How to create dataset from images in matlab. I have 100 images i want to load in mat file for further model

2 views (last 30 days)
Naresh khuriwal
Naresh khuriwal on 25 Dec 2017
Commented: Fadi Alsuhimat on 14 Nov 2018
i have load my all images in mat file using DIR function. but when i use this data set and train model the following error occurs.
breast_cancer
trainingData =
76×6 table
name folder date bytes isdir datenum
____________ _______________________ ______________________ __________ _____ __________
'mdb001.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:56' 1.0486e+06 false 7.3179e+05
'mdb002.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:56' 1.0486e+06 false 7.3179e+05
'mdb003.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:56' 1.0486e+06 false 7.3179e+05
'mdb004.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:56' 1.0486e+06 false 7.3179e+05
'mdb005.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:56' 1.0486e+06 false 7.3179e+05
'mdb006.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:56' 1.0486e+06 false 7.3179e+05
'mdb007.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:56' 1.0486e+06 false 7.3179e+05
'mdb008.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:56' 1.0486e+06 false 7.3179e+05
'mdb009.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:56' 1.0486e+06 false 7.3179e+05
'mdb010.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:56' 1.0486e+06 false 7.3179e+05
'mdb011.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:56' 1.0486e+06 false 7.3179e+05
'mdb012.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:56' 1.0486e+06 false 7.3179e+05
'mdb013.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:56' 1.0486e+06 false 7.3179e+05
'mdb014.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:56' 1.0486e+06 false 7.3179e+05
'mdb015.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:56' 1.0486e+06 false 7.3179e+05
'mdb016.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:56' 1.0486e+06 false 7.3179e+05
'mdb017.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:56' 1.0486e+06 false 7.3179e+05
'mdb018.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb019.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb020.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb021.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb022.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb023.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb024.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb025.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb026.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb027.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb028.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb029.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb030.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb031.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb032.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb033.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb034.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb035.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb036.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb037.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb038.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb039.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:47:58' 1.0486e+06 false 7.3179e+05
'mdb040.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb041.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb042.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb043.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb044.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb045.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb046.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb047.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb048.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb049.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb050.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb051.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb052.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb053.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb054.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb055.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb056.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb057.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb058.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb059.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb060.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:00' 1.0486e+06 false 7.3179e+05
'mdb061.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:02' 1.0486e+06 false 7.3179e+05
'mdb062.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:02' 1.0486e+06 false 7.3179e+05
'mdb063.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:06' 1.0486e+06 false 7.3179e+05
'mdb064.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:06' 1.0486e+06 false 7.3179e+05
'mdb065.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:06' 1.0486e+06 false 7.3179e+05
'mdb066.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:06' 1.0486e+06 false 7.3179e+05
'mdb067.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:06' 1.0486e+06 false 7.3179e+05
'mdb068.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:06' 1.0486e+06 false 7.3179e+05
'mdb069.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:06' 1.0486e+06 false 7.3179e+05
'mdb070.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:06' 1.0486e+06 false 7.3179e+05
'mdb071.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:06' 1.0486e+06 false 7.3179e+05
'mdb072.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:06' 1.0486e+06 false 7.3179e+05
'mdb073.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:06' 1.0486e+06 false 7.3179e+05
'mdb074.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:06' 1.0486e+06 false 7.3179e+05
'mdb075.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:06' 1.0486e+06 false 7.3179e+05
'mdb076.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:08' 1.0486e+06 false 7.3179e+05
testData =
19×6 table
name folder date bytes isdir datenum
____________ _______________________ ______________________ __________ _____ __________
'mdb077.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:08' 1.0486e+06 false 7.3179e+05
'mdb078.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:08' 1.0486e+06 false 7.3179e+05
'mdb079.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:08' 1.0486e+06 false 7.3179e+05
'mdb080.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:08' 1.0486e+06 false 7.3179e+05
'mdb081.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:08' 1.0486e+06 false 7.3179e+05
'mdb082.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:08' 1.0486e+06 false 7.3179e+05
'mdb083.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:08' 1.0486e+06 false 7.3179e+05
'mdb084.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:08' 1.0486e+06 false 7.3179e+05
'mdb085.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:08' 1.0486e+06 false 7.3179e+05
'mdb086.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:08' 1.0486e+06 false 7.3179e+05
'mdb087.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:08' 1.0486e+06 false 7.3179e+05
'mdb088.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:08' 1.0486e+06 false 7.3179e+05
'mdb089.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:08' 1.0486e+06 false 7.3179e+05
'mdb090.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:08' 1.0486e+06 false 7.3179e+05
'mdb091.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:08' 1.0486e+06 false 7.3179e+05
'mdb092.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:08' 1.0486e+06 false 7.3179e+05
'mdb093.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:08' 1.0486e+06 false 7.3179e+05
'mdb094.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:08' 1.0486e+06 false 7.3179e+05
'mdb095.pgm' 'E:\Warehouse\all-mias' '30-Jul-2003 14:48:10' 7.9667e+05 false 7.3179e+05
layers =
11x1 Layer array with layers:
1 '' Image Input 1024x1024x1 images with 'zerocenter' normalization
2 '' Convolution 32 3x3 convolutions with stride [1 1] and padding [1 1]
3 '' ReLU ReLU
4 '' Convolution 32 3x3 convolutions with stride [1 1] and padding [1 1]
5 '' ReLU ReLU
6 '' Max Pooling 3x3 max pooling with stride [2 2] and padding [0 0]
7 '' Fully Connected 6 fully connected layer
8 '' ReLU ReLU
9 '' Fully Connected 6 fully connected layer
10 '' Softmax softmax
11 '' Classification Output crossentropyex
Error using vision.internal.cnn.parseInputsFasterRCNN>iAllGroundTruthBoxes (line 306)
Cannot concatenate the table variables 'bytes' and 'folder', because their types are double and cell.
Error in vision.internal.cnn.parseInputsFasterRCNN (line 172) allBoxes = iAllGroundTruthBoxes(trainingData);
Error in trainFasterRCNNObjectDetector (line 239) vision.internal.cnn.parseInputsFasterRCNN(...
Error in breast_cancer (line 80) detector = trainFasterRCNNObjectDetector(trainingData, layers, options)
these are the my code
%% Train Faster R-CNN Vehicle Detector
%% % Load training data. load('BCI.mat');
nrows = size(vehicleDataset,1); r80 = round(0.80 * nrows); trainingData = vehicleDataset(1:r80,:,:); testData = vehicleDataset(r80+1:end,:,:);
%[trainingData,testData] = splitEachLabel(vehicleDataset,0.3,'randomize');
trainingData = struct2table(trainingData) testData = struct2table(testData)
objectClasses = size(trainingData,1);
numClassesPlusBackground = objectClasses + 1;
%% % Configure training options.
% Create image input layer. inputLayer = imageInputLayer([1024 1024]);
% Define the convolutional layer parameters. filterSize = [3 3]; numFilters = 32;
% Create the middle layers. middleLayers = [
convolution2dLayer(filterSize, numFilters, 'Padding', 1)
reluLayer()
convolution2dLayer(filterSize, numFilters, 'Padding', 1)
reluLayer()
maxPooling2dLayer(3, 'Stride',2)
];
finalLayers = [
% Add a fully connected layer with 64 output neurons. The output size
% of this layer will be an array with a length of 64.
fullyConnectedLayer(6)
% Add a ReLU non-linearity.
reluLayer()
% Add the last fully connected layer. At this point, the network must
% produce outputs that can be used to measure whether the input image
% belongs to one of the object classes or background. This measurement
% is made using the subsequent loss layers.
fullyConnectedLayer(6)
% Add the softmax loss layer and classification layer.
softmaxLayer()
classificationLayer()
];
layers = [ inputLayer middleLayers finalLayers ]
options = trainingOptions('sgdm', ... 'MiniBatchSize', 32, ... 'InitialLearnRate', 1e-6, ... 'MaxEpochs', 10);
%% % Train detector. Training will take a few minutes. detector = trainFasterRCNNObjectDetector(trainingData, layers, options)
%% % Test the Fast R-CNN detector on a test image. img = imread('E:\Warehouse\all-mias/mdb001.pgm');
%% % Run detector. [bbox, score, label] = detect(detector, img);
%% % Display detection results. detectedImg = insertShape(img, 'Rectangle', bbox); figure imshow(detectedImg)

Sign in to answer this question.

Answers (0)

Categories

Find more on Deep Learning Toolbox in Help Center and File Exchange

Tags

Products

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!