Code Monkey home page Code Monkey logo

paddledetection's Introduction

简体中文 | English

PaddleDetection

产品动态

简介

PaddleDetection为基于飞桨PaddlePaddle的端到端目标检测套件,提供多种主流目标检测、实例分割、跟踪、关键点检测算法,配置化的网络模块组件、数据增强策略、损失函数等,推出多种服务器端和移动端工业级SOTA模型,并集成了模型压缩和跨平台高性能部署能力,帮助开发者更快更好完成端到端全开发流程。

PaddleDetection提供了目标检测、实例分割、多目标跟踪、关键点检测等多种能力

特性

  • 模型丰富: 包含目标检测实例分割人脸检测100+个预训练模型,涵盖多种全球竞赛冠军方案
  • 使用简洁:模块化设计,解耦各个网络组件,开发者轻松搭建、试用各种检测模型及优化策略,快速得到高性能、定制化的算法。
  • 端到端打通: 从数据增强、组网、训练、压缩、部署端到端打通,并完备支持云端/边缘端多架构、多设备部署。
  • 高性能: 基于飞桨的高性能内核,模型训练速度及显存占用优势明显。支持FP16训练, 支持多机训练。

套件结构概览

Architectures Backbones Components Data Augmentation
  • Two-Stage Detection
    • Faster RCNN
    • FPN
    • Cascade-RCNN
    • Libra RCNN
    • Hybrid Task RCNN
    • PSS-Det
  • One-Stage Detection
    • RetinaNet
    • YOLOv3
    • YOLOv4
    • PP-YOLOv1/v2/Tiny
    • SSD
  • Anchor Free
    • CornerNet-Squeeze
    • FCOS
    • TTFNet
    • PicoDet
  • Instance Segmentation
    • Mask RCNN
    • SOLOv2
  • Face-Detction
    • FaceBoxes
    • BlazeFace
    • BlazeFace-NAS
  • Transformer
    • DETR/Deformable DETR
    • Sparse RCNN
    • Swin Transformer
  • Multi-Object-Tracking
    • JDE
    • FairMOT
    • DeepSort
  • KeyPoint-Detection
    • HRNet
    • HigherHRNet
  • ResNet(&vd)
  • ResNeXt(&vd)
  • SENet
  • Res2Net
  • HRNet
  • Hourglass
  • CBNet
  • GCNet
  • DarkNet
  • CSPDarkNet
  • VGG
  • MobileNetv1/v3
  • GhostNet
  • Efficientnet
  • BlazeNet
  • Common
    • Sync-BN
    • Group Norm
    • DCNv2
    • Non-local
  • KeyPoint
    • DarkPose
  • FPN
    • BiFPN
    • BFP
    • HRFPN
    • ACFPN
  • Loss
    • Smooth-L1
    • GIoU/DIoU/CIoU
    • IoUAware
  • Post-processing
    • SoftNMS
    • MatrixNMS
  • Speed
    • FP16 training
    • Multi-machine training
  • Resize
  • Lighting
  • Flipping
  • Expand
  • Crop
  • Color Distort
  • Random Erasing
  • Mixup
  • Mosaic
  • Cutmix
  • Grid Mask
  • Auto Augment
  • Random Perspective

模型性能概览

各模型结构和骨干网络的代表模型在COCO数据集上精度mAP和单卡Tesla V100上预测速度(FPS)对比图。

说明:

  • CBResNetCascade-Faster-RCNN-CBResNet200vd-FPN模型,COCO数据集mAP高达53.3%
  • Cascade-Faster-RCNNCascade-Faster-RCNN-ResNet50vd-DCN,PaddleDetection将其优化到COCO数据mAP为47.8%时推理速度为20FPS
  • PP-YOLO在COCO数据集精度45.9%,Tesla V100预测速度72.9FPS,精度速度均优于YOLOv4
  • PP-YOLO v2是对PP-YOLO模型的进一步优化,在COCO数据集精度49.5%,Tesla V100预测速度68.9FPS
  • 图中模型均可在模型库中获取

各移动端模型在COCO数据集上精度mAP和高通骁龙865处理器上预测速度(FPS)对比图。

说明:

  • 测试数据均使用高通骁龙865(4*A77 + 4*A55)处理器batch size为1, 开启4线程测试,测试使用NCNN预测库,测试脚本见MobileDetBenchmark
  • PP-PicoDetPP-YOLO-Tiny为PaddleDetection自研模型,其余模型PaddleDetection暂未提供

文档教程

入门教程

进阶教程

模型库

应用案例

第三方教程推荐

版本更新

版本更新内容请参考版本更新文档

许可证书

本项目的发布受Apache 2.0 license许可认证。

贡献代码

我们非常欢迎你可以为PaddleDetection提供代码,也十分感谢你的反馈。

  • 感谢Mandroide清理代码并且统一部分函数接口。
  • 感谢FL77N贡献Sparse-RCNN模型。
  • 感谢Chen-Song贡献Swin Faster-RCNN模型。

引用

@misc{ppdet2019,
title={PaddleDetection, Object detection and instance segmentation toolkit based on PaddlePaddle.},
author={PaddlePaddle Authors},
howpublished = {\url{https://github.com/PaddlePaddle/PaddleDetection}},
year={2019}
}

paddledetection's People

Contributors

jerrywgz avatar yghstill avatar heavengate avatar nemonameless avatar wangxinxin08 avatar qingqing01 avatar willthefrog avatar lyuwenyu avatar zhiboniu avatar littletomatodonkey avatar ghostxsl avatar wanghaoshuang avatar baiyfbupt avatar zoooo0820 avatar slf12 avatar noplz avatar flyingqianmm avatar sunahong1993 avatar channingss avatar fdinsky avatar walloollaw avatar yzl19940819 avatar jiweimaster avatar ceci3 avatar qingshuchen avatar tink2123 avatar luotao1 avatar mandroide avatar bjjwwang avatar joey12300 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.