Matlab function trainNetwork doesn't generate training progress plot

I'm trying to see the training progress plot of my CNN, but when I run my script it just ends without producing any output (no figure, no output text). What am I doing wrong?

My code is below, the section labeled %% TRAIN THE NEURAL NETWORK is where I think the issue is.

function segmentation_neural_network()

%% FETCH AND PARSE DATASET

% Set datapath
datapath = 'D:\20190618-f1\images_extracted_from_zebrafish_movies\20190618-f1_10-27-56\cropped_and_rotated';
training_datapath = strcat(datapath,'\training_dataset');
testing_datapath = strcat(datapath,'\testing_dataset');

% Get training and testing datasets
training_dataset = imageDatastore(strcat(training_datapath,'\images_rgb'));
testing_dataset = imageDatastore(strcat(testing_datapath,'\images_rgb'));

% Get pixel map labels
load(strcat(training_datapath,'\pixel_maps\eye_segmentation_labels.mat'));
labels = pixelLabelDatastore(gTruth);

% Weight segmentation class importance by the number of pixels in each class
pixel_count = countEachLabel(labels); % count number of each type of pixel
frequency = pixel_count.PixelCount ./ pixel_count.ImagePixelCount; % calculate pixel type frequencies
class_weights = mean(frequency) ./ frequency; % create class weights that balance the loss function so that more common pixel types won't be preferred

%% CREATE THE NEURAL NETWORK

% Specify the input image size.
imageSize = [64 64 3];

% Specify the number of classes.
numClasses = 2; % eye, not eye

% Create DeepLab v3+.
lgraph = helperDeeplabv3PlusResnet18(imageSize, numClasses);

% Replace the network's classification layer with a pixel classification
% layer that uses class weights to balance the loss function
pxLayer = pixelClassificationLayer('Name','labels','Classes',pixel_count.Name,'ClassWeights',class_weights);
lgraph = replaceLayer(lgraph,"classification",pxLayer);

%% TRAIN THE NEURAL NETWORK

% Training hyper-parameters: edit these settings to fine-tune the network
options = trainingOptions('sgdm', 'LearnRateSchedule','piecewise', 'LearnRateDropPeriod',10, 'LearnRateDropFactor',0.3, 'Momentum',0.9, 'InitialLearnRate',1e-3, 'L2Regularization',0.005, 'MaxEpochs',30, 'MiniBatchSize',1, 'Shuffle','every-epoch', 'CheckpointPath','D:\20190618-f1\nn_checkpoints', 'Verbose',true, 'VerboseFrequency',2, 'Plots','training-progress')

% Set up data augmentation to enhance training dataset
augmenter = imageDataAugmenter('RandXReflection',true, 'RandXTranslation',[-10 10],'RandYTranslation',[-10 10]);
% Combine augmented data with training data
augmented_training_dataset = pixelLabelImageDatastore(training_dataset(1:50), labels(1:50), 'DataAugmentation',augmenter);

% Train the network 
[eye_segmentation_nn, info] = trainNetwork(augmented_training_dataset,lgraph,options);

end

Answer 1

[Hiro Yoshino]

How about running this script outside of the function? see what will happen?