This example shows how to generate CUDA® MEX for a you only look once (YOLO) v2 object detector. A YOLO v2 object detection network is composed of two subnetworks. A feature extraction network followed by a detection network. This example generates code for the network trained in theObject Detection Using YOLO v2 Deep Learningexample from Computer Vision Toolbox™. For more information, seeObject Detection Using YOLO v2 Deep Learning(Computer Vision Toolbox). You can modify this example to generate CUDA® MEX for the network imported in theImport Pretrained ONNX YOLO v2 Object Detectorexample from Computer Vision Toolbox™. For more information, seeImport Pretrained ONNX YOLO v2 Object Detector(Computer Vision Toolbox).
Required
This example generates CUDA MEX and has the following third-party requirements.
CUDA® enabled NVIDIA® GPU and compatible driver.
Optional
For non-MEX builds such as static, dynamic libraries or executables, this example has the following additional requirements.
NVIDIA toolkit.
NVIDIA cuDNN library.
Environment variables for the compilers and libraries. For more information, seeThird-Party Hardware(GPU Coder)andSetting Up the Prerequisite Products(GPU Coder).
Use thecoder.checkGpuInstall
(GPU Coder)function to verify that the compilers and libraries necessary for running this example are set up correctly.
envCfg = coder.gpuEnvConfig('host'); envCfg.DeepLibTarget ='cudnn'; envCfg.DeepCodegen = 1; envCfg.Quiet = 1; coder.checkGpuInstall(envCfg);
This example uses theyolov2ResNet50VehicleExample
MAT-file containing the pretrained network. The file is approximately 98MB in size. Download the file from the MathWorks website.
matFile = matlab.internal.examples.downloadSupportFile('vision/data','yolov2ResNet50VehicleExample.mat'); vehicleDetector = load(matFile); net = vehicleDetector.detector.Network
net = DAGNetwork with properties: Layers: [150×1 nnet.cnn.layer.Layer] Connections: [162×2 table] InputNames: {'input_1'} OutputNames: {'yolov2OutputLayer'}
The DAG network contains 150 layers including convolution, ReLU, and batch normalization layers and the YOLO v2 transform and YOLO v2 output layers. To display an interactive visualization of the deep learning network architecture, use theanalyzeNetwork
function.
analyzeNetwork(net);
yolov2_detect
Entry-Point FunctionTheyolov2_detect.m
entry-point function takes an image input and runs the detector on the image using the deep learning network saved in theyolov2ResNet50VehicleExample.mat
file. The function loads the network object from theyolov2ResNet50VehicleExample.mat
file into a persistent variableyolov2Objand reuses the persistent object on subsequent detection calls.
type('yolov2_detect.m')
function outImg = yolov2_detect(in,matFile) % Copyright 2018-2021 The MathWorks, Inc. persistent yolov2Obj; if isempty(yolov2Obj) yolov2Obj = coder.loadDeepLearningNetwork(matFile); end % Call to detect method [bboxes,~,labels] = yolov2Obj.detect(in,'Threshold',0.5); % Convert categorical labels to cell array of charactor vectors labels = cellstr(labels); % Annotate detections in the image. outImg = insertObjectAnnotation(in,'rectangle',bboxes,labels);
To generate CUDA code for the entry-point function, create a GPU code configuration object for a MEX target and set the target language to C++. Use thecoder.DeepLearningConfig
(GPU Coder)function to create aCuDNN
deep learning configuration object and assign it to theDeepLearningConfig
property of the GPU code configuration object. Run thecodegen
command specifying an input size of 224-by-224-by-3. This value corresponds to the input layer size of YOLOv2.
cfg = coder.gpuConfig('mex'); cfg.TargetLang ='C++'; cfg.DeepLearningConfig = coder.DeepLearningConfig('cudnn'); cfg.GenerateReport = true; inputArgs = {ones(224,224,3,“uint8”),coder.Constant(matFile)}; codegen-configcfgyolov2_detect-argsinputArgs
Code generation successful: View report
Set up the video file reader and read the input video. Create a video player to display the video and the output detections.
videoFile ='highway_lanechange.mp4'; videoFreader = vision.VideoFileReader(videoFile,'VideoOutputDataType',“uint8”); depVideoPlayer = vision.DeployableVideoPlayer('Size','Custom','CustomSize',[640 480]);
Read the video input frame-by-frame and detect the vehicles in the video using the detector.
cont = ~isDone(videoFreader);whilecont I = step(videoFreader); in = imresize(I,[224,224]); out = yolov2_detect_mex(in,matFile); step(depVideoPlayer, out);% Exit the loop if the video player figure window is closedcont = ~isDone(videoFreader) && isOpen(depVideoPlayer);end
[1] Redmon, Joseph, and Ali Farhadi. "YOLO9000: Better, Faster, Stronger." 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2017.
Copyright 2017-2021The MathWorks, Inc.