Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Mark Ma e213a71c06 | 2 years ago | |
---|---|---|
.github/ISSUE_TEMPLATE | 2 years ago | |
.travis | 2 years ago | |
benchmark | 2 years ago | |
configs | 2 years ago | |
dataset | 2 years ago | |
demo | 2 years ago | |
deploy | 2 years ago | |
docs | 2 years ago | |
ppdet | 2 years ago | |
scripts | 2 years ago | |
static | 2 years ago | |
tests | 2 years ago | |
tools | 2 years ago | |
.gitignore | 2 years ago | |
.pre-commit-config.yaml | 2 years ago | |
.style.yapf | 4 years ago | |
.travis.yml | 3 years ago | |
LICENSE | 3 years ago | |
README.md | 3 years ago | |
README_cn.md | 2 years ago | |
README_en.md | 2 years ago | |
requirements.txt | 2 years ago | |
setup.py | 2 years ago |
简体中文 | English
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。
Architectures | Backbones | Components | Data Augmentation |
|
|
|
|
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:
CBResNet
为Cascade-Faster-RCNN-CBResNet200vd-FPN
模型,COCO数据集mAP高达53.3%Cascade-Faster-RCNN
为Cascade-Faster-RCNN-ResNet50vd-DCN
,PaddleDetection将其优化到COCO数据mAP为47.8%时推理速度为20FPSPP-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YOLOv4PP-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:
参数配置
模型压缩(基于PaddleSlim)
进阶开发
版本更新内容请参考版本更新文档
本项目的发布受Apache 2.0 license许可认证。
我们非常欢迎你可以为PaddleDetection提供代码,也十分感谢你的反馈。
@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
Python Jupyter Notebook Markdown C++ Java other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》