How do I use my trained CNN model to predict new pictures?

Question

Abdulaziz Alotaibi 2021-2-16

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/746887-how-do-i-use-my-trained-cnn-model-to-predict-new-pictures

回答： Abhishek Gupta 2021-2-19

采纳的回答： Abhishek Gupta

在 MATLAB Online 中打开

Hello there,

I created simple classification model using the following example:

https://www.mathworks.com/help/deeplearning/gs/create-simple-deep-learning-classification-network.html#CreateSimpleDeepLearningClassificationNetworkExample-4

and I got 91% accuracy, now I want to use this CNN model to try it on new images, How do I do that?

this is my code:

clear;
clc;
outputFolder = fullfile("binary_dataset");
rootFolder = fullfile(outputFolder, "Categories");
categories = {'Anomaly','No-Anomaly'}; % names of the folders
imds = imageDatastore(fullfile(rootFolder,categories),'LabelSource','foldernames');
tbl = countEachLabel(imds);
[imdsTrain,imdsValidation] = splitEachLabel(imds, 0.8, 'randomize');
inputSize = [40 24 1];
numClasses = 2;
layers = [
    imageInputLayer(inputSize)
    convolution2dLayer(5,20,'Padding',1)
    batchNormalizationLayer
    reluLayer
    maxPooling2dLayer(2,'Stride',2)
    convolution2dLayer(5,20,'Padding',1)
    batchNormalizationLayer
    reluLayer
    maxPooling2dLayer(2,'Stride',2)
    convolution2dLayer(5,20,'Padding',1)
    batchNormalizationLayer
    reluLayer
    maxPooling2dLayer(2,'Stride',2)
    fullyConnectedLayer(numClasses)
    softmaxLayer
    classificationLayer];
options = trainingOptions('sgdm', ...
    'MaxEpochs',200, ...
    'ValidationData',imdsValidation, ...
    'ValidationFrequency',30, ...
    'Verbose',false, ...
    'Plots','training-progress');
net = trainNetwork(imdsTrain,layers,options);
YPred = classify(net,imdsValidation);
YValidation = imdsValidation.Labels;
accuracy = mean(YPred == YValidation)

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Abhishek Gupta 2021-2-19

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/746887-how-do-i-use-my-trained-cnn-model-to-predict-new-pictures#answer_627474

在 MATLAB Online 中打开

Hi,

As per my understanding, you want to make predictions for new input using your trained network. You can do the same using the 'predict()' function in MATLAB: -

predictions = predict(net,newImages);

For more information, check out the documentation here: -

https://www.mathworks.com/help/deeplearning/ref/seriesnetwork.predict.html