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/tacotron2 NVIDIA's PyTorch implementation of the Tacotron 2 text-to-speech model, which synthesizes mel spectrograms from text for vocoder-based audi… | 32 | 5295 | maintenance |
| yunjey/stargan Official PyTorch implementation of StarGAN, a unified generative adversarial network for multi-domain image-to-image translation (CVPR 2018… | 32 | 5295 | maintenance |
| tensorflow/tpu A collection of reference models and tools for training machine learning models on Google Cloud TPUs, maintained as a public mirror by the … | 68 | 5278 | maintenance |
| zsyOAOA/InvSR InvSR is a Python research library implementing arbitrary-steps image super-resolution via diffusion inversion, leveraging pre-trained diff… | 48 | 1459 | active |
| Walter0807/MotionBERT Official PyTorch implementation of MotionBERT (ICCV 2023), a unified pretrained model for learning human motion representations from 2D ske… | 61 | 1454 | active |
| YanjieZe/3D-Diffusion-Policy 3D Diffusion Policy (DP3) is a visual imitation learning algorithm that combines compact 3D point cloud representations with diffusion poli… | 43 | 1453 | active |
| dbolya/yolact YOLACT is a PyTorch implementation of a fully convolutional model for real-time instance segmentation, accompanying the YOLACT and YOLACT++… | 47 | 5242 | maintenance |
| google-deepmind/rlax RLax is a JAX-based library of building blocks for implementing reinforcement learning agents, providing mathematical operations like value… | 79 | 1449 | active |
| zylo117/Yet-Another-EfficientDet-Pytorch A PyTorch re-implementation of Google's EfficientDet object detection model with pretrained weights matching near-SOTA accuracy at real-tim… | 23 | 5233 | maintenance |
| amdegroot/ssd.pytorch A PyTorch implementation of the Single Shot MultiBox Detector (SSD) object detection model from the 2016 paper by Wei Liu et al. It include… | 32 | 5222 | maintenance |
| deepseek-ai/EPLB EPLB is DeepSeek's open-source Expert Parallelism Load Balancer for Mixture-of-Experts models. It computes balanced expert replication and … | 23 | 1443 | active |
| tianweiy/CausVid CausVid is a research codebase implementing a fast autoregressive video diffusion model distilled from a bidirectional diffusion transforme… | 33 | 1441 | active |
| tensorspace-team/tensorspace TensorSpace is a neural network 3D visualization framework built on TensorFlow.js, Three.js, and Tween.js. It provides Keras-like APIs to b… | 23 | 5198 | maintenance |
| neuralchen/SimSwap SimSwap is a PyTorch-based face-swapping framework that performs arbitrary face swaps on images and videos using a single trained model. It… | 23 | 5192 | maintenance |
| sql-machine-learning/sqlflow SQLFlow is a compiler that extends SQL with AI-oriented syntax (training, prediction, evaluation, explanation, and mathematical programming… | 23 | 5190 | maintenance |
| voice-cloning-app/Voice-Cloning-App A Python/PyTorch desktop application for cloning and synthesizing human voices from audio datasets. It handles the full pipeline from autom… | 23 | 1438 | active |
| Francis-Rings/StableAnimator StableAnimator is an end-to-end ID-preserving video diffusion framework that animates a reference human image according to a sequence of po… | 37 | 1433 | active |
| facebookresearch/vggsfm VGGSfM is a deep learning-based Structure from Motion pipeline from Meta AI and Oxford VGG that recovers camera poses and 3D point clouds f… | 26 | 1430 | active |
| nv-tlabs/GEN3C GEN3C is NVIDIA's research codebase for a generative video model that achieves precise camera control and temporal 3D consistency using a 3… | 56 | 1425 | active |
| mdbloice/Augmentor Augmentor is a standalone Python library for image augmentation in machine learning, providing a pipeline of stochastic operations like rot… | 32 | 5131 | maintenance |
| ZheC/Realtime_Multi-Person_Pose_Estimation Reference implementation of the CVPR'17 paper 'Realtime Multi-Person Pose Estimation', a bottom-up approach that detects keypoints for mult… | 32 | 5126 | maintenance |
| Wav2Lip UHQ Extension A Wav2Lip Studio extension for the Stable Diffusion WebUI (Automatic1111) that generates high-quality lip-synced talking-face videos from a… | 29 | 1423 | active |
| ARahim3/mlx-tune A Python library for fine-tuning LLMs, vision-language, audio (TTS/STT), embedding, OCR, and JEPA models natively on Apple Silicon Macs usi… | 69 | 1416 | active |
| jrzaurin/pytorch-widedeep A PyTorch library for multimodal deep learning that combines tabular data with text and images using Wide and Deep model architectures. It … | 55 | 1416 | active |
| Terrain Diffusion Terrain Diffusion is a Python framework that uses diffusion models as a learned, deterministic replacement for Perlin noise, generating inf… | 58 | 1414 | active |
| Lyken17/pytorch-OpCounter THOP (PyTorch-OpCounter) is a Python library that counts the MACs/FLOPs and parameters of PyTorch models. It profiles arbitrary nn.Modules … | 32 | 5083 | maintenance |
| explosion/spacy-transformers A spaCy v3 extension package that provides pipeline components for using pretrained transformer models like BERT, RoBERTa, XLNet, and GPT-2… | 65 | 1413 | stable |
| fudan-generative-vision/hallo3 Hallo3 is a research model from Fudan University that animates a single portrait image into a highly dynamic and realistic talking-head vid… | 23 | 1413 | active |
| affinelayer/pix2pix-tensorflow A TensorFlow implementation of pix2pix, a conditional GAN that learns a mapping from input images to output images. It is a faithful port o… | 32 | 5078 | maintenance |
| lucidrains/self-rewarding-lm-pytorch A PyTorch library implementing the Self-Rewarding Language Model training framework from MetaAI, along with the SPIN training method. It pr… | 17 | 1412 | active |
| dailenson/SDT Official PyTorch implementation of the CVPR 2023 paper 'Disentangling Writer and Character Styles for Handwriting Generation' (SDT). It gen… | 40 | 1411 | active |
| lucidrains/transfusion-pytorch A PyTorch implementation of Transfusion, MetaAI's approach to predicting the next token and diffusing images with a single multi-modal mode… | 70 | 1408 | active |
| SpikingBrain SpikingBrain-7B is a brain-inspired large language model that combines hybrid efficient attention, MoE modules, and spike encoding, with a … | 51 | 1408 | active |
| mratsim/Arraymancer Arraymancer is a fast, ergonomic N-dimensional tensor (ndarray) library written in Nim, inspired by NumPy and PyTorch. It provides CPU, CUD… | 57 | 1407 | active |
| open-gigaai/giga-world-policy GigaWorld-Policy is a World Action Model (WAM) for robot policy learning that jointly models actions and future visual observations during … | 53 | 1406 | active |
| XiaoMi/mace MACE (Mobile AI Compute Engine) is a deep learning inference framework optimized for mobile heterogeneous computing on Android, iOS, Linux … | 23 | 5052 | maintenance |
| zju3dv/street_gaussians Street Gaussians is a research implementation of the ECCV 2024 paper 'Modeling Dynamic Urban Scenes with Gaussian Splatting', which reconst… | 69 | 1405 | active |
| gnobitab/InstaFlow InstaFlow is a one-step text-to-image generation model based on Rectified Flow, enabling ultra-fast Stable Diffusion inference without iter… | 29 | 1403 | active |
| nachifur/MulimgViewer MulimgViewer is a Python-based multi-image viewer that displays many images in a single interface for side-by-side comparison, parallel sel… | 63 | 1402 | active |
| yfeng95/PRNet PRNet is a Python/TensorFlow implementation of the ECCV 2018 Position Map Regression Network for joint 3D face reconstruction and dense ali… | 32 | 5018 | maintenance |
| Zejun-Yang/AniPortrait AniPortrait is a Python framework from Tencent that generates photorealistic portrait animations from an audio clip and a reference image, … | 26 | 5014 | maintenance |
| xl0/lovely-tensors A Python library that provides human-friendly summaries of PyTorch tensors, showing shape, statistics, histograms, and NaN/Inf detection in… | 63 | 1395 | active |
| TheRock TheRock is AMD's open-source build and release system for the ROCm software stack, replacing the legacy monolithic ROCm release process wit… | 89 | 1394 | active |
| galilai-group/lejepa LeJEPA is a Python framework for scalable, theoretically grounded self-supervised representation learning based on Joint-Embedding Predicti… | 42 | 1393 | active |
| ByteDance-Seed/SeedVR SeedVR/SeedVR2 are diffusion-transformer based models for generic real-world and AIGC video and image restoration, with SeedVR2 using adver… | 44 | 1390 | active |
| cszn/BSRGAN BSRGAN is a PyTorch implementation of a practical degradation model for deep blind image super-resolution, presented at ICCV 2021. It provi… | 32 | 1390 | stable |
| logtd/ComfyUI-Fluxtapoz A set of ComfyUI custom nodes for editing and stylizing images with Flux models, implementing techniques like RF-Inversion, RF-Edit, Firefl… | 24 | 1390 | active |
| Junyi42/monst3r MonST3R is the official PyTorch implementation of an ICLR 2025 paper that estimates per-timestep geometry (pointmaps) from dynamic videos i… | 22 | 1390 | active |
| haoheliu/voicefixer VoiceFixer is a Python library and CLI tool for general speech restoration, using a pretrained neural vocoder to restore degraded human spe… | 23 | 1387 | stable |
| Zefan-Cai/KVCache-Factory KVCache-Factory is a unified Python framework implementing many KV cache compression, retrieval, merging, and quantization methods for long… | 65 | 1384 | active |
| yanx27/Pointnet_Pointnet2_pytorch A pure PyTorch implementation of the PointNet and PointNet++ deep learning architectures for point cloud processing. It includes training a… | 32 | 4958 | maintenance |
| autonomousvision/unimatch UniMatch is a PyTorch research library implementing a unified transformer-based model for optical flow, stereo matching, and depth estimati… | 32 | 1383 | stable |
| ali-vilab/TeaCache TeaCache is a training-free caching approach that accelerates inference for video diffusion models by estimating output differences across … | 30 | 1383 | active |
| keyu-tian/SparK SparK is the official PyTorch implementation of an ICLR 2023 Spotlight paper that applies BERT/MAE-style masked image modeling to convoluti… | 22 | 1382 | stable |
| AlmondGod/tinyworlds A minimal Python implementation of DeepMind's Genie autoregressive world model, including a video tokenizer, action tokenizer, and dynamics… | 51 | 1380 | active |
| zhixuhao/unet A Keras implementation of the U-Net convolutional network architecture for image segmentation, based on the original biomedical segmentatio… | 62 | 4941 | maintenance |
| FireRedTeam/FireRed-Image-Edit FireRed-Image-Edit is an open-source image editing foundation model built on diffusion models, released as PyTorch model weights with infer… | 46 | 1378 | active |
| Neuromancer NeuroMANCER is a PyTorch-based differentiable programming library for solving parametric constrained optimization problems, physics-informe… | 69 | 1377 | active |
| qubvel/segmentation_models A Python library providing neural network architectures for image segmentation (Unet, FPN, Linknet, PSPNet) built on Keras and TensorFlow K… | 23 | 4923 | maintenance |
| minimaxir/textgenrnn A Python 3 library built on Keras/TensorFlow for easily training char-rnn style neural networks that generate text from any dataset in a fe… | 23 | 4918 | maintenance |
| Goal-Driven Autonomous Exploration (DRL Robot Navigation) A ROS Gazebo simulation project that trains a mobile robot to navigate to random goals while avoiding obstacles using a TD3 deep reinforcem… | 54 | 1374 | active |
| macanv/BERT-BiLSTM-CRF-NER A TensorFlow implementation of named entity recognition that fine-tunes Google BERT with a BiLSTM-CRF model, primarily targeting Chinese te… | 32 | 4907 | maintenance |
| OpenPrompt OpenPrompt is a PyTorch-based open-source framework for prompt-learning, providing a standard, flexible pipeline of templates and verbalize… | 23 | 4903 | maintenance |
| bytedance/flux Flux is a GPU kernel library from ByteDance that overlaps computation with communication for tensor and expert parallelism in dense and MoE… | 30 | 1369 | active |
| OpenPPL/ppl.nn PPLNN is a high-performance deep-learning inference engine written in C++ that runs ONNX models on x86 CPUs and NVIDIA GPUs, with a dedicat… | 32 | 1368 | active |
| NVIDIA-AI-IOT/torch2trt torch2trt is a Python library that converts PyTorch models to TensorRT engines using the TensorRT Python API, with a simple single-function… | 23 | 4885 | maintenance |
| PKU-VCL-3DV/SLAM3R SLAM3R is a real-time dense 3D scene reconstruction system that regresses 3D points from monocular RGB video using feed-forward neural netw… | 39 | 1366 | active |
| kengz/SLM-Lab SLM Lab is a modular deep reinforcement learning framework built in PyTorch, offering ready-to-use algorithms like PPO, SAC, DQN, and A2C v… | 91 | 1365 | active |
| ImprintLab/MedSegDiff MedSegDiff is a diffusion probabilistic model framework for segmenting and reconstructing organs and tissues from medical images, with a tr… | 47 | 1364 | active |
| bytedance/UNO UNO is a research framework from ByteDance for subject-driven image generation with diffusion transformers, supporting both single- and mul… | 35 | 1364 | active |
| Sense-X/Co-DETR Co-DETR is a PyTorch implementation of DETRs with Collaborative Hybrid Assignments Training, an ICCV 2023 object detection and instance seg… | 32 | 1364 | stable |
| FreedomIntelligence/HuatuoGPT-o1 HuatuoGPT-o1 is a medical large language model project for complex medical reasoning, with open-sourced models (7B-72B), fine-tuning data, … | 22 | 1363 | active |
| huggingface/finetrainers finetrainers is a Hugging Face library for scalable, memory-optimized training (fine-tuning) of diffusion models, including LoRA training o… | 68 | 1362 | active |
| MoonInTheRiver/DiffSinger Official PyTorch implementation of DiffSinger, an AAAI 2022 paper on singing voice synthesis and text-to-speech using a shallow diffusion m… | 62 | 4861 | maintenance |
| shivammehta25/Matcha-TTS Matcha-TTS is a PyTorch-based text-to-speech system that uses conditional flow matching for fast, non-autoregressive speech synthesis. It s… | 60 | 1360 | active |
| yinguobing/head-pose-estimation A Python library for realtime human head pose estimation using ONNX Runtime and OpenCV. It combines face detection (SCRFD), 68-point facial… | 23 | 1357 | stable |
| ant-research/CoDeF CoDeF is the official PyTorch implementation of Content Deformation Fields, a video representation combining a canonical content field and … | 29 | 4843 | maintenance |
| blei-lab/edward Edward is a Python library for probabilistic modeling, inference, and criticism built on TensorFlow. It supports deep generative models, va… | 23 | 4843 | maintenance |
| wyhuai/DDNM DDNM is a Python research codebase implementing the Denoising Diffusion Null-Space Model for zero-shot image restoration, published as an I… | 32 | 1356 | stable |
| sjvasquez/handwriting-synthesis A Python implementation of Alex Graves' handwriting synthesis experiments using recurrent neural networks, generating realistic handwritten… | 32 | 4824 | maintenance |
| studio-dots-ai/dots.tts dots.tts is a 2B-parameter fully continuous, end-to-end autoregressive text-to-speech system, distributed as a Python library with pretrain… | 77 | 1350 | active |
| MegEngine/MegEngine MegEngine is a fast, scalable deep learning framework with automatic differentiation, developed in C++ with Python bindings. It unifies tra… | 23 | 4809 | maintenance |
| segment-any-text/wtpsplit wtpsplit is a Python toolkit for segmenting text into sentences or other semantic units using the SaT and WtP deep learning models. It prov… | 93 | 1347 | active |
| hao-ai-lab/LookaheadDecoding A Python library implementing Lookahead Decoding, an exact parallel decoding algorithm that accelerates LLM inference without a draft model… | 28 | 1343 | active |
| rstudio/tensorflow An R package that provides full access to the TensorFlow API from R via reticulate, bridging R users to TensorFlow's Python implementation.… | 56 | 1340 | active |
| HiDream-ai/HiDream-O1-Image HiDream-O1-Image is an open-weights 8B image generation foundation model built on a Pixel-level Unified Transformer (UiT) that natively enc… | 50 | 1340 | active |
| alibaba/graph-learn Graph-Learn (formerly AliGraph) is a distributed framework for developing and applying large-scale graph neural networks, with a training l… | 32 | 1340 | active |
| open-edge-platform/geti Geti is an open-source, end-to-end Vision AI application from Intel that takes users from raw images to deployed computer vision models, ru… | 92 | 1338 | active |
| jonathan-laurent/AlphaZero.jl A generic, simple, and fast Julia implementation of DeepMind's AlphaZero algorithm for training game-playing agents via self-play and MCTS.… | 69 | 1338 | active |
| senguptaumd/Background-Matting Official research code for 'Background Matting: The World is Your Green Screen' (CVPR 2020), a deep network that extracts per-pixel alpha m… | 32 | 4764 | maintenance |
| wenqsun/DimensionX DimensionX is a research framework that generates photorealistic 3D and 4D scenes from a single image using controllable video diffusion mo… | 40 | 1336 | active |
| mapillary/inplace_abn A PyTorch extension library implementing In-Place Activated BatchNorm (InPlace-ABN), which redefines BN plus nonlinear activation as a sing… | 67 | 1333 | stable |
| braindecode/braindecode Braindecode is an open-source Python toolbox built on PyTorch for decoding raw electrophysiological brain signals such as EEG, ECoG, and ME… | 98 | 1332 | active |
| bytedance/Bernini Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer perf… | 54 | 1330 | active |
| facebookincubator/AITemplate AITemplate is a Python framework that compiles deep neural networks into high-performance CUDA (NVIDIA) or HIP (AMD) C++ code for fast fp16… | 67 | 4730 | maintenance |
| LLaVA-VL/LLaVA-NeXT LLaVA-NeXT is a collection of open large multimodal models (LLaVA-NeXT, LLaVA-Video, LLaVA-OneVision, LLaVA-Critic-R1) that combine vision … | 61 | 4729 | maintenance |
| Vahe1994/AQLM Official PyTorch implementation of AQLM, an extreme LLM compression method via additive quantization, extended with PV-Tuning for finetunin… | 54 | 1329 | active |
| Tongjilibo/bert4torch bert4torch is a PyTorch library providing an elegant reimplementation of transformer models (BERT, RoBERTa, T5, GPT, ChatGLM, LLaMA, etc.) … | 76 | 1326 | active |
| agemagician/ProtTrans ProtTrans provides state-of-the-art pre-trained Transformer language models for protein sequences, trained on thousands of GPUs and hundred… | 29 | 1326 | active |
| inference-labs-inc/JSTprove JSTprove is a Rust CLI toolkit that generates zero-knowledge proofs of machine learning inference on ONNX models, built on Polyhedra Networ… | 64 | 1324 | active |