PaddleSharp 
💗.NET Wrapper for PaddleInference C API, include PaddleOCR, PaddleDetection, Rotation Detector support Windows(x64), NVIDIA GPU and Linux(Ubuntu-20.04 x64).
PaddleOCR support 14 OCR languages model download on-demand, allow rotated text angle detection, 180 degree text detection.
PaddleDetection support PPYolo detection model and PicoDet model.
NuGet Packages/Docker Images
Infrastructure packages
| NuGet Package | Version | Description |
|---|---|---|
| Sdcb.PaddleInference |  |
Paddle Inference C API .NET binding |
| Sdcb.PaddleInference.runtime.win64.openblas |  |
Paddle Inference native windows-x64-openblas binding |
| Sdcb.PaddleInference.runtime.win64.mkl |  |
Paddle Inference native windows-x64-mkldnn binding |
Note: Linux does not need a native binding NuGet package like windows(Sdcb.PaddleInference.runtime.win64.mkl), instead, you can/should based from a Dockerfile to development:
| Docker Images | Version | Description |
|---|---|---|
| sdflysha/dotnet6-paddle |  |
PaddleInference 2.4.0, OpenCV 4.6.0, based on official Ubuntu 20.04 .NET 6 Runtime |
| sdflysha/dotnet6sdk-paddle |  |
PaddleInference 2.4.0, OpenCV 4.6.0, based on official Ubuntu 20.04 .NET 6 SDK |
Paddle Inference GPU package
Since GPU package are too large(>1.5GB), I cannot publish a NuGet package to nuget.org, there is a limitation of 250MB when upload to Github, there is some related issues to this:
However you're good to build your own GPU nuget package using 01-build-native.linq.
There is 2 old version GPU package here, might unable to use(not very large at that time):
| NuGet Package | Version | Description |
|---|---|---|
| Sdcb.PaddleInference.runtime.win64.cuda10_cudnn7 |  |
Paddle Inference native windows-x64(CUDA 10/cuDNN 7.x) binding |
| Sdcb.PaddleInference.runtime.win64.cuda11_cudnn8_tr7 |  |
Paddle Inference native windows-x64(CUDA 11/cuDNN 8.0/TensorRT 7) binding |
Here is the GPU package that I compiled(not from baidu):
| NuGet Package | Version | Description |
|---|---|---|
| cuda117_cudnn84_tr84_sm86 |  |
win64/CUDA 11.7/cuDNN 8.4/TensorRT 8.4/sm86 binding |
| cuda102_cudnn76_sm61_75 |  |
win64/CUDA 10.2/cuDNN 7.6/sm61+sm75 binding |
| cuda116_cudnn84_sm86_onnx |  |
win64/CUDA 11.6/cuDNN 8.4/sm86/onnx binding |
PaddleOCR packages
| NuGet Package | Version | Description |
|---|---|---|
| Sdcb.PaddleOCR |  |
PaddleOCR library(based on Sdcb.PaddleInference) |
| Sdcb.PaddleOCR.Models.Online |  |
Online PaddleOCR models, will download when first using |
| Sdcb.PaddleOCR.Models.LocalV3 |  |
Full local v3 models, include multiple language(~130MB) |
| Sdcb.PaddleOCR.KnownModels |  |
Old online model download helper, deprecated |
Rotation Detection packages(part of PaddleClass)
| NuGet Package | Version | Description |
|---|---|---|
| Sdcb.RotationDetector |  |
RotationDetector library(based on Sdcb.PaddleInference) |
PaddleDetection packages
| NuGet Package | Version | Description |
|---|---|---|
| Sdcb.PaddleDetection |  |
PaddleDetection library(based on Sdcb.PaddleInference) |
Usage
- PaddleOCR: PaddleOCR
- PaddleDetection: PaddleDetection
FAQ
Why my code runs good in my windows machine, but DllNotFoundException in other machine:
-
Please ensure the latest Visual C++ Redistributable was installed in
Windows(typically it should automatically installed if you haveVisual Studioinstalled) Otherwise, it will failed with following error(Windows only):DllNotFoundException: Unable to load DLL 'paddle_inference_c' or one of its dependencies (0x8007007E)If it's Unable to load DLL OpenCvSharpExtern.dll or one of its dependencies, then most likely the Media Foundation is not installed in windows server 2012 R2 machine:
-
Many old CPUs does not support AVX instructions, please ensure your CPU supports AVX, or download the x64-noavx-openblas dlls and disable Mkldnn:
PaddleConfig.Defaults.UseMkldnn = false; -
If you're using Win7-x64, and your CPU do support AVX2, then you might also need to extract following 3 dlls into
C:\Windows\System32folder to make it run:- api-ms-win-core-libraryloader-l1-2-0.dll
- api-ms-win-core-processtopology-obsolete-l1-1-0.dll
- API-MS-Win-Eventing-Provider-L1-1-0.dll
You can download these 3 dlls here: win7-x64-onnxruntime-missing-dlls.zip
How to enable GPU?
Enable GPU support can significantly improve the throughput and lower the CPU usage.
Steps to use GPU in windows:
- (for windows) Install the package:
Sdcb.PaddleInference.runtime.win64.cuda*instead ofSdcb.PaddleInference.runtime.win64.mkl, do not install both. - Install CUDA from NVIDIA, and configure environment variables to
PATHorLD_LIBRARY_PATH(linux) - Install cuDNN from NVIDIA, and configure environment variables to
PATHorLD_LIBRARY_PATH(linux) - Install TensorRT from NVIDIA, and configure environment variables to
PATHorLD_LIBRARY_PATH(linux)
You can refer this blog page for GPU in Windows: 关于PaddleSharp GPU使用 常见问题记录
If you're using Linux, you need to compile your own OpenCvSharp4 environment following the docker build scripts follow the CUDA/cuDNN/TensorRT configuration tasks.
After these steps completed, you can try specify PaddleDevice.Gpu() in paddle device configure parameter then enjoy🚀.
TensorRT
To use TensorRT, just specify PaddleDevice.Gpu().And(PaddleDevice.TensorRt("shape-info.txt")) instead of PaddleDevice.Gpu() to make it work.
Thanks & Sponsors
- 深圳-钱文松
- iNeuOS工业互联网操作系统：http://www.ineuos.net
Contact
QQ group of C#/.NET computer vision technical communicate(C#/.NET计算机视觉技术交流群): 579060605
