Instance Segmentation Using Mask R-CNN Deep Learning encountered array size mismatch error

Question

Sardar Ali 2021-6-22

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/862440-instance-segmentation-using-mask-r-cnn-deep-learning-encountered-array-size-mismatch-error

回答： Anshika Chaurasia 2021-9-14

I have followed the instructions mentioned https://uk.mathworks.com/help/deeplearning/ug/instance-segmentation-using-mask-rcnn.html. Not sure what to do with errors. Complete code attached below. Please guide

% %Create directories to store the COCO training images and annotation data.
% imageFolder = fullfile('dataFolder',"images");
% captionsFolder = fullfile('dataFolder',"annotations");
% if ~exist('imageFolder','dir')
%     mkdir('imageFolder')
%     mkdir('captionsFolder')
% end
% 
% annotationFile = fullfile(captionsFolder,"instances_train2014.json");
% str = fileread(annotationFile);
% 
% cocoAPIDir = fullfile('dataFolder',"cocoapi-master","MatlabAPI");
% addpath(cocoAPIDir);
% 
% unpackAnnotationDir = fullfile('dataFolder',"annotations_unpacked","matFiles");
% if ~exist(unpackAnnotationDir,'dir')
%     mkdir(unpackAnnotationDir)
% end
% 
  trainClassNames = {'person','car'};
%  helper.unpackAnnotations(trainClassNames,annotationFile,imageFolder,unpackAnnotationDir);
ds = fileDatastore(unpackAnnotationDir, ...
    'ReadFcn',@(x)helper.cocoAnnotationMATReader(x,imageFolder));
imageSize = [800 800 3];
dsTrain = transform(ds,@(x)helper.preprocessData(x,imageSize));
data = preview(dsTrain);
numClasses = length(trainClassNames)-1;
params = createMaskRCNNConfig(imageSize,numClasses,trainClassNames);
netFasterRCNN = fasterRCNNLayers(params.ImageSize,numClasses,params.AnchorBoxes,'resnet101');
netMaskRCNN = createMaskRCNN(netFasterRCNN,1,params);
dlnet = dlnetwork(netMaskRCNN);
%deepNetworkDesigner(netMaskRCNN)
initialLearnRate = 0.01;
momentum = 0.9;
decay = 0.0001;
velocity = [];
maxEpochs = 30;
miniBatchSize = 2;
miniBatchFcn = @(img,boxes,labels,masks) deal(cat(4,img{:}),boxes,labels,masks);
mbqTrain = minibatchqueue(dsTrain,4, ...
    "MiniBatchFormat",["SSCB","","",""], ...
    "MiniBatchSize",miniBatchSize, ...
    "OutputCast",["single","","",""], ...
    "OutputAsDlArray",[true,false,false,false], ...
    "MiniBatchFcn",miniBatchFcn, ...
    "OutputEnvironment",["auto","cpu","cpu","cpu"]);
doTraining = true;
if doTraining
    
    iteration = 1; 
    start = tic;
    
     % Create subplots for the learning rate and mini-batch loss
    fig = figure;
    [lossPlotter] = helper.configureTrainingProgressPlotter(fig);
    
    % Initialize verbose output
    helper.initializeVerboseOutput([]);
    
    % Custom training loop
    for epoch = 1:maxEpochs
        reset(mbqTrain)
        shuffle(mbqTrain)
    
        while hasdata(mbqTrain)
            % Get next batch from minibatchqueue
            [X,gtBox,gtClass,gtMask] = next(mbqTrain);
        
            % Evaluate the model gradients and loss
            [gradients,loss,state] = dlfeval(@networkGradients,X,gtBox,gtClass,gtMask,dlnet,params);
            dlnet.State = state;
            
            % Compute the learning rate for the current iteration
            learnRate = initialLearnRate/(1 + decay*iteration);
            
            if(~isempty(gradients) && ~isempty(loss))    
                [dlnet.Learnables,velocity] = sgdmupdate(dlnet.Learnables,gradients,velocity,learnRate,momentum);
            else
                continue;
            end
            
            helper.displayVerboseOutputEveryEpoch(start,learnRate,epoch,iteration,loss);
                
            % Plot loss/accuracy metric
            D = duration(0,0,toc(start),'Format','hh:mm:ss');
            addpoints(lossPlotter,iteration,double(gather(extractdata(loss))))
            subplot(2,1,2)
            title(strcat("Epoch: ",num2str(epoch),", Elapsed: "+string(D)))
            drawnow
            
            iteration = iteration + 1;    
        end
    
    end
    net = dlnet;
    
    % Save the trained network
    modelDateTime = string(datetime('now','Format',"yyyy-MM-dd-HH-mm-ss"));
    save(strcat("trainedMaskRCNN-",modelDateTime,"-Epoch-",num2str(maxEpochs),".mat"),'net');
    
end