Code Generation for a Deep Learning Simulink Model that Detect Defects on Printed Circuit Boards Using YOLOX Network

Third-Party Prerequisites

The list shows the hardware and software prerequisites for the MEX function generated in this example. For non-MEX builds such as static, dynamic libraries or executables, this example has additional requirements.

Download Pretrained YOLOX Detector

This example uses a pretrained version of the YOLOX object detector. The file is approximately 19MB in size. Download the files from the MathWorks website.

trainedPCBDefectDetectorNet_url = "https://ssd.mathworks.com/supportfiles/"+ ...
     "vision/data/trainedPCBDefectDetectorYOLOX.zip";
downloadTrainedNetwork(trainedPCBDefectDetectorNet_url,pwd);
matFile = "trainedPCBDefectDetectorYOLOX.mat";
load(matFile);

YOLOX Detector

The YOLOX object detector [1] uses CSP-DarkNet-53 as the base network and is retrained using the PCB defect data set [2][3]. The YOLOX network can detect six types of defect: missing hole, mouse bite, open circuit, short, spur, and spurious copper.

disp(detector);

  yoloxObjectDetector with properties:

                 ClassNames: {6×1 cell}
                  InputSize: [800 800 3]
    NormalizationStatistics: [1×1 struct]
                  ModelName: 'tiny-coco'

The yoloXDetect Entry-Point Function

The yoloXDetect entry-point function runs the detector on an input image by using the deep learning network in the trainedPCBDefectDetectorYOLOX.mat file. The entry-point function performs these operations:

type("yoloXDetect.m")

function [bboxes,scores,labels] = yoloXDetect(image,matFile)

% Copyright 2023 The MathWorks, Inc.

persistent myDetector;

if isempty(myDetector)
    myDetector = vision.loadYOLOXObjectDetector(matFile);
end

% Call to detect method
[bboxes,scores,labels] = detect(myDetector,image,Threshold = 0.6, ...
    AutoResize = 1);

Evaluate yoloXDetect Entry-Point Function

Evaluate the yoloXDetect entry-point function and display the results. By default, the example uses the 01_missing_hole_01.jpg as the sample image. This image has missing holes on the PCB.

sampleImage = imread("01_missing_hole_01.jpg");
sampleImage = imresize(sampleImage,[400 800]);
[bboxes,~,labels] = yoloXDetect(sampleImage,matFile);
labels = cellstr(labels);
defectsImage = insertObjectAnnotation(sampleImage,"rectangle",bboxes,labels);
imshow(defectsImage)
title("Predicted Defects - MATLAB Simulation")

YOLOX Defect Detection Simulink Model

The Simulink® model for performing PCB defect detection is shown. The YOLOX PCB Defect Detector MATLAB Function block uses the vision.loadYOLOXObjectDetector (Computer Vision Toolbox) function to load the pretrained YOLOX deep learning network. The MATLAB Function block calls the detect method to predict the bounding boxes, labels, and class-specific confidence scores. When the model runs, the Video Viewer block displays the input image along with the detected defects.

open_system("yolox_pcb_defect_detector");

Customize Configuration Parameters for Simulation

Open Configuration Parameters dialog box. In Simulation Target pane, select GPU acceleration. In the Deep Learning group, select the target library as TensorRT. You can also use the MATLAB commands:

set_param("yolox_pcb_defect_detector","GPUAcceleration","on");
set_param("yolox_pcb_defect_detector","SimDLTargetLibrary","tensorrt");

Run the Simulation

To build and simulate the yolox_pcb_defect_detector model, select Run on the Simulate tab or use the MATLAB command:

out = sim("yolox_pcb_defect_detector");

Customize Configuration Parameters for Code Generation

For code generation, open Configuration Parameters dialog box, in Code Generation pane, select the Language as C++ and enable Generate GPU code. Then, in the Interface settings, in the Deep Learning group, set Deep learning library to None. In the Code interface group, set Multi-instance code error diagnostic to None. You can also use the MATLAB commands:

set_param("yolox_pcb_defect_detector","GenerateGPUCode","CUDA");
set_param("yolox_pcb_defect_detector", "DLTargetLibrary","none");
set_param("yolox_pcb_defect_detector","MultiInstanceErrorCode","None")

You can write deep learning constants to their own data files during code generation and control the minimum size of the deep learning constants. In Code Generation pane, in the Advanced parameters group, set Large constant generation in MATLAB functions to Write only deep learning constatns to data files, and Large constant threshold in MATLAB functions (bytes) to 64. You can also use the MATLAB commands:

set_param("yolox_pcb_defect_detector","LargeConstantGeneration","WriteOnlyDNNConstantsToDataFiles");
set_param("yolox_pcb_defect_detector","LargeConstantThreshold",64);

In Hardware Implementation pane, set the production hardware device type. Then select Support long long to enable long long data type for simulation and code generation on the hardware. You can also use the MATLAB commands:

if ispc
    set_param("yolox_pcb_defect_detector","ProdHWDeviceType","Intel->x86-64 (Windows64)");
else
    set_param("yolox_pcb_defect_detector","ProdHWDeviceType","Intel->x86-64 (Linux 64)");
end
set_param("yolox_pcb_defect_detector","ProdLongLongMode","on");

Build the Simulink Model

Build the Simulink model on the host GPU by using the slbuild command or by pressing Ctrl+B. The code generator places the files in a build folder, a subfolder named yolox_pcb_defect_detector_grt_rtw under your current working folder.

slbuild('yolox_pcb_defect_detector');

References

[1] Ge, Zheng, Songtao Liu, Feng Wang, Zeming Li, and Jian Sun. "YOLOX: Exceeding YOLO Series in 2021", arXiv, August 6, 2021. https://arxiv.org/abs/2107.08430.

[2] Huang, Weibo, and Peng Wei. "A PCB Dataset for Defects Detection and Classification." Preprint, submitted January 23, 2019. https://arxiv.org/abs/1901.08204.

[3] PCB-DATASET. Accessed December 20, 2022. https://github.com/Ironbrotherstyle/PCB-DATASET.