Get Started with Deep Network Designer

This example shows how to use Deep Network Designer to adapt a pretrained GoogLeNet network to classify a new collection of images. This process is called transfer learning and is usually much faster and easier than training a new network, because you can apply learned features to a new task using a smaller number of training images. To prepare a network for transfer learning interactively, use Deep Network Designer.

Extract Data for Training

In the workspace, unzip the data.

unzip('MerchData.zip');

Select a Pretrained Network

Open Deep Network Designer.

deepNetworkDesigner

Load a pretrained GoogLeNet network by selecting it from the Deep Network Designer start page. If you need to download the network, then click Install to open the Add-On Explorer.

Deep Network Designer displays a zoomed-out view of the whole network. Explore the network plot. To zoom in with the mouse, use Ctrl+scroll wheel.

Load Data Set

To load the data into Deep Network Designer, on the Data tab, click Import Data > Import Image Data. The Import Image Data dialog box opens.

In the Data source list, select Folder. Click Browse and select the extracted MerchData folder.

The dialog box also allows you to split the validation data from within the app. Divide the data into 70% training data and 30% validation data.

Specify augmentation operations to perform on the training images. For this example, apply a random reflection in the x-axis, a random rotation from the range [-90,90] degrees, and a random rescaling from the range [1,2].

Click Import to import the data into Deep Network Designer.

Using Deep Network Designer, you can visually inspect the distribution of the training and validation data in the Data pane. You can see that, in this example, there are five classes in the data set. You can also view random observations from each class.

Deep Network Designer resizes the images during training to match the network input size. To view the network input size, on the Designer pane, click the imageInputLayer. This network has an input size of 224-by-224.

Edit Network for Transfer Learning

To retrain a pretrained network to classify new images, replace the last learnable layer and the final classification layer with new layers adapted to the new data set. In GoogLeNet, these layers have the names 'loss3-classifier' and 'output', respectively.

In the Designer pane, drag a new fullyConnectedLayer from the Layer Library onto the canvas. Set OutputSize to the number of classes in the new data, in this example, 5.

Edit learning rates to learn faster in the new layers than in the transferred layers. Set WeightLearnRateFactor and BiasLearnRateFactor to 10. Delete the last fully connected layer and connect your new layer instead.

Replace the output layer. Scroll to the end of the Layer Library and drag a new classificationLayer onto the canvas. Delete the original output layer and connect your new layer instead.

Check Network

Check your network by clicking Analyze. The network is ready for training if Deep Learning Network Analyzer reports zero errors.

Train Network

To train the network with the default settings, on the Training tab, click Train.

If you want greater control over the training, click Training Options and choose the settings to train with. The default training options are better suited for large data sets. For small data sets, use smaller values for the mini-batch size and the validation frequency. For more information on selecting training options, see trainingOptions.

For this example, set InitialLearnRate to 0.0001ValidationFrequency to 5, and MaxEpochs to 8. As there are 55 observations, set MiniBatchSize to 11 to divide the training data evenly and ensure the whole training set is used during each epoch.

To train the network with the specified training options, click Close and then click Train.

Deep Network Designer allows you to visualize and monitor the training progress. You can then edit the training options and retrain the network, if required.

Export Results from Training

To export the results from training, on the Training tab, select Export > Export Trained Network and Results. Deep Network Designer exports the trained network as the variable trainedNetwork_1 and the training info as the variable trainInfoStruct_1.

You can also generate MATLAB code, which recreates the network and the training options used. On the Training tab, select Export > Generate Code for Training.

Test Trained Network

Select a new image to classify using the trained network.

I = imread("MerchDataTest.jpg");

Resize the test image to match the network input size.

I = imresize(I, [224 224]);

Classify the test image using the trained network.

[YPred,probs] = classify(trainedNetwork_1,I);
imshow(I)
label = YPred;
title(string(label) + ", " + num2str(100*max(probs),3) + "%");

Matlabsolutions.com provides guaranteed satisfaction with a commitment to complete the work within time. Combined with our meticulous work ethics and extensive domain experience, We are the ideal partner for all your homework/assignment needs. We pledge to provide 24*7 support to dissolve all your academic doubts. We are composed of 300+ esteemed Matlab and other experts who have been empanelled after extensive research and quality check.

Matlabsolutions.com provides undivided attention to each Matlab assignment order with a methodical approach to solution. Our network span is not restricted to US, UK and Australia rather extends to countries like Singapore, Canada and UAE. Our Matlab assignment help services include Image Processing Assignments, Electrical Engineering Assignments, Matlab homework help, Matlab Research Paper help, Matlab Simulink help. Get your work done at the best price in industry.

Machine Learning in MATLAB

Train Classification Models in Classification Learner App

Train Regression Models in Regression Learner App

Distribution Plots

Explore the Random Number Generation UI

Design of Experiments

Machine Learning Models

Logistic regression

Logistic regression create generalized linear regression model - MATLAB fitglm 2

Support Vector Machines for Binary Classification

Support Vector Machines for Binary Classification 2

Support Vector Machines for Binary Classification 3

Support Vector Machines for Binary Classification 4

Support Vector Machines for Binary Classification 5

Assess Neural Network Classifier Performance

Naive Bayes Classification

ClassificationTree class

Discriminant Analysis Classification

Ensemble classifier

ClassificationTree class 2

Train Generalized Additive Model for Binary Classification

Train Generalized Additive Model for Binary Classification 2

Classification Using Nearest Neighbors

Classification Using Nearest Neighbors 2

Classification Using Nearest Neighbors 3

Classification Using Nearest Neighbors 4

Classification Using Nearest Neighbors 5

Linear Regression

Linear Regression 2

Linear Regression 3

Linear Regression 4

Nonlinear Regression

Nonlinear Regression 2

Visualizing Multivariate Data

Generalized Linear Models

Generalized Linear Models 2

RegressionTree class

RegressionTree class 2

Neural networks

Gaussian Process Regression Models

Gaussian Process Regression Models 2

Understanding Support Vector Machine Regression

Understanding Support Vector Machine Regression 2

RegressionEnsemble



matlab assignment help


matlab assignment help