PaddlePaddle

PaddlePaddle Joined Nov 2016 View on GitHub

Stars
271,189
across 106 public repos
Rank
#47
of 94,827 organizations, top 0.05%

Repositories with 50+ stars

PaddlePaddle's repositories with their overall rank
RankRepositoryLanguageStars
168

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Python 92,535
1,814

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice (『飞桨』核心框架,深度学习&机器学习高性能单机、分布式训练和跨平台部署)

C++ 24,140
3,630

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

Python 14,467
4,180

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

Python 12,987
4,191

PaddleFormers is an easy-to-use library of pre-trained large language model zoo based on PaddlePaddle.

Python 12,970
4,286

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech...

Python 12,706
6,194

Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image...

Python 9,414
7,448

PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.

Python 8,039
7,814

The official repository for ERNIE 4.5 and ERNIEKit – its industrial-grade development toolkit based on PaddlePaddle.

Python 7,740
8,395

PaddlePaddle High Performance Deep Learning Inference Engine for Mobile and Edge (飞桨高性能深度学习端侧推理引擎)

C++ 7,290
8,895

Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.

Python 6,934
9,948

All-in-One Development Tool based on PaddlePaddle

Python 6,292
10,824

A treasure chest for visual classification and recognition powered by PaddlePaddle

Python 5,859
13,287

Deep Learning Visualization Toolkit(『飞桨』深度学习可视化工具 )

HTML 4,878
16,139

Recommendation Algorithm大规模推荐算法库,包含推荐系统经典及最新算法LR、Wide&Deep、DSSM、TDM、MIND、Word2Vec、Bert4Rec、DeepWalk、SSR、AITM,DSIN,SIGN,IPREC、GRU4Rec、Youtube_dnn、NCF、GNN、FM、FFM、DeepFM、DCN、DIN、DIEN、DLRM、MMOE、PLE、ESM...

Python 4,088
17,910

High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle

Python 3,724
18,209

深度学习入门课、资深课、特色课、学术案例、产业实践案例、深度学习知识百科及面试题库The course, case and knowledge of Deep Learning and AI

Jupyter Notebook 3,667
19,423

A high-performance distributed training framework for Reinforcement Learning

Python 3,454
24,652

Deep Learning 101 with PaddlePaddle (『飞桨』深度学习框架入门教程)

Jupyter Notebook 2,753
38,568

novel deep learning research works with PaddlePaddle

Python 1,774
40,191

Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video...

Python 1,705
42,397

PaddleSlim is an open-source library for deep model compression and architecture search.

Python 1,614
43,225

Paddle Graph Learning (PGL) is an efficient and flexible graph learning framework based on PaddlePaddle

Python 1,584
59,975

Bio-Computing Platform Featuring Large-Scale Representation Learning and Multi-Task Deep Learning “螺旋桨”生物计算工具集

Python 1,122
60,857

Paddle.js is a web project for Baidu PaddlePaddle, which is an open source deep learning framework running in the browser. Paddle.js can either load a pre-trained model, or transforming a model...

JavaScript 1,103
69,442

ONNX Model Exporter for PaddlePaddle

C++ 950
71,008

A flexible, high-performance carrier for machine learning models(『飞桨』服务化部署框架)

C++ 927
81,843

lib, demo, model, data

C++ 797
83,125

🚀 RocketQA, dense retrieval for information retrieval and question answering, including both Chinese and English state-of-the-art models.

Python 784
84,311

Deep learning model converter for PaddlePaddle. (『飞桨』深度学习模型转换工具)

Python 772
89,891

Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high...

Python 721
96,148

Large-scale open domain KNOwledge grounded conVERsation system based on PaddlePaddle

Python 669
96,536

🚀🚀🚀 YOLO series of PaddlePaddle implementation, PP-YOLOE+, RT-DETR, YOLOv5, YOLOv6, YOLOv7, YOLOv8, YOLOv10, YOLO11, YOLOX, YOLOv5u, YOLOv7u, YOLOv6Lite, RTMDet and so on. 🚀🚀🚀

Python 666
98,393 Jupyter Notebook 652
99,866

A 3D computer vision development toolkit based on PaddlePaddle. It supports point-cloud object detection, segmentation, and monocular 3D object detection models.

Python 642
101,949

PAddle PARAllel text-to-speech toolKIT (supporting Tacotron2, Transformer TTS, FastSpeech2/FastPitch, SpeedySpeech, WaveFlow and Parallel WaveGAN)

Python 628
107,234

FlyCV is a high-performance library for processing computer visual tasks.

C++ 594
116,044

Awesome Easy-to-Use Deep Time Series Modeling based on PaddlePaddle, including comprehensive functionality modules like TSDataset, Analysis, Transform, Models, AutoTS, and Ensemble, etc.,...

Python 545
117,617

High performance Cross-platform Inference-engine, you could run Anakin on x86-cpu,arm, nv-gpu, amd-gpu,bitmain and cambricon devices.

C++ 537
123,015

Federated Deep Learning in PaddlePaddle

Python 511
125,249

视觉预训练基础模型仓库

Python 501
127,342

Awesome Remote Sensing Toolkit based on PaddlePaddle.

Python 491
128,945

飞桨大模型开发套件,提供大语言模型、跨模态大模型、生物计算大模型等领域的全流程开发工具链。

Python 484
136,290

PaddleScience is SDK and library for developing AI-driven scientific computing applications based on PaddlePaddle.

Python 455
160,868

PaddleSpatial is an open-source spatial-temporal computing tool based on PaddlePaddle.

GLSL 377
162,425

ERNIE Bot Agent is a Large Language Model (LLM) Agent Framework, powered by the advanced capabilities of ERNIE Bot and the platform resources of Baidu AI Studio.

Jupyter Notebook 373
193,745

PaddlePaddle Docker images and K8s operators for PaddleOCR/Detection developers to use on public/private cloud.

Go 305
194,817

Collection of Reinforcement Learning / Meta Reinforcement Learning Environments.

Python 303
201,588

PASSL包含 SimCLR,MoCo v1/v2,BYOL,CLIP,PixPro,simsiam, SwAV, BEiT,MAE 等图像自监督算法以及 Vision Transformer,DEiT,Swin Transformer,CvT,T2T-ViT,MLP-Mixer,XCiT,ConvNeXt,PVTv2 等基础视觉算法

Python 291
205,882

Documentations for PaddlePaddle

Python 284
215,756 C++ 269
220,716

InterpretDL: Interpretation of Deep Learning Models,基于『飞桨』的模型可解释性算法库。

Python 262
243,306

PaddleRobotics is an open-source algorithm library for robots based on Paddle, including open-source parts such as human-robot interaction, complex motion control, environment perception, SLAM...

Python 233
290,545

ElasticCTR,即飞桨弹性计算推荐系统,是基于Kubernetes的企业级推荐系统开源解决方案。该方案融合了百度业务场景下持续打磨的高精度CTR模型、飞桨开源框架的大规模分布式训练能力、工业级稀疏参数弹性调度服务,帮助用户在Kubernetes环境中一键完成推荐系统部署,具备高性能、工业级部署、端到端体验的特点,并且作为开源套件,满足二次深度开发的需求。

Python 188
293,109

飞桨可信AI

Python 186
295,733

a Fast, Flexible, Extensible and Easy-to-use NLP Large-scale Pretraining and Multi-task Learning Framework.

Python 184
337,459 Python 157
341,112

Paddle Large Scale Classification Tools,supports ArcFace, CosFace, PartialFC, Data Parallel + Model Parallel. Model includes ResNet, ViT, Swin, DeiT, CaiT, FaceViT, MoCo, MAE, ConvMAE, CAE.

Python 155
360,088

Compiler Infrastructure for Neural Networks

C++ 145
360,088

PaddlePaddle Developer Community

Jupyter Notebook 145
388,710

Off-The-Shelf AI Development Kit for APP Developers based on Paddle Lite (『飞桨』移动端开箱即用AI套件, 包含Java & Objective C接口支持)

Objective-C 132
393,432

An End-to-End Deep Learning Toolkit for Materials Science

Python 130
395,913 Python 129
411,280 Go 123
411,280

PaddlePaddle Code Convert Toolkit. 『飞桨』深度学习代码转换工具

Python 123
425,061 Python 118
452,649

PaddlePaddle custom device implementaion. (『飞桨』自定义硬件接入实现)

Python 109
492,016

A Large-Scale Computation Graph Database for Tensor Compiler Research

Python 98
530,463

Paddle with Decentralized Trust based on Xuperchain

Go 89
540,157

A C++/Python simulator package for reinforcement learning

C++ 87
555,233

400+ AI Models: Rich, high-quality AI models, including CV, NLP, Speech, Video and Cross-Modal. Easy to Use: 3 lines of code to predict 400+ AI models.

Python 84
571,580 Python 81
588,864

PaddleSleeve

Python 78
607,098

hapi is a High-level API that supports both static and dynamic execution modes

Jupyter Notebook 75
620,054

Embedded and Mobile Deployment

Python 73
663,577 Python 67
687,767

PaddleCFD is a deep learning toolkit for surrogate modeling, equation discovery, shape optimization and flow-control strategy discovery in the field of fluid mechanics.

Python 64
704,714

Efficient Mask-Aware Distributed Attention for Long-Context Training

Python 62
797,173

Paddle Automatically Diff Precision Toolkits.

Python 53

Among 94,827 organizations

250k–400k stars: 27 organizations, including PaddlePaddle

Stars along the bottom, and organizations in each band on a log scale

Where the stars are

Languages

  1. Python 220.4k stars, 81% · 56 repos
  2. C++ 35.7k stars, 13% · 10 repos
  3. Jupyter Notebook 7.7k stars, 3% · 6 repos
  4. HTML 4.9k stars, 2% · 1 repo
  5. JavaScript 1.1k stars, <1% · 1 repo
  6. Go 517 stars, <1% · 3 repos
  7. GLSL 377 stars, <1% · 1 repo
  8. Objective-C 132 stars, <1% · 1 repo

When they were made

79 repos with 50+ stars, made between 2016 and 2026

Quick stats

Next rank
+6,029 stars to reach #46
Next milestone
+471,557 stars to reach the top 0.01%
Public repos
106, 79 with 50+ stars
Popular repos
25 over 1k stars, 6 over 10k stars
Top repo
PaddleOCR, #168 of all repos, 34% of stars
Smaller repos
392 stars from repos under 50

Stars counted Recounted daily Next count around