English | 简体中文

💗 .NET Wrapper for PaddleInference C API, support Windows(x64) 💻, NVIDIA Cuda 10.2+ based GPU 🎮 and Linux(Ubuntu-22.04 x64) 🐧, currently contained following main components:

• PaddleOCR 📖 support 14 OCR languages model download on-demand, allow rotated text angle detection, 180 degree text detection, also support table recognition 📊.
• PaddleDetection 🎯 support PPYolo detection model and PicoDet model 🏹.
• RotationDetection 🔄 use Baidu's official text_image_orientation_infer model to detect text picture's rotation angle(0, 90, 180, 270).
• PaddleNLP ChineseSegmenter 📚 support PaddleNLP Lac Chinese segmenter model, supports tagging/customized words.
• Paddle2Onnx 🔄 Allow user export ONNX model using C#.

Please checkout this page 📄.

NuGet Package 💼	Version 📌	Description 📚
Sdcb.PaddleInference		Paddle Inference C API .NET binding ⚙️

Package	Version 📌	Description
Sdcb.PaddleInference.runtime.win64.mkl		win64+mkldnn
Sdcb.PaddleInference.runtime.win64.openblas		win64+openblas
Sdcb.PaddleInference.runtime.win64.openblas-noavx		no AVX, for old CPUs
Sdcb.PaddleInference.runtime.win64.cu120-sm86-89		for NVIDIA 30/40 series
Sdcb.PaddleInference.runtime.win64.cu120-sm80		for NVIDIA A100/A10
Sdcb.PaddleInference.runtime.win64.cu120-sm61-75		for NVIDIA 10/20 series

Note: cu120 means CUDA 12.0, it's compiled in CUDA 12.0.1/cuDNN 8.9.7.29/Tensor RT 8.6.1.6 version.

Linux OS packages(preview):

Package	Version 📌	Description
Sdcb.PaddleInference.runtime.linux-loongarch64		Loongnix GCC 8.2 Loongarch64
Sdcb.PaddleInference.runtime.linux64.mkl.gcc82		Linux-x64 GCC 8.2(tested in Ubuntu 22.04)

Be aware, as the Linux operating system cannot modify the value of LD_LIBRARY_PATH at runtime. If dependent dynamic libraries (such as libcommon.so) are loaded before the main dynamic library (such as libpaddle_inference_c.so), and also due to protobuf errors reported: PaddlePaddle/Paddle#62670

Therefore, all NuGet packages for Linux operating systems are in a preview state, and I'm unable to resolve this issue. Currently, if you are using the NuGet package on Linux, you need to manually specify the LD_LIBRARY_PATH environment variable before running the program, using the following commands:

• For x64 CPUs: export LD_LIBRARY_PATH=/<program directory>/bin/Debug/net8.0/runtimes/linux-x64/native:$LD_LIBRARY_PATH

• For Loongson 5000 or above CPUs (linux-loongarch64): export LD_LIBRARY_PATH=/<program directory>/bin/Debug/net8.0/runtimes/linux-loongarch64/native:$LD_LIBRARY_PATH

Some of packages already deprecated(Version <= 2.5.0):

Package	Version 📌	Description
Sdcb.PaddleInference.runtime.win64.cuda102_cudnn76_tr72_sm61_75		win64/CUDA 10.2/cuDNN 7.6/TensorRT 7.2/sm61+sm75
Sdcb.PaddleInference.runtime.win64.cuda118_cudnn86_tr85_sm86_89		win64/CUDA 11.8/cuDNN 8.6/TensorRT 8.5/sm86+sm89
Sdcb.PaddleInference.runtime.win64.cuda117_cudnn84_tr84_sm86		win64/CUDA 11.7/cuDNN 8.4/TensorRT 8.4/sm86
Sdcb.PaddleInference.runtime.win64.cuda102_cudnn76_sm61_75		win64/CUDA 10.2/cuDNN 7.6/sm61+sm75
Sdcb.PaddleInference.runtime.win64.cuda116_cudnn84_sm86_onnx		win64/CUDA 11.6/cuDNN 8.4/sm86/onnx

Any other packages that starts with Sdcb.PaddleInference.runtime might deprecated.

Baidu packages were downloaded from here: https://www.paddlepaddle.org.cn/inference/master/guides/install/download_lib.html#windows

All Windows packages were compiled manually by me.

Baidu official GPU packages are too large(>1.5GB) to publish 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) ❌

But You're good to build your own GPU nuget package using 01-build-native.linq 🛠️.

• Mkldnn - PaddleDevice.Mkldnn()

  Based on Mkldnn, generally fast

• Openblas - PaddleDevice.Openblas()

  Based on openblas, slower, but dependencies file smaller and consume lesser memory

• Onnx - PaddleDevice.Onnx()

  Based on onnxruntime, is also pretty fast and consume less memory

• Gpu - PaddleDevice.Gpu()

  Much faster but relies on NVIDIA GPU and CUDA

  If you wants to use GPU, you should refer to FAQ How to enable GPU? section, CUDA/cuDNN/TensorRT need to be installed manually.

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 fail with the 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 the Windows Server 2012 R2 machine:

2. Many old CPUs do not support AVX instructions, please ensure your CPU supports AVX, or download the x64-noavx-openblas DLLs and disable Mkldnn: PaddleDevice.Openblas() 🚀

3. If you're using Win7-x64, and your CPU does support AVX2, then you might also need to extract the 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.cu120* 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 to 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 and the CUDA/cuDNN/TensorRT configuration tasks. 🐧

After these steps are completed, you can try specifying PaddleDevice.Gpu() in the paddle device configuration parameter, then enjoy the performance boost! 🎉

• 崔亮 https://github.com/cuiliang
• 梁现伟
• 深圳-钱文松
• iNeuOS工业互联网操作系统：http:https://www.ineuos.net

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