Alturos.Yolo

A state of the art real-time object detection system for C# (Visual Studio). This project has CPU and GPU support, with GPU the detection works much faster. The primary goal of this project is an easy use of yolo, this package is available on nuget and you must only install two packages to start detection. In the background we are use the Windows Yolo version of AlexeyAB/darknet. Send an image path or the byte array to yolo and receive the position of the detected objects. Our project is meant to return the object-type and -position as processable data.

nuget

Quick install Alturos.Yolo over nuget

PM> install-package Alturos.Yolo (c# wrapper and c++ dlls 22MB)
PM> install-package Alturos.YoloV2TinyVocData (Pre-Trained Dataset 56MB)

Object Detection

Example code

Detect the type and the position of an image

var configurationDetector = new ConfigurationDetector();
var config = configurationDetector.Detect();
//using (var yoloWrapper = new YoloWrapper("yolov2-tiny-voc.cfg", "yolov2-tiny-voc.weights", "voc.names"))
using (var yoloWrapper = new YoloWrapper(config))
{
	var items = yoloWrapper.Detect(@"image.jpg");
	//items[0].Type -> "Person, Car, ..."
	//items[0].Confidence -> 0.0 (low) -> 1.0 (high)
	//items[0].X -> bounding box
	//items[0].Y -> bounding box
	//items[0].Width -> bounding box
	//items[0].Height -> bounding box
}

System requirements

• .NET Framework 4.6.1
• Microsoft Visual C++ 2017 Redistributable x64

GPU requirements (optional)

1. Install Nvidia CUDA Toolkit 9.2 (must be installed add a hardware driver for cuda support)
2. Download Nvidia cuDNN v7.1.4 for CUDA 9.2 (DLL cudnn64_7.dll required for gpu processing)

Build requirements

• Visual Studio 2017

Benchmark / Performance

Average processing speed of test images bird1.png, bird2.png, car1.png, motorbike1.png

CPU

Processor	YOLOv2-tiny	YOLOv3	yolo9000
Intel i7 3770	290 ms	2380 ms	-
Intel Xeon E5-1620 v3	207 ms	4327 ms	-
Intel Xeon E3-1240 v6	182 ms	3213 ms	-

GPU

Graphic card	Single precision	Memory	Slot	YOLOv2-tiny	YOLOv3	yolo9000
NVIDIA Quadro K420	300 GFLOPS	2 GB	Single	-	-	-
NVIDIA Quadro K620	768 GFLOPS	2 GB	Single	-	-	-
NVIDIA Quadro K1200	1151 GFLOPS	4 GB	Single	-	-	-
NVIDIA Quadro P400	599 GFLOPS	2 GB	Single	-	-	-
NVIDIA Quadro P600	1117 GFLOPS	2 GB	Single	-	-	-
NVIDIA Quadro P620	1386 GFLOPS	2 GB	Single	-	-	-
NVIDIA Quadro P1000	1862 GFLOPS	4 GB	Single	-	-	-
NVIDIA Quadro P2000	3011 GFLOPS	5 GB	Single	-	-	-
NVIDIA Quadro P4000	5304 GFLOPS	8 GB	Single	-	-	-
NVIDIA Quadro P5000	8873 GFLOPS	16 GB	Dual	-	-	-
NVIDIA GeForce GT 710	366 GFLOPS	2 GB	Single	-	-	-
NVIDIA GeForce GT 730	693 GFLOPS	2-4 GB	Single	-	-	-
NVIDIA GeForce GT 1030	1098 GFLOPS	2 GB	Single	40 ms	170 ms	-
NVIDIA GeForce GTX 1060	4372 GFLOPS	6 GB	Dual	25 ms	100 ms	-

Pre-Trained Dataset

Model	Processing Resolution	Cfg	Weights	Names
YOLOv3	608x608	yolov3.cfg	yolov3.weights	coco.names
YOLOv3-tiny	416x416	yolov3-tiny.cfg	yolov3.weights	coco.names
YOLOv2	608x608	yolov2.cfg	yolov2.weights	coco.names
YOLOv2-tiny	416x416	yolov2-tiny.cfg	yolov2-tiny.weights	voc.names
yolo9000	448x448	darknet9000.cfg	yolo9000.weights	9k.names

Annotation Tool

To marking bounded boxes of objects in images for training neural network you can use VoTT

Debugging Gpu Tool

Check graphic device usage "%PROGRAMFILES%\NVIDIA Corporation\NVSMI\nvidia-smi.exe"

Dataset of tagged images

http://cocodataset.org/

Directory Structure

.
├── Alturos.Yolo.dll              # C# yolo wrapper
├── x64/
│   ├── yolo_cpp_dll_cpu.dll      # yolo runtime for cpu
│   ├── yolo_cpp_dll_gpu.dll      # yolo runtime fot gpu
│   ├── cudnn64_7.dll             # required by yolo_cpp_dll_gpu (optional only required for gpu processig)
│   ├── opencv_world340.dll       # required by yolo_cpp_dll_xxx (process image as byte data detect_mat)
│   ├── pthreadGC2.dll            # required by yolo_cpp_dll_xxx (POSIX Threads)
│   ├── pthreadVC2.dll            # required by yolo_cpp_dll_xxx (POSIX Threads)
│   ├── msvcr100.dll              # required by pthread (POSIX Threads)