project.m

I = imread('C:\ECE 4132\dataset\asl_alphabet_test\asl_alphabet_test\A_test.jpg');
bw = im2bw(I, 0.2);
gray = rgb2gray(I);
bin = imbinarize(gray);
%imshow(bw)

imds = imageDatastore('C:\ECE 4132\dataset\asl_alphabet_train\asl_alphabet_train', 'IncludeSubfolders', true, 'LabelSource', 'foldernames');
[imdsTrain,imdsValidation] = splitEachLabel(imds,0.7,'randomized');
%augimds=augmentedImageDatastore([227 227],imds);
%[augimdsTrain,augimdsValidation] = splitEachLabel(augimds,0.7,'randomized');

% numTrainImages = numel(imdsTrain.Labels);
% idx = randperm(numTrainImages,16);
% figure
% for i = 1:16
%     subplot(4,4,i)
%     I = readimage(imdsTrain,idx(i));
%     imshow(I)
% end
% numTrainAugImages = numel(augimdsTrain.Labels);
% idx = randperm(numTrainAugImages,16);
% figure
% for i = 1:16
%     subplot(4,4,i)
%     I = readimage(augimdsTrain,idx(i));
%     imshow(I)
% end

net = alexnet;
layersTransfer = net.Layers(1:end-3);
numClasses = numel(categories(imdsTrain.Labels));
layers = [
    layersTransfer
    fullyConnectedLayer(numClasses,'WeightLearnRateFactor',20,'BiasLearnRateFactor',20)
    softmaxLayer
    classificationLayer];

augimdsValidation = augmentedImageDatastore([227 227], imdsValidation);
augimdsTrain = augmentedImageDatastore([227 227], imdsTrain);

options = trainingOptions('sgdm', ...
    'MiniBatchSize',10, ...
    'MaxEpochs',2, ...
    'InitialLearnRate',3e-4, ...
    'Shuffle','every-epoch', ...
    'Verbose',false, ...
    'Plots','training-progress');
%netTransfer = trainNetwork(augimdsTrain,layers,options);

[YPred,scores] = classify(netTransfer,augimdsValidation);

idx = randperm(numel(imdsValidation.Files),4);
figure
for i = 1:4
    subplot(2,2,i)
    I = readimage(imdsValidation,idx(i));
    imshow(I)
    label = YPred(idx(i));
    title(string(label));
end

%analyzeNetwork(net);
%hello down there