Preprocess Data for Deep Neural Networks

Manage and preprocess data for deep learning

Preprocessing data to ensure that it is in a format that the network can accept is a common first step in deep learning workflows. For example, you can resize image input to match the size of an image input layer. You can also preprocess data to enhance desired features or reduce artifacts that can bias the network. For example, you can normalize or remove noise from input data.

You can preprocess image input with operations such as resizing by using datastores and functions available in MATLAB^® and Deep Learning Toolbox™. Other MATLAB toolboxes offer functions, datastores, and apps for labeling, processing, and augmenting deep learning data. Use specialized tools from other MATLAB toolboxes to process data for domains such as image processing, object detection, semantic segmentation, signal processing, audio processing, and text analytics.

Apps

Image Labeler	Label images for computer vision applications
Video Labeler	Label video for computer vision applications
Ground Truth Labeler	Label ground truth data for automated driving applications
Lidar Labeler	Label ground truth data in lidar point clouds (Since R2020b)
Signal Labeler	Label signal attributes, regions, and points of interest, and extract features

Functions

`imageDatastore`	Datastore for image data
`augmentedImageDatastore`	Transform batches to augment image data
`imageDataAugmenter`	Configure image data augmentation
`augment`	Apply identical random transformations to multiple images
`minibatchqueue`	Create mini-batches for deep learning (Since R2020b)

Topics

Preprocess Deep Learning Data

Data Sets for Deep Learning
Discover data sets for various deep learning tasks.
Preprocess Images for Deep Learning
Learn how to resize images for training, prediction, and classification, and how to preprocess images using data augmentation, transformations, and specialized datastores.
Preprocess Volumes for Deep Learning
Read and preprocess volumetric image and label data for 3-D deep learning.
Preprocess Data for Domain-Specific Deep Learning Applications

Perform deterministic or randomized data processing for domains such as image processing, object detection, semantic segmentation, signal and audio processing, and text analytics.

Customize Datastores

Datastores for Deep Learning
Learn how to use datastores in deep learning applications.
Train Network Using Out-of-Memory Sequence Data
This example shows how to train a deep learning network on out-of-memory sequence data by transforming and combining datastores.
Classify Text Data Using Convolutional Neural Network
This example shows how to classify text data using a convolutional neural network.
Optimize Datastores for Deep Learning Performance
Explore methods for speeding up deep learning workflows that use datastores.
Develop Custom Mini-Batch Datastore
Create a fully customized mini-batch datastore that contains training and test data sets for network training, prediction, and classification.

Label Ground Truth Training Data

Choose an App to Label Ground Truth Data
Decide which app to use to label ground truth data: Image Labeler, Video Labeler, Ground Truth Labeler, Lidar Labeler, Signal Labeler, or Medical Image Labeler.
Get Started with Ground Truth Labelling (Automated Driving Toolbox)
Interactively label multiple lidar and video signals simultaneously.
Custom Labeling Functions (Signal Processing Toolbox)
Create and manage custom labeling functions.
Label Spoken Words in Audio Signals (Signal Processing Toolbox)
Use Signal Labeler to label spoken words in an audio signal.
Label Pixels for Semantic Segmentation (Computer Vision Toolbox)
Label pixels for training a semantic segmentation network by using a labeling app.

Featured Examples

Create and Explore Datastore for Image Classification

Create, read, and augment an image datastore for use in training a deep learning network. In particular, this example shows how to create an ImageDatastore object from a collection of images, read and extract the properties of the datastore, and create an augmentedImageDatastore for use during training.

Open Live Script

Prepare Datastore for Image-to-Image Regression

Prepare a datastore for training an image-to-image regression network using the transform and combine functions of ImageDatastore.

Open Live Script

Classify Out-of-Memory Text Data Using Deep Learning

Classify out-of-memory text data with a deep learning network using a transformed datastore.

Open Live Script

How useful was this information?

Unrated 1 star 2 stars 3 stars 4 stars 5 stars