apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-07 01:22:59 +08:00
Code Issues Actions 2 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
python/fastdeploy/vision/classification/ppcls/__init__.py
View File

@@ -46,7 +46,6 @@ class PaddleClasPreprocessor(ProcessorManager):
When the initial operator is Resize, and input image size is large,
maybe it's better to run resize on CPU, because the HostToDevice memcpy
is time consuming. Set this True to run the initial resize on CPU.
:param: v: True or False
"""
self._manager.initial_resize_on_cpu(v)