PaddleSharp 🌟

💗 .NET Wrapper for PaddleInference C API, support Windows(x64) 💻, NVIDIA Cuda 11.8+ 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#.

NuGet Packages/Docker Images 📦

Release notes 📝

Please checkout this page 📄.

Infrastructure packages 🏗️

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

Native Packages 🏗️

| Package | Version 📌 | Description | | ------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------ | | Sdcb.PaddleInference.runtime.win64.mkl | | Recommended for most users (CPU, MKL) | | Sdcb.PaddleInference.runtime.win64.openblas | | CPU, OpenBLAS | | Sdcb.PaddleInference.runtime.win64.openblas-noavx | | CPU, no AVX, for old CPUs | | Sdcb.PaddleInference.runtime.win64.cu118_cudnn89_sm61 | | CUDA 11.8, GTX 10 Series | | Sdcb.PaddleInference.runtime.win64.cu118_cudnn89_sm75 | | CUDA 11.8, RTX 20/GTX 16xx Series | | Sdcb.PaddleInference.runtime.win64.cu118_cudnn89_sm86 | | CUDA 11.8, RTX 30 Series | | Sdcb.PaddleInference.runtime.win64.cu118_cudnn89_sm89 | | CUDA 11.8, RTX 40 Series | | Sdcb.PaddleInference.runtime.win64.cu126_cudnn95_sm61 | | CUDA 12.6, GTX 10 Series | | Sdcb.PaddleInference.runtime.win64.cu126_cudnn95_sm75 | | CUDA 12.6, RTX 20/GTX 16xx Series | | Sdcb.PaddleInference.runtime.win64.cu126_cudnn95_sm86 | | CUDA 12.6, RTX 30 Series | | Sdcb.PaddleInference.runtime.win64.cu126_cudnn95_sm89 | | CUDA 12.6, RTX 40 Series | | Sdcb.PaddleInference.runtime.win64.cu129_cudnn910_sm61 | | CUDA 12.9, GTX 10 Series | | Sdcb.PaddleInference.runtime.win64.cu129_cudnn910_sm75 | | CUDA 12.9, RTX 20/GTX 16xx Series | | Sdcb.PaddleInference.runtime.win64.cu129_cudnn910_sm86 | | CUDA 12.9, RTX 30 Series | | Sdcb.PaddleInference.runtime.win64.cu129_cudnn910_sm89 | | CUDA 12.9, RTX 40 Series | | Sdcb.PaddleInference.runtime.win64.cu129_cudnn910_sm120 | | CUDA 12.9, RTX 50 Series | | Sdcb.PaddleInference.runtime.linux-x64.openblas | | Linux x64, OpenBLAS | | Sdcb.PaddleInference.runtime.linux-x64.mkl | | Linux x64, MKL | | Sdcb.PaddleInference.runtime.linux-x64 | | Linux x64, MKL+OpenVINO | | Sdcb.PaddleInference.runtime.linux-arm64 | | Linux ARM64 | | Sdcb.PaddleInference.runtime.osx-x64 | | macOS x64, include ONNXRuntime | | Sdcb.PaddleInference.runtime.osx-arm64 | | macOS ARM64 |

Package Selection Guide:

• We recommend Sdcb.PaddleInference.runtime.win64.mkl for most users. It offers the best balance between performance and package size. Please note that this package does not support GPU acceleration, making it suitable for most general scenarios.
• openblas-noavx is tailored for older CPUs that do not support the AVX2 instruction set.
• The remaining packages cover various CUDA combinations (GPU acceleration), supporting three CUDA versions:
  • CUDA 11.8: Supports 10–40 series NVIDIA GPUs
  • CUDA 12.6: Supports 10–40 series NVIDIA GPUs
  • CUDA 12.9: Supports 10–50 series NVIDIA GPUs

Important:
Not all GPU packages are suitable for every card. Please refer to the following GPU-to-sm suffix mapping:

| sm Suffix | Supported GPU Series | |-------------|-------------------------------------------| | sm61 | GTX 10 Series | | sm75 | RTX 20 Series (and GTX 16xx series such as GTX 1660) | | sm86 | RTX 30 Series | | sm89 | RTX 40 Series | | sm120 | RTX 50 Series (supported by CUDA 12.9 only) |

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

All packages were co