I am getting error in function imds=image​Datastore(​fullfile(r​ootFolder, categories), 'LabelSource', 'foldernames'); why?

2 次查看（过去 30 天）
yogita
yogita 2016-6-1
回答： Arthur 2018-4-6
i am getting an error for above code in matlab 2016a
  9 个评论
显示 7更早的评论
yogita
yogita 2016-6-1
编辑：Walter Roberson 2016-6-1
url = 'http://www.vision.caltech.edu/Image_Datasets/Caltech101/101_ObjectCategories.tar.gz';
% Store the output in a temporary folder
outputFolder = fullfile(tempdir, 'caltech101'); % define output folder
rootFolder = fullfile(outputFolder, '101_ObjectCategories');
categories = {'airplanes', 'ferry', 'laptop'};
imds = imageDatastore(fullfile(rootFolder, categories), 'LabelSource', 'foldernames');
tbl = countEachLabel(imds);
minSetCount = min(tbl{:,2}); % determine the smallest amount of images in a category
% Use splitEachLabel method to trim the set.
imds = splitEachLabel(imds, minSetCount, 'randomize');
% Notice that each set now has exactly the same number of images.
countEachLabel(imds);
% Find the first instance of an image for each category
airplanes = find(imds.Labels == 'airplanes', 1);
ferry = find(imds.Labels == 'ferry', 1);
laptop = find(imds.Labels == 'laptop', 1);
figure
subplot(1,3,1);
imshow(imds.Files{airplanes})
subplot(1,3,2);
imshow(imds.Files{ferry})
subplot(1,3,3);
imshow(imds.Files{laptop})
%Store CNN model in a temporary folder
cnnMatFile = fullfile(tempdir, 'imagenet-caffe-alex.mat');
% Load MatConvNet network into a SeriesNetwork
convnet = helperImportMatConvNet(cnnMatFile);
% Inspect the last layer
convnet.Layers(end)
% Number of class names for ImageNet classification task
numel(convnet.Layers(end).ClassNames);
% Set the ImageDatastore ReadFcn
imds.ReadFcn = @(filename)readAndPreprocessImage(filename);
Iout = readAndPreprocessImage(filename);
I = imread(filename);
% Some images may be grayscale. Replicate the image 3 times to
% create an RGB image.
if ismatrix(I)
I = cat(3,I,I,I);
end
% Resize the image as required for the CNN.
Iout = imresize(I, [227 227]);
% Note that the aspect ratio is not preserved. In Caltech 101, the
% object of interest is centered in the image and occupies a
% majority of the image scene. Therefore, preserving the aspect
% ratio is not critical. However, for other data sets, it may prove
% beneficial to preserve the aspect ratio of the original image
% when resizing.
[trainingSet, testSet] = splitEachLabel(imds, 0.3, 'randomize');
% Get the network weights for the second convolutional layer
w1 = convnet.Layers(2).Weights;
% Scale and resize the weights for visualization
w1 = mat2gray(w1);
w1 = imresize(w1,5);
% Display a montage of network weights. There are 96 individual sets of
% weights in the first layer.
figure
montage(w1)
title('First convolutional layer weights')
featureLayer = 'fc7';
trainingFeatures = activations(convnet, trainingSet, featureLayer, ...
'Learners', 'Linear', 'Coding', 'onevsall', 'ObservationsIn', 'columns');
% Get training labels from the trainingSet
trainingLabels = trainingSet.Labels;
% Train multiclass SVM classifier using a fast linear solver, and set
% 'ObservationsIn' to 'columns' to match the arrangement used for training
% features.
classifier = fitcecoc(trainingFeatures, trainingLabels, ...
'Learners', 'Linear', 'Coding', 'onevsall', 'ObservationsIn', 'columns');
% Extract test features using the CNN
testFeatures = activations(convnet, testSet, featureLayer, 'MiniBatchSize',32);
% Pass CNN image features to trained classifier
predictedLabels = predict(classifier, testFeatures);
% Get the known labels
testLabels = testSet.Labels;
% Tabulate the results using a confusion matrix.
confMat = confusionmat(testLabels, predictedLabels);
% Convert confusion matrix into percentage form
confMat = bsxfun(@rdivide,confMat,sum(confMat,2));
% Display the mean accuracy
mean(diag(confMat))
newImage = fullfile(rootFolder, 'airplanes', 'image_0690.jpg');
% Pre-process the images as required for the CNN
img = readAndPreprocessImage(newImage);
% Extract image features using the CNN
imageFeatures = activations(convnet, img, featureLayer);
% Make a prediction using the classifier
label = predict(classifier, imageFeatures);

请先登录，再进行评论。

请先登录，再回答此问题。

回答（2 个）

Walter Roberson
Walter Roberson 2016-6-1
You removed some of the code that is needed to download data. Go back to http://www.mathworks.com/examples/matlab-computer-vision/mw/vision_product-DeepLearningImageClassificationExample-image-category-classification-using-deep-learning and pull out the entire code.
In particular you need the lines
if ~exist(outputFolder, 'dir') % download only once
disp('Downloading 126MB Caltech101 data set...');
untar(url, outputFolder);
end
and
% Location of pre-trained "AlexNet"
cnnURL = 'http://www.vlfeat.org/matconvnet/models/beta16/imagenet-caffe-alex.mat';
and
if ~exist(cnnMatFile, 'file') % download only once
disp('Downloading pre-trained CNN model...');
websave(cnnMatFile, cnnURL);
end
Arthur
Arthur 2018-4-6
Consider to adapt your code to:
path = char(path) %pass to this variable your complet data set path
categories = {'airplanes', 'ferry', 'laptop'};
imds = imageDatastore(fullfile(path, categories), 'LabelSource', 'foldernames');
tbl = countEachLabel(imds);

类别

在 Help Center 和 File Exchange 中查找有关 Image Data Workflows 的更多信息

标签

Community Treasure Hunt

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

Start Hunting!

Translated by