Main Content

Code Generation for Semantic Segmentation Network

This example shows code generation for an image segmentation application that uses deep learning. It uses the codegen command to generate a MEX function that performs prediction on a DAG Network object for SegNet [1], a deep learning network for image segmentation.

Third-Party Prerequisites


This example generates CUDA MEX and has the following third-party requirements.

  • CUDA® enabled NVIDIA® GPU and compatible driver.


For non-MEX builds such as static, dynamic libraries or executables, this example has the following additional requirements.

Verify GPU Environment

Use the coder.checkGpuInstall (GPU Coder) function to verify that the compilers and libraries necessary for running this example are set up correctly.

envCfg = coder.gpuEnvConfig('host');
envCfg.DeepLibTarget = 'cudnn';
envCfg.DeepCodegen = 1;
envCfg.Quiet = 1;

Segmentation Network

SegNet [1] is a type of convolutional neural network (CNN) designed for semantic image segmentation. It is a deep encoder-decoder multi-class pixel-wise segmentation network trained on the CamVid [2] dataset and imported into MATLAB® for inference. The SegNet [1] is trained to segment pixels belonging to 11 classes that include Sky, Building, Pole, Road, Pavement, Tree, SignSymbol, Fence, Car, Pedestrian, and Bicyclist.

For information regarding training a semantic segmentation network in MATLAB by using the CamVid [2] dataset, see Semantic Segmentation Using Deep Learning (Computer Vision Toolbox).

The segnet_predict Entry-Point Function

The segnet_predict.m entry-point function takes an image input and performs prediction on the image by using the deep learning network saved in the SegNet.mat file. The function loads the network object from the SegNet.mat file into a persistent variable mynet and reuses the persistent variable on subsequent prediction calls.

function out = segnet_predict(in)
% Copyright 2018-2021 The MathWorks, Inc.

persistent mynet;

if isempty(mynet)
    mynet = coder.loadDeepLearningNetwork('SegNet.mat');

% pass in input
out = predict(mynet,in);

Get Pretrained SegNet DAG Network Object

net = getSegNet();

The DAG network contains 91 layers including convolution, batch normalization, pooling, unpooling, and the pixel classification output layers. Use the analyzeNetwork function to display an interactive visualization of the deep learning network architecture.


Run MEX Code Generation

To generate CUDA code for the segnet_predict.m entry-point function, create a GPU code configuration object for a MEX target and set the target language to C++. Use the coder.DeepLearningConfig (GPU Coder) function to create a CuDNN deep learning configuration object and assign it to the DeepLearningConfig property of the GPU code configuration object. Run the codegen command specifying an input size of [360,480,3]. This value corresponds to the input layer size of SegNet.

cfg = coder.gpuConfig('mex');
cfg.TargetLang = 'C++';
cfg.DeepLearningConfig = coder.DeepLearningConfig('cudnn');
codegen -config cfg segnet_predict -args {ones(360,480,3,'uint8')} -report
Code generation successful: View report

Run Generated MEX

Load and display an input image. Call segnet_predict_mex on the input image.

im = imread('gpucoder_segnet_image.png');

predict_scores = segnet_predict_mex(im);

The predict_scores variable is a three-dimensional matrix that has 11 channels corresponding to the pixel-wise prediction scores for every class. Compute the channel by using the maximum prediction score to get pixel-wise labels.

[~,argmax] = max(predict_scores,[],3);

Overlay the segmented labels on the input image and display the segmented region.

classes = [

cmap = camvidColorMap();
SegmentedImage = labeloverlay(im,argmax,'ColorMap',cmap);


[1] Badrinarayanan, Vijay, Alex Kendall, and Roberto Cipolla. "SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation." arXiv preprint arXiv:1511.00561, 2015.

[2] Brostow, Gabriel J., Julien Fauqueur, and Roberto Cipolla. "Semantic object classes in video: A high-definition ground truth database." Pattern Recognition Letters Vol 30, Issue 2, 2009, pp 88-97.

Related Topics