为深度神经网络预处理数据
管理和预处理深度学习数据
预处理数据以确保它采用网络可接受的格式是深度学习工作流中常见的第一步。例如,您可以调整图像输入的大小以匹配图像输入层的大小。您还可以对数据进行预处理,以增强所需的特征或减少可能导致网络偏差的伪影。例如,您可以对输入数据进行归一化或去噪。
您可以使用 MATLAB® 和 Deep Learning Toolbox™ 中提供的数据存储和函数通过调整大小等操作来预处理图像输入。其他 MATLAB 工具箱提供了用于标注、处理和增强深度学习数据的函数、数据存储和 App。您可以使用其他 MATLAB 工具箱中的专用工具,针对图像处理、目标检测、语义分割、信号处理、音频处理和文本分析等领域处理数据。
App
图像标注器 | Label images for computer vision applications |
视频标注器 | Label video for computer vision applications |
真实值标注器 | Label ground truth data for automated driving applications |
激光雷达标注器 | Label ground truth data in lidar point clouds (自 R2020b 起) |
信号标注器 | Label signal attributes, regions, and points of interest, and extract features |
函数
imageDatastore | 图像数据的数据存储 |
augmentedImageDatastore | 变换批量以增强图像数据 |
imageDataAugmenter | Configure image data augmentation |
augment | Apply identical random transformations to multiple images |
minibatchqueue | Create mini-batches for deep learning (自 R2020b 起) |
主题
预处理深度学习数据
- Data Sets for Deep Learning
Discover data sets for various deep learning tasks. - 预处理图像以进行深度学习
了解如何调整图像大小以进行训练、预测和分类,以及如何使用数据增强、变换和专用数据存储对图像进行预处理。 - 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.
自定义数据存储
- Datastores for Deep Learning
Learn how to use datastores in deep learning applications. - 使用无法放入内存的序列数据训练网络
此示例说明如何通过变换和合并数据存储基于无法放入内存的序列数据来训练深度学习网络。 - 使用卷积神经网络对文本数据进行分类
此示例说明如何使用卷积神经网络对文本数据进行分类。 - 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.
标注真实值训练数据
- 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.