zhupengyang

benchmark

FluidDoc

Documentations for PaddlePaddle

mace

MACE is a deep learning inference framework optimized for mobile heterogeneous computing platforms.

models

Pre-trained and Reproduced Deep Learning Models （『飞桨』官方模型库，包含多种学术前沿和工业场景验证的深度学习模型）

Paddle

PArallel Distributed Deep LEarning （PaddlePaddle核心框架，高性能单机、分布式训练和跨平台部署）

Paddle-Inference-Demo

Paddle-Lite

Multi-platform high performance deep learning inference engine (『飞桨』多平台高性能深度学习预测引擎）

Paddle-Lite-Demo

lib, demo, model, data

PaddleClas

A treasure chest for image classification powered by PaddlePaddle

PaddleDetection

Object detection and instance segmentation toolkit based on PaddlePaddle.

PaddleGAN

PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, wav2lip, picture repair, image editing, photo2cartoon, image style transfer, and so on.

PaddleNLP

NLP Core Library and Model Zoo based on PaddlePaddle 2.0

PaddleOCR

Awesome multilingual OCR toolkits based on PaddlePaddle （practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices）

tensorflow

An Open Source Machine Learning Framework for Everyone

TIM-VX

Verisilicon Tensor Interface Module

TNN

TNN：由腾讯优图实验室打造，移动端高性能、轻量级推理框架，同时拥有跨平台、高性能、模型压缩、代码裁剪等众多突出优势。TNN框架在原有Rapidnet、ncnn框架的基础上进一步加强了移动端设备的支持以及性能优化，同时也借鉴了业界主流开源框架高性能和良好拓展性的优点。目前TNN已经在手Q、微视、P图等应用中落地，欢迎大家参与协同共建，促进TNN推理框架进一步完善。