apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-11-03 11:02:01 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

[CVCUDA] PP-OCR detector preprocessor integrate CV-CUDA (#1382)

Browse Source 
* move manager initialized_ flag to ppcls

* update dbdetector preprocess api

* declare processor op

* ppocr detector preprocessor support cvcuda

* move cvcuda op to class member

* ppcls use manager register api

* refactor det preprocessor init api

* add set preprocessor api

* add create processor macro

* new processor call api

* ppcls preprocessor init resize on cpu

* ppocr detector preprocessor set normalize api

* revert ppcls pybind

* remove dbdetector set preprocessor

* refine dbdetector preprocessor includes

* remove mean std in py constructor

* add comments

* update comment

* Update __init__.py
This commit is contained in:
Wang Xinyu
2023-02-22 19:39:11 +08:00
committed by GitHub
parent 2f8d9c9a57
commit 91a1c72f98
24 changed files with 448 additions and 330 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
fastdeploy/vision/classification/ppcls/preprocessor.h
View File

@@ -55,6 +55,7 @@ class FASTDEPLOY_DECL PaddleClasPreprocessor : public ProcessorManager {
private:
bool BuildPreprocessPipelineFromConfig();
bool initialized_ = false;
std::vector<std::shared_ptr<Processor>> processors_;
// for recording the switch of hwc2chw
bool disable_permute_ = false;