apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2026-04-29 11:49:59 +08:00
Code Issues Actions 15 Packages Projects Releases Wiki Activity

[RKNPU2] Add Quantized PPHumanSeg (#905)

Browse Source 
* 更新rknpu2 backend核心代码

* 更新模型导出核心代码

* 删除无用的config文件

* 新增配置文件以及修改文档

* 模型转换以及文档

* 更新文档

* 更新与配置文件

* 更新PPHumanSeg全量化

* 更新文档

* 更新文档

* 更新文档
This commit is contained in:
Zheng_Bicheng
2022-12-19 20:07:32 +08:00
committed by GitHub
parent 4ac0e33b71
commit 218f33f8b1
8 changed files with 129 additions and 108 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/cn/faq/rknpu2/rknpu2.md
+5 -14
View File
@@ -16,21 +16,12 @@ ONNX模型不能直接调用RK芯片中的NPU进行运算，需要把ONNX模型
|------------------|-------------------|-------------------------------|--------------------|
| Detection | Picodet | Picodet-s | 162/112 |
| Detection | RKYOLOV5 | YOLOV5-S-Relu(int8) | -/57 |
| Detection | RKYOLOX | - | -/- |
| Detection | RKYOLOV7 | - | -/- |
| Segmentation | Unet | Unet-cityscapes | -/- |
| Segmentation | PP-LiteSeg | PP_LiteSeg_T_STDC1_cityscapes | -/- |
| Segmentation | PP-HumanSegV2Lite | portrait | 53/50 |
| Segmentation | PP-HumanSegV2Lite | human | 53/50 |
| Face Detection | SCRFD | SCRFD-2.5G-kps-640 | 112/108 |
## TODO
以下为TODO计划，表示还正在准备支持，但是还存在问题或还可以改进的模型。
| 任务场景 | 模型 | 模型版本(表示已经测试的版本) | ARM CPU/RKNN速度(ms) |
|------------------|---------|---------------------|--------------------|
| Detection | PPYOLOE | PPYOLOE(int8) | -/- |
| Detection | YOLOv5 | YOLOv5-s_v6.2(int8) | -/- |
| Face Recognition | ArcFace | ArcFace_r18 | 600/3 |
| Face Recognition | cosFace | cosFace_r18 | 600/3 |
| Segmentation | PP-HumanSegV2Lite | portrait | 133/43 |
| Segmentation | PP-HumanSegV2Lite | human | 133/43 |
| Face Detection | SCRFD | SCRFD-2.5G-kps-640 | 108/42 |
## RKNPU2 Backend推理使用教程