Awesome Open Source
Awesome Open Source

SRGan in Tensorflow

This is an implementation of the paper Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network using TensorFlow.

Usage

Set up

  1. Download the VGG19 weights provided by TensorFlow-Slim. Place the vgg_19.ckpt file in this directory.
  2. Download a dataset of images. I recommend ImageNet or Places205. Specify the directory containing your dataset using the --train-dir argument when training the model.

Training

SRResNet-MSE

python train.py --name srresnet-mse --content-loss mse --train-dir path/to/dataset

SRResNet-VGG22

python train.py --name srresnet-vgg22 --content-loss vgg22 --train-dir path/to/dataset

SRGAN-MSE

python train.py --name srgan-mse --use-gan --content-loss mse --train-dir path/to/dataset --load results/srresnet-mse/weights-1000000

SRGAN-VGG22

python train.py --name srgan-vgg22 --use-gan --content-loss vgg22 --train-dir path/to/dataset --load results/srresnet-mse/weights-1000000

SRGAN-VGG54

python train.py --name srgan-vgg54 --use-gan --content-loss vgg54 --train-dir path/to/dataset --load results/srresnet-mse/weights-1000000

Results

Set5 Ledig SRResNet This SRResNet Ledig SRGAN This SRGAN
PSNR 32.05 32.11 29.40 28.21
SSIM 0.9019 0.8933 0.8472 0.8200
Set14 Ledig SRResNet This SRResNet Ledig SRGAN This SRGAN
PSNR 28.49 28.61 26.02 25.74
SSIM 0.8184 0.7809 0.7397 0.6909
BSD100 Ledig SRResNet This SRResNet Ledig SRGAN This SRGAN
PSNR 27.58 27.57 25.16 24.80
SSIM 0.7620 0.7346 0.6688 0.6314
Alternatives To Tensorflow Srgan
Select To Compare


Alternative Project Comparisons
Related Awesome Lists
Top Programming Languages
Top Projects

Get A Weekly Email With Trending Projects For These Topics
No Spam. Unsubscribe easily at any time.
Python (822,298
Deep Learning (37,067
Tensorflow (22,480
Convolutional Neural Networks (12,578
Generative Adversarial Network (5,232
Adversarial (3,531
Vgg (2,472
Super Resolution (848
Srgan (173
Vgg19 (105
Srresnet (6