How to convert Non Image data to images for use in CNN

5 次查看（过去 30 天）

显示更早的评论

Ambali Odebowale 2022-10-16

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1828328-how-to-convert-non-image-data-to-images-for-use-in-cnn

评论： Ambali Odebowale 2022-10-17

采纳的回答： Image Analyst

I have non-image data that I would like to convert to images for use in CNN. Any help would be appreciated.

采纳的回答

Image Analyst 2022-10-16

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1828328-how-to-convert-non-image-data-to-images-for-use-in-cnn#answer_1076603

Perhaps the reshape and imresize functions would work. What form is your non-image data in? Vectors? You can just write them into an image.

7 个评论
显示 5更早的评论隐藏 5更早的评论

Image Analyst 2022-10-17

编辑：Image Analyst 2022-10-17

在 MATLAB Online 中打开

Of course you can view the images but they will be very small so you need to magnify them to see them.

imshow(thisImage, [], 'InitialMagnification', 3000);

Remember images must be rectangular. 3 is not for gray scale. So since you have 21 elements, you can either have a 3x7 or a 7x3 image. So you don'[t really have much choice. 3*7 = 21 and 7*3 = 21. No other combinations multiply to give you 21. Or you can have a different size if you want if you paste it in to the upper left corner.

Remember some predefined networks require images of a certain size so you may have to use imresize() with the 'nearest' option if you want to use a prebuilt network such as AlexNet. Or you can build your own, which might train faster since your images will be so much smaller than those used for prebuilt networks, such as 227x227 for Alexnet.

Ambali Odebowale 2022-10-17

You are a genius! Thanks

请先登录，再进行评论。

更多回答（1 个）

Walter Roberson 2022-10-16

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1828328-how-to-convert-non-image-data-to-images-for-use-in-cnn#answer_1076778

You can use an arrayDatastore after reading in the files, or perhaps a tabularTextDatastore . You probably do not need to convert to images.

3 个评论
显示 1更早的评论隐藏 1更早的评论

Ambali Odebowale 2022-10-16

编辑：Walter Roberson 2022-10-16

在 MATLAB Online 中打开

I have previously used imageDatastore after following a solution posted in another discussion. However, there is no clue on how to compare input data with the target one and how I can view the output. Do you have idea on this? Here is the code for your reference. Thanks

location = 'C:\Users\z5288520\Downloads\NonImageDataMatlab\signal.mat';
imds = imageDatastore(location, 'FileExtensions', '.mat', 'IncludeSubfolders',1, ...
    'LabelSource','foldernames');
countEachLabel(imds);
trainingDS = imds;
% Convert labels to categoricals
trainingDS.Labels = categorical(trainingDS.Labels);
trainingDS.ReadFcn = @readFcn1;
layers = [ ...
    imageInputLayer([94 21 1])
    convolution2dLayer(5,20)
    reluLayer
    maxPooling2dLayer(2,'Stride',2)
    fullyConnectedLayer(1)
    softmaxLayer
    classificationLayer];
options = trainingOptions('sgdm', ...
    'MaxEpochs',20,...
    'InitialLearnRate',1e-4, ...
    'Verbose',false, ...
    'Plots','training-progress');
trainedNet = trainNetwork(imds,layers,options);