show
Syntax
Description
Examples
Unzip the digit sample data and create an image datastore. The imageDatastore function automatically labels the images based on folder names.
unzip("DigitsData.zip") imds = imageDatastore("DigitsData", ... IncludeSubfolders=true, ... LabelSource="foldernames");
Define the convolutional neural network architecture. Specify the size of the images in the input layer of the network and the number of classes in the final fully connected layer. Each image is 28-by-28-by-1 pixels.
inputSize = [28 28 1];
numClasses = numel(categories(imds.Labels));
layers = [
imageInputLayer(inputSize)
convolution2dLayer(5,20)
batchNormalizationLayer
reluLayer
fullyConnectedLayer(numClasses)
softmaxLayer];Specify the training options.
Train for four epochs using the SGDM solver.
Monitor the accuracy metric.
options = trainingOptions("sgdm", ... MaxEpochs=4, ... Metrics="accuracy");
Train the neural network. For classification, use cross-entropy loss. Return the trained network and the training information.
[net,info] = trainnet(imds,layers,"crossentropy",options); Iteration Epoch TimeElapsed LearnRate TrainingLoss TrainingAccuracy
_________ _____ ___________ _________ ____________ ________________
1 1 00:00:03 0.01 2.7615 3.9062
50 1 00:00:11 0.01 0.48724 84.375
100 2 00:00:17 0.01 0.16261 96.094
150 2 00:00:24 0.01 0.10018 96.094
200 3 00:00:29 0.01 0.056833 100
250 4 00:00:34 0.01 0.031866 100
300 4 00:00:40 0.01 0.021502 100
312 4 00:00:42 0.01 0.029409 99.219
Training stopped: Max epochs completed
View the training information.
info
info =
TrainingInfo with properties:
TrainingHistory: [312×5 table]
ValidationHistory: [0×0 table]
OutputNetworkIteration: 312
StopReason: "Max epochs completed"
Display the training information in a plot using the show function.
show(info)
Close the plot using the close function.
close(info)
Input Arguments
Version History
Introduced in R2023b
