segnetLayers
(To be removed) Create SegNet layer graph for semantic segmentation
segnetLayers
will be removed in a future release. Create a SegNet
network using a dlnetwork
(Deep Learning Toolbox) object instead. For more
information, see Version History.
Syntax
Description
returns SegNet layers, lgraph
= segnetLayers(imageSize
,numClasses
,model
)lgraph
, that is preinitialized with
layers and weights from a pretrained model
.
SegNet is a convolutional neural network for semantic image segmentation. The
network uses a pixelClassificationLayer
to predict the categorical label for every
pixel in an input image.
Use segnetLayers
to create the network architecture for
SegNet. You must train the network using the Deep Learning Toolbox™ function trainNetwork
(Deep Learning Toolbox).
returns uninitialized SegNet layers configured using the specified encoder
depth.lgraph
= segnetLayers(imageSize
,numClasses
,encoderDepth
)
returns a SegNet layer with additional options specified by one or more
lgraph
= segnetLayers(imageSize
,numClasses
,encoderDepth
,Name,Value
)Name,Value
pair arguments.
Examples
Input Arguments
Output Arguments
Tips
The sections within the SegNet encoder and decoder subnetworks are made up of convolutional, batch normalization, and ReLU layers.
All convolutional layers are configured such that the bias term is fixed to zero.
Convolution layer weights in the encoder and decoder subnetworks are initialized using the '
MSRA
' weight initialization method. For'vgg16'
or'vgg19'
models, only the decoder subnetwork is initialized using MSRA.[1]Networks produced by
segnetLayers
support GPU code generation for deep learning once they are trained withtrainNetwork
(Deep Learning Toolbox). See Code Generation (Deep Learning Toolbox) for details and examples.
References
[1] He, K., X. Zhang, S. Ren, and J. Sun. "Delving Deep Into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification." Proceedings of the IEEE International Conference on Computer Vision. 2015, 1026–1034.
[2] Badrinarayanan, V., A. Kendall, and R. Cipolla. "Segnet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation." arXiv. Preprint arXiv: 1511.0051, 2015.
Extended Capabilities
Version History
Introduced in R2017bSee Also
dlnetwork
(Deep Learning Toolbox) | trainnet
(Deep Learning Toolbox) | semanticseg
| evaluateSemanticSegmentation
Topics
- Getting Started with Semantic Segmentation Using Deep Learning
- Deep Learning in MATLAB (Deep Learning Toolbox)