Convolutional neural networks (CNNs, or ConvNets) are essential tools for deep learning, and are especially useful for image classification, object detection, and recognition tasks. CNNs are implemented as a series of interconnected layers. The layers are made up of repeated blocks of convolutional, ReLU (rectified linear units), and pooling layers. The convolutional layers convolve their input with a set of filters. The filters were automatically learned during network training. The ReLU layer adds nonlinearity to the network, which enables the network to approximate the nonlinear mapping between image pixels and the semantic content of an image. The pooling layers downsample their inputs and help consolidate local image features.
Convolutional neural networks require Neural Network Toolbox™. Training and prediction are supported on a CUDA®-capable GPU with a compute capability of 3.0 or higher. Use of a GPU is recommended and requires Parallel Computing Toolbox™.
You can construct a CNN architecture, train a network using semantic segmentation, and use the trained network to predict class labels or detect objects. You can also extract features from a pretrained network, and use these features to train a classifier. Additionally, you can perform transfer learning which retrains the CNN on new data.
|Train an R-CNN deep learning object detector|
|Train a Fast R-CNN deep learning object detector|
|Train a Faster R-CNN deep learning object detector|
|Detect objects using R-CNN deep learning detector|
|Detect objects using Fast R-CNN deep learning detector|
|Detect objects using Faster R-CNN deep learning detector|
|Semantic image segmentation using deep learning|
|Create SegNet layers for semantic segmentation|
|Create fully convolutional network layers for semantic segmentation|
|Data source for semantic segmentation networks|
|Evaluate semantic segmentation data set against ground truth|
|Semantic segmentation quality metrics|
|Datastore for pixel label data|
|Create pixel classification layer for semantic segmentation|
|Neural network layer in a neural network that can be used to crop an input feature map|
|Overlay label matrix regions on 2-D image|
Segment objects by class using deep learning
Deep Learning Basics (Neural Network Toolbox)
Discover deep learning capabilities in MATLAB using convolutional neural networks (ConvNets) for classification and regression
This example shows how to train a semantic segmentation network using deep learning.
This example shows how to use a pre-trained Convolutional Neural Network (CNN) as a feature extractor for training an image category classifier.
This example shows how to train an object detector using deep learning and R-CNN (Regions with Convolutional Neural Networks).
This example shows how to train an object detector using a deep learning technique named Faster R-CNN (Regions with Convolutional Neural Networks).
Decide which R-CNN detector training function to use.
Pretrained Convolutional Neural Networks (Neural Network Toolbox)
Learn how to download and use pretrained convolutional neural networks for classification, transfer learning and feature extraction.