-
-
Sample_Matches
-
All_Mismatches
Contents
- Load train Data
- Size of first image in dataset
- Load Test Data
- Calculate the number of images in each category.
- Define Network Architecture
- Specify Training Options
- Train Network Using Training Data
- Classify validation
- Compute Accuracy
- move diary file
- Test one at a time
- Find the square root of the false matches to determine the subplots
- Recalbirating true and false
- start plotting mismatches
- start plotting sample of correct match
% Biometric Systems % CYS616 % CONVOLUTIONAL NEURAL NETWORK FOR IRIS RECOGNITION clc; % Clear the command window. close all; % Close all figures (except those of imtool.) clear; % Erase all existing variables. Or clearvars if you want. workspace; % Make sure the workspace panel is showing. reset(gpuDevice); % Reset GPU memory diary Progress.txt diary on
Load train Data
categories = {
'001','002','003','004','005','006','007','008','009','010', ...
'011','012','013','014','015','016','017','018','019','020', ...
'021','022','023','024','025','026','027','028','029','030', ...
'031','032','033','034','035','036','037','038','039','040', ...
'041','042','043','044','045','046','047','048','049','050', ...
'051','052','053','054','055','056','057','058','059','060', ...
'061','062','063','064','065','066','067','068','069','070', ...
'071','072','073','074','075','076','077','078','079','080', ...
'081','082','083','084','085','086','087','088','089','090', ...
'091','092','093','094','095','096','097','098','099','100', ...
'101','102','103','104','105','106','107','108','109','110', ...
'111','112','113','114','115','116','117','118','119','120', ...
'121','122','123','124','125','126','127','128','129','130', ...
'131','132','133','134','135','136','137','138','139','140', ...
'141','142','143','144','145','146','147','148','149','150', ...
'151','152','153','154','155','156','157','158','159','160', ...
'161','162','163','164','165','166','167','168','169','170', ...
'171','172','173','174','175','176','177','178','179','180', ...
'181','182','183','184','185','186','187','188','189','190', ...
'191','192','193','194','195','196','197','198','199','200', ...
'201','202','203','204','205','206','207','208','209','210', ...
'211','212','213','214','215','216','217','218','219','220', ...
'221','222','223'};
imdsTrain = imageDatastore(fullfile(pwd,'Dataset/TrainData', categories),'IncludeSubfolders',true,'FileExtensions','.bmp','LabelSource','foldernames');
num_train = size(imdsTrain.Files,1);
Size of first image in dataset
img = readimage(imdsTrain,1);
[x , y , z] = size(img);
Load Test Data
imdsValidation = imageDatastore(fullfile(pwd,'Dataset/TestData', categories),'IncludeSubfolders',true,'FileExtensions','.bmp','LabelSource','foldernames'); num_test = size(imdsValidation.Files,1);
Calculate the number of images in each category.
labelCount = countEachLabel(imdsTrain);
Define Network Architecture
layers = [
imageInputLayer([x y z]);
convolution2dLayer(3,8,'Padding','same')
batchNormalizationLayer
reluLayer();
maxPooling2dLayer(5,'Stride',2)
convolution2dLayer(3,16,'Padding','same')
batchNormalizationLayer
reluLayer();
averagePooling2dLayer(5,'Stride',2)
convolution2dLayer(3,16,'Padding','same')
batchNormalizationLayer
reluLayer();
maxPooling2dLayer(5,'Stride',2)
convolution2dLayer(3,32,'Padding','same')
batchNormalizationLayer
reluLayer();
averagePooling2dLayer(5,'Stride',2)
convolution2dLayer(3,32,'Padding','same')
batchNormalizationLayer
reluLayer();
fullyConnectedLayer(size(categories,2),'BiasLearnRateFactor',2);
softmaxLayer
classificationLayer];
Specify Training Options
options = trainingOptions('sgdm', ...
'InitialLearnRate', 0.001, ...
'ValidationData',imdsValidation, ...
'ValidationFrequency',100, ...
'Shuffle','every-epoch', ...
'MaxEpochs', 10, ...
'MiniBatchSize', 8, ...
'LearnRateSchedule','piecewise', ...
'LearnRateDropFactor',0.5, ...
'LearnRateDropPeriod',50, ...
'ExecutionEnvironment','gpu', ...
'Verbose', true, 'VerboseFrequency', 10);
Train Network Using Training Data
[net_Wael, info] = trainNetwork(imdsTrain,layers,options);
save('TrainedNetwork.mat','net_Wael')
movefile('TrainedNetwork.mat','results')
Initializing input data normalization. |======================================================================================================================| | Epoch | Iteration | Time Elapsed | Mini-batch | Validation | Mini-batch | Validation | Base Learning | | | | (hh:mm:ss) | Accuracy | Accuracy | Loss | Loss | Rate | |======================================================================================================================| | 1 | 1 | 00:00:03 | 0.00% | 0.30% | 5.8989 | 5.8493 | 0.0010 | | 1 | 10 | 00:00:03 | 0.00% | | 6.3078 | | 0.0010 | | 1 | 20 | 00:00:04 | 0.00% | | 5.7647 | | 0.0010 | | 1 | 30 | 00:00:04 | 12.50% | | 4.6819 | | 0.0010 | | 1 | 40 | 00:00:05 | 0.00% | | 6.0511 | | 0.0010 | | 1 | 50 | 00:00:05 | 12.50% | | 5.2941 | | 0.0010 | | 1 | 60 | 00:00:06 | 25.00% | | 4.8073 | | 0.0010 | | 1 | 70 | 00:00:06 | 0.00% | | 5.5946 | | 0.0010 | | 1 | 80 | 00:00:07 | 0.00% | | 4.9676 | | 0.0010 | | 1 | 90 | 00:00:08 | 12.50% | | 4.1375 | | 0.0010 | | 1 | 100 | 00:00:11 | 25.00% | 20.48% | 4.5945 | 4.1891 | 0.0010 | | 1 | 110 | 00:00:11 | 0.00% | | 5.6557 | | 0.0010 | | 1 | 120 | 00:00:12 | 25.00% | | 4.4698 | | 0.0010 | | 1 | 130 | 00:00:12 | 25.00% | | 3.4383 | | 0.0010 | | 1 | 140 | 00:00:13 | 37.50% | | 4.0359 | | 0.0010 | | 1 | 150 | 00:00:13 | 25.00% | | 3.3781 | | 0.0010 | | 1 | 160 | 00:00:14 | 12.50% | | 3.2702 | | 0.0010 | | 1 | 170 | 00:00:14 | 37.50% | | 2.7774 | | 0.0010 | | 1 | 180 | 00:00:15 | 25.00% | | 3.2226 | | 0.0010 | | 1 | 190 | 00:00:16 | 37.50% | | 2.7147 | | 0.0010 | | 2 | 200 | 00:00:18 | 37.50% | 48.13% | 2.5095 | 2.4462 | 0.0010 | | 2 | 210 | 00:00:19 | 75.00% | | 1.3925 | | 0.0010 | | 2 | 220 | 00:00:19 | 50.00% | | 2.9466 | | 0.0010 | | 2 | 230 | 00:00:20 | 50.00% | | 2.5476 | | 0.0010 | | 2 | 240 | 00:00:20 | 75.00% | | 1.8553 | | 0.0010 | | 2 | 250 | 00:00:21 | 50.00% | | 2.1814 | | 0.0010 | | 2 | 260 | 00:00:22 | 75.00% | | 1.3891 | | 0.0010 | | 2 | 270 | 00:00:22 | 50.00% | | 2.0654 | | 0.0010 | | 2 | 280 | 00:00:23 | 87.50% | | 0.8888 | | 0.0010 | | 2 | 290 | 00:00:23 | 75.00% | | 1.2809 | | 0.0010 | | 2 | 300 | 00:00:26 | 87.50% | 70.70% | 1.7367 | 1.4797 | 0.0010 | | 2 | 310 | 00:00:26 | 87.50% | | 0.7486 | | 0.0010 | | 2 | 320 | 00:00:27 | 75.00% | | 1.1256 | | 0.0010 | | 2 | 330 | 00:00:28 | 87.50% | | 0.9025 | | 0.0010 | | 2 | 340 | 00:00:28 | 100.00% | | 0.7769 | | 0.0010 | | 2 | 350 | 00:00:29 | 100.00% | | 0.5883 | | 0.0010 | | 2 | 360 | 00:00:29 | 87.50% | | 0.6106 | | 0.0010 | | 2 | 370 | 00:00:30 | 75.00% | | 0.6648 | | 0.0010 | | 2 | 380 | 00:00:30 | 100.00% | | 0.4217 | | 0.0010 | | 2 | 390 | 00:00:31 | 100.00% | | 0.5894 | | 0.0010 | | 3 | 400 | 00:00:33 | 100.00% | 86.10% | 0.4794 | 0.8252 | 0.0010 | | 3 | 410 | 00:00:34 | 100.00% | | 0.1444 | | 0.0010 | | 3 | 420 | 00:00:35 | 87.50% | | 0.4606 | | 0.0010 | | 3 | 430 | 00:00:35 | 75.00% | | 0.5521 | | 0.0010 | | 3 | 440 | 00:00:36 | 100.00% | | 0.1855 | | 0.0010 | | 3 | 450 | 00:00:36 | 87.50% | | 0.3960 | | 0.0010 | | 3 | 460 | 00:00:37 | 87.50% | | 0.4560 | | 0.0010 | | 3 | 470 | 00:00:37 | 87.50% | | 0.5018 | | 0.0010 | | 3 | 480 | 00:00:38 | 100.00% | | 0.2638 | | 0.0010 | | 3 | 490 | 00:00:38 | 87.50% | | 0.3632 | | 0.0010 | | 3 | 500 | 00:00:41 | 100.00% | 91.33% | 0.1457 | 0.5355 | 0.0010 | | 3 | 510 | 00:00:42 | 87.50% | | 0.3922 | | 0.0010 | | 3 | 520 | 00:00:42 | 100.00% | | 0.1587 | | 0.0010 | | 3 | 530 | 00:00:43 | 100.00% | | 0.1844 | | 0.0010 | | 3 | 540 | 00:00:43 | 100.00% | | 0.1165 | | 0.0010 | | 3 | 550 | 00:00:44 | 100.00% | | 0.6054 | | 0.0010 | | 3 | 560 | 00:00:45 | 100.00% | | 0.0861 | | 0.0010 | | 3 | 570 | 00:00:45 | 100.00% | | 0.0987 | | 0.0010 | | 3 | 580 | 00:00:46 | 100.00% | | 0.2619 | | 0.0010 | | 4 | 590 | 00:00:46 | 100.00% | | 0.0685 | | 0.0010 | | 4 | 600 | 00:00:49 | 100.00% | 94.47% | 0.0628 | 0.4107 | 0.0010 | | 4 | 610 | 00:00:50 | 100.00% | | 0.0989 | | 0.0010 | | 4 | 620 | 00:00:50 | 100.00% | | 0.0897 | | 0.0010 | | 4 | 630 | 00:00:51 | 100.00% | | 0.1051 | | 0.0010 | | 4 | 640 | 00:00:51 | 100.00% | | 0.0589 | | 0.0010 | | 4 | 650 | 00:00:52 | 100.00% | | 0.1304 | | 0.0010 | | 4 | 660 | 00:00:52 | 100.00% | | 0.1253 | | 0.0010 | | 4 | 670 | 00:00:53 | 100.00% | | 0.0776 | | 0.0010 | | 4 | 680 | 00:00:53 | 100.00% | | 0.0596 | | 0.0010 | | 4 | 690 | 00:00:54 | 100.00% | | 0.0640 | | 0.0010 | | 4 | 700 | 00:00:57 | 100.00% | 95.81% | 0.0766 | 0.3357 | 0.0010 | | 4 | 710 | 00:00:57 | 100.00% | | 0.0595 | | 0.0010 | | 4 | 720 | 00:00:58 | 100.00% | | 0.0207 | | 0.0010 | | 4 | 730 | 00:00:58 | 100.00% | | 0.0253 | | 0.0010 | | 4 | 740 | 00:00:59 | 100.00% | | 0.0761 | | 0.0010 | | 4 | 750 | 00:00:59 | 100.00% | | 0.1142 | | 0.0010 | | 4 | 760 | 00:01:00 | 100.00% | | 0.0487 | | 0.0010 | | 4 | 770 | 00:01:00 | 100.00% | | 0.0661 | | 0.0010 | | 4 | 780 | 00:01:01 | 100.00% | | 0.0962 | | 0.0010 | | 5 | 790 | 00:01:01 | 100.00% | | 0.0182 | | 0.0010 | | 5 | 800 | 00:01:04 | 100.00% | 95.22% | 0.0296 | 0.3024 | 0.0010 | | 5 | 810 | 00:01:05 | 100.00% | | 0.0279 | | 0.0010 | | 5 | 820 | 00:01:05 | 100.00% | | 0.0272 | | 0.0010 | | 5 | 830 | 00:01:06 | 100.00% | | 0.0298 | | 0.0010 | | 5 | 840 | 00:01:06 | 100.00% | | 0.0548 | | 0.0010 | | 5 | 850 | 00:01:07 | 100.00% | | 0.0499 | | 0.0010 | | 5 | 860 | 00:01:07 | 100.00% | | 0.0150 | | 0.0010 | | 5 | 870 | 00:01:08 | 100.00% | | 0.0194 | | 0.0010 | | 5 | 880 | 00:01:09 | 100.00% | | 0.0747 | | 0.0010 | | 5 | 890 | 00:01:09 | 100.00% | | 0.0809 | | 0.0010 | | 5 | 900 | 00:01:12 | 100.00% | 96.71% | 0.0372 | 0.2745 | 0.0010 | | 5 | 910 | 00:01:12 | 100.00% | | 0.0237 | | 0.0010 | | 5 | 920 | 00:01:13 | 100.00% | | 0.0249 | | 0.0010 | | 5 | 930 | 00:01:14 | 100.00% | | 0.0268 | | 0.0010 | | 5 | 940 | 00:01:14 | 100.00% | | 0.0201 | | 0.0010 | | 5 | 950 | 00:01:15 | 100.00% | | 0.0362 | | 0.0010 | | 5 | 960 | 00:01:15 | 100.00% | | 0.0328 | | 0.0010 | | 5 | 970 | 00:01:16 | 100.00% | | 0.0349 | | 0.0010 | | 6 | 980 | 00:01:16 | 100.00% | | 0.0244 | | 0.0010 | | 6 | 990 | 00:01:17 | 100.00% | | 0.0154 | | 0.0010 | | 6 | 1000 | 00:01:20 | 100.00% | 96.56% | 0.0196 | 0.2753 | 0.0010 | | 6 | 1010 | 00:01:20 | 100.00% | | 0.0427 | | 0.0010 | | 6 | 1020 | 00:01:21 | 100.00% | | 0.0230 | | 0.0010 | | 6 | 1030 | 00:01:21 | 100.00% | | 0.0460 | | 0.0010 | | 6 | 1040 | 00:01:22 | 100.00% | | 0.0298 | | 0.0010 | | 6 | 1050 | 00:01:22 | 100.00% | | 0.0227 | | 0.0010 | | 6 | 1060 | 00:01:23 | 100.00% | | 0.0442 | | 0.0010 | | 6 | 1070 | 00:01:23 | 100.00% | | 0.0120 | | 0.0010 | | 6 | 1080 | 00:01:24 | 100.00% | | 0.1166 | | 0.0010 | | 6 | 1090 | 00:01:25 | 100.00% | | 0.0333 | | 0.0010 | | 6 | 1100 | 00:01:27 | 100.00% | 96.11% | 0.0192 | 0.2617 | 0.0010 | | 6 | 1110 | 00:01:28 | 100.00% | | 0.0398 | | 0.0010 | | 6 | 1120 | 00:01:28 | 100.00% | | 0.0294 | | 0.0010 | | 6 | 1130 | 00:01:29 | 100.00% | | 0.0256 | | 0.0010 | | 6 | 1140 | 00:01:29 | 100.00% | | 0.0682 | | 0.0010 | | 6 | 1150 | 00:01:30 | 100.00% | | 0.0215 | | 0.0010 | | 6 | 1160 | 00:01:31 | 100.00% | | 0.0304 | | 0.0010 | | 6 | 1170 | 00:01:31 | 100.00% | | 0.0210 | | 0.0010 | | 7 | 1180 | 00:01:32 | 100.00% | | 0.0117 | | 0.0010 | | 7 | 1190 | 00:01:32 | 100.00% | | 0.0163 | | 0.0010 | | 7 | 1200 | 00:01:35 | 100.00% | 95.96% | 0.0204 | 0.2605 | 0.0010 | | 7 | 1210 | 00:01:36 | 100.00% | | 0.0172 | | 0.0010 | | 7 | 1220 | 00:01:36 | 100.00% | | 0.0626 | | 0.0010 | | 7 | 1230 | 00:01:37 | 100.00% | | 0.0245 | | 0.0010 | | 7 | 1240 | 00:01:37 | 100.00% | | 0.0150 | | 0.0010 | | 7 | 1250 | 00:01:38 | 100.00% | | 0.0216 | | 0.0010 | | 7 | 1260 | 00:01:38 | 100.00% | | 0.0168 | | 0.0010 | | 7 | 1270 | 00:01:39 | 100.00% | | 0.0243 | | 0.0010 | | 7 | 1280 | 00:01:39 | 100.00% | | 0.0195 | | 0.0010 | | 7 | 1290 | 00:01:40 | 100.00% | | 0.0259 | | 0.0010 | | 7 | 1300 | 00:01:43 | 100.00% | 96.56% | 0.0450 | 0.2477 | 0.0010 | | 7 | 1310 | 00:01:43 | 100.00% | | 0.0311 | | 0.0010 | | 7 | 1320 | 00:01:44 | 100.00% | | 0.0367 | | 0.0010 | | 7 | 1330 | 00:01:44 | 100.00% | | 0.0388 | | 0.0010 | | 7 | 1340 | 00:01:45 | 100.00% | | 0.0157 | | 0.0010 | | 7 | 1350 | 00:01:45 | 100.00% | | 0.0188 | | 0.0010 | | 7 | 1360 | 00:01:46 | 100.00% | | 0.0161 | | 0.0010 | | 8 | 1370 | 00:01:47 | 100.00% | | 0.0161 | | 0.0010 | | 8 | 1380 | 00:01:47 | 100.00% | | 0.0246 | | 0.0010 | | 8 | 1390 | 00:01:48 | 100.00% | | 0.0162 | | 0.0010 | | 8 | 1400 | 00:01:50 | 100.00% | 96.86% | 0.0243 | 0.2382 | 0.0010 | | 8 | 1410 | 00:01:51 | 100.00% | | 0.0179 | | 0.0010 | | 8 | 1420 | 00:01:52 | 100.00% | | 0.0203 | | 0.0010 | | 8 | 1430 | 00:01:52 | 100.00% | | 0.0103 | | 0.0010 | | 8 | 1440 | 00:01:53 | 100.00% | | 0.0100 | | 0.0010 | | 8 | 1450 | 00:01:53 | 100.00% | | 0.0158 | | 0.0010 | | 8 | 1460 | 00:01:54 | 100.00% | | 0.0301 | | 0.0010 | | 8 | 1470 | 00:01:54 | 100.00% | | 0.0258 | | 0.0010 | | 8 | 1480 | 00:01:55 | 100.00% | | 0.0369 | | 0.0010 | | 8 | 1490 | 00:01:55 | 100.00% | | 0.0241 | | 0.0010 | | 8 | 1500 | 00:01:58 | 100.00% | 95.96% | 0.0207 | 0.2491 | 0.0010 | | 8 | 1510 | 00:01:59 | 100.00% | | 0.0134 | | 0.0010 | | 8 | 1520 | 00:01:59 | 100.00% | | 0.0139 | | 0.0010 | | 8 | 1530 | 00:02:00 | 100.00% | | 0.0120 | | 0.0010 | | 8 | 1540 | 00:02:00 | 100.00% | | 0.0206 | | 0.0010 | | 8 | 1550 | 00:02:01 | 100.00% | | 0.0297 | | 0.0010 | | 8 | 1560 | 00:02:01 | 100.00% | | 0.0320 | | 0.0010 | | 9 | 1570 | 00:02:02 | 100.00% | | 0.0101 | | 0.0010 | | 9 | 1580 | 00:02:02 | 100.00% | | 0.0545 | | 0.0010 | | 9 | 1590 | 00:02:03 | 100.00% | | 0.0088 | | 0.0010 | | 9 | 1600 | 00:02:06 | 100.00% | 96.41% | 0.0123 | 0.2439 | 0.0010 | | 9 | 1610 | 00:02:06 | 100.00% | | 0.0150 | | 0.0010 | | 9 | 1620 | 00:02:07 | 100.00% | | 0.0313 | | 0.0010 | | 9 | 1630 | 00:02:07 | 100.00% | | 0.0161 | | 0.0010 | | 9 | 1640 | 00:02:08 | 100.00% | | 0.0135 | | 0.0010 | | 9 | 1650 | 00:02:09 | 100.00% | | 0.0152 | | 0.0010 | | 9 | 1660 | 00:02:09 | 100.00% | | 0.0113 | | 0.0010 | | 9 | 1670 | 00:02:10 | 100.00% | | 0.0139 | | 0.0010 | | 9 | 1680 | 00:02:10 | 100.00% | | 0.0090 | | 0.0010 | | 9 | 1690 | 00:02:11 | 100.00% | | 0.0134 | | 0.0010 | | 9 | 1700 | 00:02:14 | 100.00% | 95.96% | 0.0139 | 0.2346 | 0.0010 | | 9 | 1710 | 00:02:14 | 100.00% | | 0.0166 | | 0.0010 | | 9 | 1720 | 00:02:15 | 100.00% | | 0.0131 | | 0.0010 | | 9 | 1730 | 00:02:15 | 100.00% | | 0.0090 | | 0.0010 | | 9 | 1740 | 00:02:16 | 100.00% | | 0.0107 | | 0.0010 | | 9 | 1750 | 00:02:17 | 100.00% | | 0.0107 | | 0.0010 | | 10 | 1760 | 00:02:17 | 100.00% | | 0.0093 | | 0.0010 | | 10 | 1770 | 00:02:18 | 100.00% | | 0.0084 | | 0.0010 | | 10 | 1780 | 00:02:18 | 100.00% | | 0.0078 | | 0.0010 | | 10 | 1790 | 00:02:19 | 100.00% | | 0.0118 | | 0.0010 | | 10 | 1800 | 00:02:22 | 100.00% | 96.56% | 0.0142 | 0.2341 | 0.0010 | | 10 | 1810 | 00:02:22 | 100.00% | | 0.0159 | | 0.0010 | | 10 | 1820 | 00:02:23 | 100.00% | | 0.0354 | | 0.0010 | | 10 | 1830 | 00:02:23 | 100.00% | | 0.0094 | | 0.0010 | | 10 | 1840 | 00:02:24 | 100.00% | | 0.0171 | | 0.0010 | | 10 | 1850 | 00:02:24 | 100.00% | | 0.0161 | | 0.0010 | | 10 | 1860 | 00:02:25 | 100.00% | | 0.0131 | | 0.0010 | | 10 | 1870 | 00:02:25 | 100.00% | | 0.0350 | | 0.0010 | | 10 | 1880 | 00:02:26 | 100.00% | | 0.0247 | | 0.0010 | | 10 | 1890 | 00:02:27 | 100.00% | | 0.0101 | | 0.0010 | | 10 | 1900 | 00:02:29 | 100.00% | 96.71% | 0.0116 | 0.2256 | 0.0010 | | 10 | 1910 | 00:02:30 | 100.00% | | 0.0085 | | 0.0010 | | 10 | 1920 | 00:02:31 | 100.00% | | 0.0072 | | 0.0010 | | 10 | 1930 | 00:02:31 | 100.00% | | 0.0149 | | 0.0010 | | 10 | 1940 | 00:02:32 | 100.00% | | 0.0155 | | 0.0010 | | 10 | 1950 | 00:02:35 | 100.00% | 96.41% | 0.0190 | 0.2316 | 0.0010 | |======================================================================================================================|
Classify validation
labels = classify(net_Wael,imdsValidation);
Compute Accuracy
YValidation = imdsValidation.Labels;
accuracy02 = sum(labels == YValidation)/numel(YValidation)*100;
dis=['The final accuracy rate is: ', num2str(accuracy02,'%2.2f'), '%'];
disp(dis);
diary off
The final accuracy rate is: 97.16%
move diary file
movefile('Progress.txt','results')
Test one at a time
true=0;
false=0;
for i = 1:size(imdsValidation.Files,1)
if labels(i) == imdsValidation.Labels(i)
true=true+1;
else
false=false+1;
end
end
Find the square root of the false matches to determine the subplots
f0=floor(sqrt(false));
if f0 == sqrt(false)
f1=f0;
else
f1=f0+1;
end
Recalbirating true and false
true=0;
false=0;
start plotting mismatches
falsefig = figure('Name','All Mismatch Pictures','Visible','off','Units', 'Normalized', 'OuterPosition', [0, 0.04, 1, 0.96]);
for i = 1:size(imdsValidation.Files,1)
imf = imread(imdsValidation.Files{i});
if labels(i) ~= imdsValidation.Labels(i)
colorText = 'r';
false=false+1;
if false > f0*f1
break
else
subplot(f1,f0,false);
imshow(imf);
title(char(labels(i)),'Color',colorText);
end
end
end
xlabel('ALL mismatch incidents');
saveas(falsefig,'All Mismatches.png');
movefile('All Mismatches.png','results');
start plotting sample of correct match
truefig = figure('Name','Sample of Correct Match','Visible','off','Units', 'Normalized', 'OuterPosition', [0, 0.04, 1, 0.96]);
true=0;
false=0;
for i = 1:size(imdsValidation.Files,1)
ii = randi(size(imdsValidation.Files,1));
imt = imread(imdsValidation.Files{ii});
if labels(ii) == imdsValidation.Labels(ii)
colorText = 'g';
true=true+1;
if true > f0*f1
break
else
subplot(f1,f0,true);
imshow(imt);
title(char(labels(ii)),'Color',colorText);
end
end
end
xlabel('Sample of Correct Incidents');
saveas(truefig,'Sample Matches.png');
movefile('Sample Matches.png','results');
Log in or sign up for Devpost to join the conversation.