SRGAN-MSE Matlab port

バージョン 1.0.0.1 (5.04 MB) 作成者: manoreken
SRGAN-MSE Single Image Super Resolution Matlab port. Inputs pristine image and performs 2x upsampling using a deep learning.

ダウンロード 62 件

更新 2021/6/27

ライセンスの表示

SRGAN-MSE Single Image Super Resolution Matlab port.
■ Prerequisites ■
  • Matlab 2021a
  • Image Processing toolbox
  • Statistics and Machine Learning toolbox
  • Deep Learning Toolbox
  • Parallel Computing Toolbox
■ How to Test ■
  • Run SRGAN_Test.m that calls SRGAN_2xSuperResolution.m
  • Trained net is loaded on the line 5 of SRGAN_2xSuperResolution.m
■ How to Perform SRGAN Super-Resolution to your image file ■
Input image MyPicture.jpg should be pristine (not blurred) image. SRGAN neural net will upscale the image by 2x.
img = imread("MyPicture.jpg"); % 1024x768 input image
imgSR = SRGAN_2xSuperResolution(img);
imwrite(imgSR, "MyPicture_2x_SRGAN_MSE.png"); % 2048x1536 image is outputted
■ How to Train the network using Flickr2K dataset ■
Download Flickr2K dataset and place it on Flickr2K/Flickr2K_HR for train data of 2650 images
Run CreateTrainingSetAll_Flickr2K.m to create Flickr2K_RGB_MatlabF folder that contains converted mat files.
Run SRGAN_Train_Flickr2K.m to train and create trained file.
use your trained file on SRGAN_2xSuperResolution.m
■ Difference from original SRGAN ■
1. Mean squared error regression.
2. train input size is 112x112 (not 48x48)
3. Only 2x super resolution is implemented.
4. VGG19 loss is not implemented yet. therefore it is SRGAN-MSE
■ Changelog ■
Version 20210627 1.0.0
・Initial release.
■ References ■
Ledig, C., Theis, L., Husz ́ar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken,A., Tejani, A., Totz, J., Wang, Z., et al.: Photo-realistic single image super-resolution using a generative adversarial network. In: CVPR (2017)
https://arxiv.org/pdf/1609.04802.pdf
Single Image Super-Resolution Using Deep Learning
(VDSR is implemented using Matlab Deep Learning Toolbox)
https://www.mathworks.com/help/images/single-image-super-resolution-using-deep-learning.html
Matlab PReLU layer
https://www.mathworks.com/help/deeplearning/ug/define-custom-deep-learning-layer.html

引用

manoreken (2022). SRGAN-MSE Matlab port (https://www.mathworks.com/matlabcentral/fileexchange/94885-srgan-mse-matlab-port), MATLAB Central File Exchange. 取得済み .

MATLAB リリースの互換性
作成: R2021a
R2021a と互換性あり
プラットフォームの互換性
Windows macOS Linux
タグ タグの追加

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!