mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-05 08:37:06 +08:00
b565c15bf7
* Add tinypose model * Add PPTinypose python API * Fix picodet preprocess bug && Add Tinypose examples * Update tinypose example code * Update ppseg preprocess if condition * Update ppseg backend support type * Update permute.h * Update README.md * Update code with comments * Move files dir * Delete premute.cc * Add single model pptinypose * Delete pptinypose old code in ppdet * Code format * Add ppdet + pptinypose pipeline model * Fix bug for posedetpipeline * Change Frontend to ModelFormat * Change Frontend to ModelFormat in __init__.py * Add python posedetpipeline/ * Update pptinypose example dir name * Update README.md * Update README.md * Update README.md * Update README.md * Create keypointdetection_result.md * Create README.md * Create README.md * Create README.md * Update README.md * Update README.md * Create README.md * Fix det_keypoint_unite_infer.py bug * Create README.md * Update PP-Tinypose by comment * Update by comment * Add pipeline directory * Add pptinypose dir * Update pptinypose to align accuracy * Addd warpAffine processor * Update GetCpuMat to GetOpenCVMat * Add comment for pptinypose && pipline * Update docs/main_page.md * Add README.md for pptinypose * Add README for det_keypoint_unite * Remove ENABLE_PIPELINE option * Remove ENABLE_PIPELINE option * Change pptinypose default backend * PP-TinyPose Pipeline support multi PP-Detection models * Update pp-tinypose comment * Update by comments * Add single test example Co-authored-by: Jason <jiangjiajun@baidu.com>
PP-TinyPose 模型部署
模型版本说明
目前FastDeploy支持如下模型的部署
准备PP-TinyPose部署模型
PP-TinyPose模型导出，请参考其文档说明模型导出
注意:PP-TinyPose导出的模型包含model.pdmodel、model.pdiparams和infer_cfg.yml三个文件，FastDeploy会从yaml文件中获取模型在推理时需要的预处理信息。
下载预训练模型
为了方便开发者的测试，下面提供了PP-TinyPose导出的部分模型，开发者可直接下载使用。
| 模型 | 参数文件大小 | 输入Shape | AP(业务数据集) | AP(COCO Val) | FLOPS | 单人推理耗时 (FP32) | 单人推理耗时（FP16) |
|---|---|---|---|---|---|---|---|
| PP-TinyPose-128x96 | 5.3MB | 128x96 | 84.3% | 58.4% | 81.56 M | 4.57ms | 3.27ms |
| PP-TinyPose-256x192 | 5.3M | 256x96 | 91.0% | 68.3% | 326.24M | 14.07ms | 8.33ms |
说明
- 关键点检测模型使用
COCO train2017和AI Challenger trainset作为训练集。使用COCO person keypoints val2017作为测试集。 - 关键点检测模型的精度指标所依赖的检测框为ground truth标注得到。
- 推理速度测试环境为 Qualcomm Snapdragon 865，采用arm8下4线程推理得到。
更多信息请参考：PP-TinyPose 官方文档