Main Content

Import Data into Deep Network Designer

You can import and visualize training and validation data in Deep Network Designer. Using this app you can:

  • Import datastore objects for training. After import, Deep Network Designer displays a preview of the data. For more information, see Import Data.

  • Import training data for image classification problems from an ImageDatastore object or a folder containing subfolders of images per class. You can also select built-in options to augment the training images during training. For more information, see Image Augmentation.

  • Import validation data from a datastore object. For image classification you can also select validation data from a folder containing subfolders of images for each class, or choose to split the validation data from the training data. For more information, see Validation Data.

For more information about data sets you can use to get started with deep learning, see Data Sets for Deep Learning. For more information on constructing and using datastore objects for deep learning applications, see Datastores for Deep Learning.

Import Data

In Deep Network Designer, you can import image classification data from an image datastore or a folder containing subfolders of images from each class. You can also import and train any datastore object that works with the trainNetwork function. Select an import method based on the type of datastore you are using.

Import ImageDatastore ObjectImport Any Other Datastore Object (Not Recommended for ImageDatastore)

Select Import Data > Import Image Classification Data.

Import Image Classification Data dialog. Using this dialog, you can select the source of image classification data, specify augmentation options, and split validation data.

Select Import Data > Import Custom Data.

Import Custom Data dialog. Using this dialog, you can import training and validation data sets.

After import, Deep Network Designer provides a preview of the imported data so that you can check that the data is as expected, prior to training. For image classification data, Deep Network Designer also displays a histogram of the class labels and a random selection of images from the imported data. You can also choose to see random images belonging to a specific class.

Import Data by Task

TaskData TypeData Import MethodExample Visualization
Image classification

Folder with subfolders containing images for each class. The class labels are sourced from the subfolder names.

For an example, see Transfer Learning with Deep Network Designer.

Select Import Data > Import Image Classification Data.

You can select augmentation options and specify the validation data using the Import Image Data dialog box.

After import, Deep Network Designer displays a histogram of the class labels. You can also see random observations from each class.

Deep Network Designer with imported image data.

ImageDatastore

For example, create an image datastore containing digits data.

dataFolder = fullfile(toolboxdir('nnet'),'nndemos', ... 
'nndatasets','DigitDataset');

imds = imageDatastore(dataFolder, ...
    'IncludeSubfolders',true, ...
    'LabelSource','foldernames');
For more information, see Create Simple Image Classification Network Using Deep Network Designer.

AugmentedImageDatastore

For example, create an augmented image datastore containing digits data.

dataFolder = fullfile(toolboxdir('nnet'),'nndemos', ... 
'nndatasets','DigitDataset');

imds = imageDatastore(dataFolder, ...
    'IncludeSubfolders',true, ...
    'LabelSource','foldernames');

imageAugmenter = imageDataAugmenter( ...
    'RandRotation',[1,2]);
augimds = augmentedImageDatastore([28 28],imds, ...
'DataAugmentation',imageAugmenter);

augimds = shuffle(augimds);
For more information, see Transfer Learning Using Pretrained Network.

Select Import Data > Import Custom Data.

You can specify the validation data in the Import Datastore dialog box.

After import, Deep Network Designer shows a preview of the first five observations in the datastore.

Deep Network Designer with imported augmented image datastore.

Semantic segmentation

CombinedDatastore

For example, combine an ImageDatastore and a PixelLabelDatastore (Computer Vision Toolbox).

dataFolder  = fullfile(toolboxdir('vision'), ...
'visiondata','triangleImages');

imageDir = fullfile(dataFolder,'trainingImages');
labelDir = fullfile(dataFolder,'trainingLabels');

imds = imageDatastore(imageDir);
classNames = ["triangle","background"];
labelIDs   = [255 0];

pxds = pixelLabelDatastore(labelDir,classNames,labelIDs);
cds = combine(imds,pxds);

You can also combine an ImageDatastore and a PixelLabelDatastore in a pixelLabelImageDatastore (Computer Vision Toolbox). 

pximds = pixelLabelImageDatastore(imds,pxds);
For more information about creating and training a semantic segmentation network, see Train Simple Semantic Segmentation Network in Deep Network Designer.

Select Import Data > Import Custom Data.

You can specify the validation data in the Import Datastore dialog box.

After import, Deep Network Designer shows a preview of the first five observations in the datastore.

Deep Network Designer with imported semantic segmentation datastore.

Image-to-image regression

CombinedDatastore

For example, combine noisy input images and pristine output images to create data suitable for image-to-image regression. 

dataFolder = fullfile(toolboxdir('nnet'),'nndemos', ... 
'nndatasets','DigitDataset');

imds = imageDatastore(dataFolder, ...
    'IncludeSubfolders',true, ....
    'LabelSource','foldernames');

imds = transform(imds,@(x) rescale(x));
imdsNoise = transform(imds,@(x) {imnoise(x,'Gaussian',0.2)});

cds = combine(imdsNoise,imds);
cds = shuffle(cds);
For more information about training an image-to-image regression network, see Image-to-Image Regression in Deep Network Designer.

Select Import Data > Import Custom Data.

You can specify the validation data in the Import Datastore dialog box.

After import, Deep Network Designer shows a preview of the first five observations in the datastore.

Deep Network Designer with imported combined datastore.

Regression

CombinedDatastore

Create data suitable for training regression networks by combining array datastore objects. 

[XTrain,~,YTrain] = digitTrain4DArrayData;

ads = arrayDatastore(XTrain,'IterationDimension',4, ...
 'OutputType','cell');
adsAngles = arrayDatastore(YTrain,'OutputType','cell');

cds = combine(ads,adsAngles);

For more information about training a regression network, see Train Convolutional Neural Network for Regression.

Select Import Data > Import Custom Data.

You can specify the validation data in the Import Datastore dialog box.

After import, Deep Network Designer shows a preview of the first five observations in the datastore.

Deep Network Designer with imported combined array datastores.

Sequences and time series

CombinedDatastore

To input the sequence data from the datastore of predictors to a deep learning network, the mini-batches of the sequences must have the same length. You can use the padsequences function to pad or truncate sequences to have a specific length.

For example, pad the sequences to all be the same length as the longest sequence. 

[XTrain,YTrain] = japaneseVowelsTrainData;

XTrain = padsequences(XTrain,2);

adsXTrain = arrayDatastore(XTrain,'IterationDimension',3);
adsYTrain = arrayDatastore(YTrain);

cdsTrain = combine(adsXTrain,adsYTrain);

To reduce the amount of padding, you can use a transform datastore and a helper function. For example, pad the sequences so that all the sequences in a mini-batch have the same length as the longest sequence in the mini-batch. You must also use the same mini-batch size in the training options.

[XTrain,TTrain] = japaneseVowelsTrainData; 

miniBatchSize = 27;
adsXTrain = arrayDatastore(XTrain,'OutputType',"same",'ReadSize',miniBatchSize);
adsTTrain = arrayDatastore(TTrain,'ReadSize',miniBatchSize);

tdsXTrain = transform(adsXTrain,@padToLongest);
cdsTrain = combine(tdsXTrain,adsTTrain);

function data = padToLongest(data)
sequence = padsequences(data,2,Direction="left");
for n = 1:numel(data)
    data{n} = sequence(:,:,n);
end
end

You can also reduce the amount of padding by sorting your data from shortest to longest and reduce the impact of padding by specifying the padding direction. For more information about padding sequence data, see Sequence Padding, Truncation, and Splitting.

For information about training a network on time series data, see Train Network for Time Series Forecasting Using Deep Network Designer.

You can also import sequence data using a custom datastore object. For an example showing how to create a custom sequence datastore, see Train Network Using Custom Mini-Batch Datastore for Sequence Data.

Select Import Data > Import Custom Data.

You can specify the validation data in the Import Datastore dialog box.

After import, Deep Network Designer shows a preview of the first five observations in the datastore.

Deep Network Designer with imported custom sequence datastore.

Other extended workflows (such as numeric feature input, out-of-memory data, image processing, and audio and speech processing)

Datastore

For other extended workflows, use a suitable datastore object. For example, custom datastore, randomPatchExtractionDatastore (Image Processing Toolbox), denoisingImageDatastore (Image Processing Toolbox), or audioDatastore (Audio Toolbox). For more information, see Datastores for Deep Learning.

For example, create a denoisingImageDatastore object using Image Processing Toolbox™.

dataFolder = fullfile(toolboxdir('images'),'imdata');

imds = imageDatastore(dataFolder,'FileExtensions',{'.jpg'});

dnds = denoisingImageDatastore(imds,...
    'PatchesPerImage',512,...
    'PatchSize',50,...
    'GaussianNoiseLevel',[0.01 0.1]);

For an example showing how to train a deep learning network on audio data, see Transfer Learning with Pretrained Audio Networks in Deep Network Designer.

For table array data, you must convert your data into a suitable datastore to train using Deep Network Designer. For example, start by converting your table into arrays containing the predictors and responses. Then, convert the arrays into arrayDatastore objects. Finally, combine the predictor and response array datastores into a CombinedDatastore object. You can then use the combined datastore to train in Deep Network Designer. For more information on suitable datastores, see Datastores for Deep Learning.

Select Import Data > Import Custom Data.

You can specify the validation data in the Import Datastore dialog box.

After import, Deep Network Designer shows a preview of the first five observations in the datastore.

Deep Network Designer with imported denoising image datastore.

Image Augmentation

For image classification problems, Deep Network Designer provides simple augmentation options to apply to the training data. Open the Import Image Classification Data dialog box by selecting Import Data > Import Image Classification Data. You can select options to apply a random combination of reflection, rotation, rescaling, and translation operations to the training data.

Import Image Classification Data dialog. Using this dialog, you can select the source of image classification data, specify augmentation options, and split validation data.

You can effectively increase the amount of training data by applying randomized augmentation to your data. Augmentation also enables you to train networks to be invariant to distortions in image data. For example, you can add randomized rotations to input images so that a network is invariant to the presence of rotation in input images. Data augmentation can also help prevent the network from overfitting and memorizing the exact details of the training images. When you use data augmentation, one randomly augmented version of each image is used during each epoch of training, where an epoch is a full pass of the training algorithm over the entire training data set. Therefore, each epoch uses a slightly different data set, but the actual number of training images in each epoch does not change. For more information, see Create and Explore Datastore for Image Classification.

To perform more general and complex image preprocessing operations than those offered by Deep Network Designer, use TransformedDatastore and CombinedDatastore objects. To import CombinedDatastore and TransformedDatastore objects, select Import Data > Import Custom Data.

Import Custom Data dialog. Using this dialog, you can import training and validation data sets.

For more information on image augmentation, see Preprocess Images for Deep Learning.

Validation Data

In Deep Network Designer, you can import validation data to use during training. Validation data is data that the network does not use to update the weights and biases during training. As the network does not directly use this data, it is useful for assessing the true accuracy of the network during training. You can monitor validation metrics, such as loss and accuracy, to assess if the network is overfitting or underfitting and adjust the training options as required. For example, if the validation loss is much higher than the training loss, then the network might be overfitting.

Loss plot showing the training and validation loss versus iteration number. The validation loss is much higher than the training loss.

For more information on improving the accuracy of deep learning networks, see Deep Learning Tips and Tricks.

In Deep Network Designer, you can import validation data:

  • From a datastore in the workspace.

  • From a folder containing subfolders of images for each class (image classification data only).

  • By splitting a portion of the training data to use as validation data (image classification data only). The data is split into validation and training sets once, before training. This method is called holdout validation.

Split Validation Data from Training Data

When splitting the holdout validation data from the training data, Deep Network Designer splits a percentage of the training data from each class. For example, suppose you have a data set with two classes, cat and dog, and choose to use 30% of the training data for validation. Deep Network Designer uses the last 30% of images with the label "cat" and the last 30% with the label "dog" as the validation set.

Rather than using the last 30% of the training data as validation data, you can choose to randomly allocate the observations to the training and validation sets by selecting the Randomize check box in the Import Image Data dialog box. Randomizing the images can improve the accuracy of networks trained on data stored in a nonrandom order. For example, the digits data set consists of 10,000 synthetic grayscale images of handwritten digits. This data set has an underlying order in which images with the same handwriting style appear next to each other within each class. An example of the display follows.

Six images of a handwritten number three. The first three images share the same handwriting and the latter three images share the same handwriting.

Randomizing ensures that when you split the data, the images are shuffled so that the training and validation sets contain random images from each class. Using training and validation data that consists of a similar distribution of images can help prevent overfitting. Not randomizing the data ensures that the training and validation data split is the same each time, and can help improve the reproducibility of results. For more information, see splitEachLabel.

See Also

| | | | |

Related Topics