talking-head, port… | 47 | 1075 | active |
| AILab-CVC/UniRepLKNet UniRepLKNet is a large-kernel ConvNet architecture (CVPR 2024, TPAMI 2025) that provides universal perception across image, audio, video, p… | 40 | 1074 | stable |
| 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 | 3678 | maintenance |
| openai/glide-text2im Official codebase for GLIDE, a diffusion-based text-conditional image synthesis model from OpenAI. It provides pretrained models and notebo… | 10 | 3678 | maintenance |
| NVIDIA-Merlin/HugeCTR HugeCTR is a GPU-accelerated deep learning framework from NVIDIA designed for training and inference of large recommender models, especiall… | 71 | 1073 | 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… | 59 | 1072 | active |
| RL-VIG/LibFewShot LibFewShot is a comprehensive PyTorch library for few-shot learning, implementing many fine-tuning, meta-learning, and metric-learning meth… | 51 | 1072 | 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… | 37 | 1071 | active |
| LAM LAM is a PyTorch implementation of a Large Avatar Model that reconstructs an animatable 3D Gaussian head from a single image in one forward… | 55 | 1070 | 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 … | 50 | 1069 | active |
| 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… | 46 | 1069 | 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 | 1069 | stable |
| yeates/PromptFix PromptFix is a PyTorch implementation of a diffusion-model-based image restoration model that follows natural language instructions to fix … | 25 | 1069 | 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… | 44 | 1068 | active |
| nv-tlabs/PiD PiD is a plug-and-play pixel diffusion decoder from NVIDIA that replaces VAE/RAE decoders, decoding latent representations directly into hi… | 53 | 1067 | active |
| princeton-nlp/SimCSE SimCSE is a Python library and research codebase implementing simple contrastive learning for sentence embeddings, with pre-trained unsuper… | 23 | 3652 | maintenance |
| hujie-frank/SENet Official Caffe/CUDA implementation of Squeeze-and-Excitation Networks (SENet), channel-attention building blocks for convolutional neural n… | 32 | 3651 | maintenance |
| X-LANCE/SLAM-LLM SLAM-LLM is a deep learning toolkit for training custom multimodal large language models focused on speech, language, audio, and music proc… | 52 | 1066 | active |
| drprojects/superpoint_transformer Official PyTorch implementation of Superpoint Transformer (ICCV'23), SuperCluster (3DV'24), and EZ-SP (ICRA'26) for efficient semantic and … | 74 | 1063 | active |
| 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 | 3634 | maintenance |
| Tencent-Hunyuan/HunyuanVideo-Foley HunyuanVideo-Foley is a multimodal diffusion model from Tencent Hunyuan that generates high-fidelity Foley sound effects synchronized with … | 34 | 1061 | active |
| abertsch72/unlimiformer Unlimiformer is a method and official implementation for augmenting pretrained encoder-decoder transformers with retrieval-based attention,… | 30 | 1061 | stable |
| open-gigaai/giga-models GigaModels is an open-source Python framework providing pipelines for training, inference, deployment, and compression of multi-modal, gene… | 59 | 1060 | active |
| StarGAN v2 The official PyTorch implementation of StarGAN v2, a CVPR 2020 paper on diverse image-to-image translation across multiple domains using a … | 32 | 3618 | maintenance |
| 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 |