💗.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 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

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:

• PaddlePaddle/Paddle#43874
• NuGet/Home#11706 (comment)

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

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

NuGet Package	Version	Description
Sdcb.RotationDetector		RotationDetector library(based on Sdcb.PaddleInference)

NuGet Package	Version	Description
Sdcb.PaddleDetection		PaddleDetection library(based on Sdcb.PaddleInference)

• PaddleOCR: PaddleOCR
• PaddleDetection: PaddleDetection

1. Please ensure the latest Visual C++ Redistributable was installed in Windows(typically it should automatically installed if you have Visual Studio installed) 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:

2. 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;

3. 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\System32 folder 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

Enable GPU support can significantly improve the throughput and lower the CPU usage.

Steps to use GPU in windows:

1. (for windows) Install the package: Sdcb.PaddleInference.runtime.win64.cuda* instead of Sdcb.PaddleInference.runtime.win64.mkl, do not install both.
2. Install CUDA from NVIDIA, and configure environment variables to PATH or LD_LIBRARY_PATH(linux)
3. Install cuDNN from NVIDIA, and configure environment variables to PATH or LD_LIBRARY_PATH(linux)
4. Install TensorRT from NVIDIA, and configure environment variables to PATH or LD_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🚀.

To use TensorRT, just specify PaddleDevice.Gpu().And(PaddleDevice.TensorRt("shape-info.txt")) instead of PaddleDevice.Gpu() to make it work.

• 深圳-钱文松
• iNeuOS工业互联网操作系统：http://www.ineuos.net

QQ group of C#/.NET computer vision technical communicate(C#/.NET计算机视觉技术交流群): 579060605