Main Content

Code Generation for Denoising Deep Neural Network

This example shows how to generate CUDA® MEX from MATLAB® code and denoise grayscale images by using the denoising convolutional neural network (DnCNN [1]). You can use the denoising network to estimate noise in a noisy image, and then remove it to obtain a denoised image.

Third-Party Prerequisites

Required

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

  • CUDA® enabled NVIDIA® GPU and compatible driver.

Optional

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 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;
coder.checkGpuInstall(envCfg);

Load Noisy Image

Load a noisy grayscale image into the workspace and display the image.

noisyI = imread('noisy_cameraman.png');
figure
imshow(noisyI);
title('Noisy Image');

Get Pretrained Denoising Network

Call the getDenoisingNetwork helper function to get a pretrained image denoising deep neural network.

net = getDenoisingNetwork;

The getDenoisingNetwork function returns a pretrained DnCNN [1] that you can use to detect additive white Gaussian noise (AWGN) that has unknown levels. The network is a feed-forward denoising convolutional network that implements a residual learning technique to predict a residual image. In other words, DnCNN [1] computes the difference between a noisy image and the latent clean image.

The network contains 59 layers including convolution, batch normalization, and regression output layers. To display an interactive visualization of the deep learning network architecture, use the analyzeNetwork (Deep Learning Toolbox) function.

analyzeNetwork(net);

The denoisenet_predict Function

The denoisenet_predict entry-point function takes a noisy image input and returns a denoised image by using a pretrained denoising network.

The function loads the network object returned by getDenoisingNetwork into a persistent variable mynet and reuses the persistent object on subsequent prediction calls.

type denoisenet_predict
function I = denoisenet_predict(in)
%#codegen
% Copyright 2018-2019 The MathWorks, Inc.

persistent mynet;


if isempty(mynet)   
    mynet = coder.loadDeepLearningNetwork('getDenoisingNetwork', 'DnCNN');
end

% The activations methods extracts the output from the last layer. The
% 'OutputAs' 'channels' name-value pair argument is used inorder to call
% activations on an image whose input dimensions are greater than or equal
% to the network's imageInputLayer.InputSize.

res = mynet.activations(in, 59,'OutputAs','channels');


% Once the noise is estimated, we subtract the noise from the original
% image to obtain a denoised image.

I = in - res;
  

Here, the activations method is called with the layer numeric index as 59 to extract the activations from the final layer of the network. The 'OutputAs' 'channels' name-value pair argument computes activations on images larger than the imageInputLayer.InputSize of the network.

The activations method returns an estimate of the noise in the input image by using the pretrained denoising image.

Once the noise is estimated, subtract the noise from the original image to obtain a denoised image.

Run MEX Code Generation

To generate CUDA code for the denoisenet_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 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 [256,256]. This value corresponds to the size of the noisy image that you intend to denoise.

cfg = coder.gpuConfig('mex');
cfg.TargetLang = 'C++';
cfg.DeepLearningConfig = coder.DeepLearningConfig('cudnn');
codegen -config cfg denoisenet_predict -args {ones(256,256,'single')} -report
Code generation successful: To view the report, open('codegen/mex/denoisenet_predict/html/report.mldatx').

Run Generated MEX

The DnCNN [1] is trained on input images having an input range [0,1]. Call the im2single function on noisyI to rescale the values from [0,255] to [0,1].

Call denoisenet_predict_predict on the rescaled input image.

denoisedI = denoisenet_predict_mex(im2single(noisyI));

View Denoised Image

figure
imshowpair(noisyI,denoisedI,'montage');
title('Noisy Image (left) and Denoised Image (right)');

References

[1] Zhang, K., W. Zuo, Y. Chen, D. Meng, and L. Zhang. "Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising." IEEE Transactions on Image Processing. Vol. 26, Number 7, Feb. 2017, pp. 3142-3155.

See Also

Functions

Objects

Related Topics