apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[Doc] fix tutorials/vision_processor/README_CN.md README.md (#1870)

Browse Source 
* fix readme

* fix readme en

* fix readme op list

* Update README_CN.md

* Update README.md

---------

Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
This commit is contained in:
guxukai
2023-04-25 17:17:51 +08:00
committed by GitHub
parent 430fc424ac
commit 597fe57f28
2 changed files with 47 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
tutorials/vision_processor/README.md
View File

@@ -9,20 +9,42 @@ Vision Processor is used to implement model preprocessing, postprocessing, etc.
## C++
TODO(guxukai)
C++ API, Currently supported operators are as follows:
- Cast
- CenterCrop
- HWC2CHW
- Resize
- ResizeByShort
- NormalizeAndPermute
- Normalize
- Pad
- PadToSize
- StridePad
Users can inherit `ProcessorManager` when creating a `Preprocessor` class in the C++ deployment of the visual class model, and can choose to use OpenCV or CV-CUDA through `UseCuda()` in the `ProcessorManager` base class. The base class `ProcessorManager` implements GPU memory management, CUDA stream management, etc. Users only need to implement the `Apply()` function, in which operators in the multi-hardware image processing library are called to implement processing logic. For specific implementation, please refer to the sample code.
## Python
Python API, Currently supported operators are as follows:
- Cast
- CenterCrop
- HWC2CHW
- Resize
- ResizeByShort
- NormalizeAndPermute
- Normalize
- Pad
- PadToSize
- StridePad
Users can implement a image processing modules by inheriting the `PyProcessorManager` class. The base class `PyProcessorManager` implements GPU memory management, CUDA stream management, etc. Users only need to implement the apply() function by calling vision processors in this library and implements processing logic. For specific implementation, please refer to the demo code.
### Demo
- [Python Demo](python)
- [C++ Demo](cpp)
### Performance comparison between CV-CUDA and OpenCV: