apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-05 16:48:03 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity
Files
7b15f72516a1f2bb2e8b6f347ca5a60d14d2bd0e
FastDeploy/examples/vision/keypointdetection
History
yeliang2258 7b15f72516 [Backend] Add OCR、Seg、 KeypointDetection、Matting、 ernie-3.0 and adaface models for XPU Deploy (#960) 
* [FlyCV] Bump up FlyCV -> official release 1.0.0

* add seg models for XPU

* add ocr model for XPU

* add matting

* add matting python

* fix infer.cc

* add keypointdetection support for XPU

* Add adaface support for XPU

* add ernie-3.0

* fix doc

Co-authored-by: DefTruth <qiustudent_r@163.com>
Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
2022-12-26 15:02:58 +08:00
..
det_keypoint_unite
[Backend] Add OCR、Seg、 KeypointDetection、Matting、 ernie-3.0 and adaface models for XPU Deploy (#960)
2022-12-26 15:02:58 +08:00
tiny_pose
[Backend] Add OCR、Seg、 KeypointDetection、Matting、 ernie-3.0 and adaface models for XPU Deploy (#960)
2022-12-26 15:02:58 +08:00
README.md
[Model] Add tinypose single && pipeline model (#177)
2022-10-21 09:28:23 +08:00

README.md

关键点检测模型

FastDeploy目前支持两种关键点检测任务方式的部署

任务 说明 模型格式 示例 版本
单人关键点检测 部署PP-TinyPose系列模型，输入图像仅包含单人 Paddle 参考tinypose目录 Release/2.5
单人/多人关键点检测 部署PicoDet + PP-TinyPose的模型串联任务，输入图像先通过检测模型，得到独立的人像子图后，再经过PP-TinyPose模型检测关键点 Paddle 参考det_keypoint_unite目录 Release/2.5

预训练模型准备

本文档提供了如下预训练模型，开发者可直接下载使用

模型 说明 模型格式 版本
PP-TinyPose-128x96 单人关键点检测模型 Paddle Release/2.5
PP-TinyPose-256x192 单人关键点检测模型 Paddle Release/2.5
PicoDet-S-Lcnet-Pedestrian-192x192 + PP-TinyPose-128x96 单人关键点检测串联配置 Paddle Release/2.5
PicoDet-S-Lcnet-Pedestrian-320x320 + PP-TinyPose-256x192 多人关键点检测串联配置 Paddle Release/2.5