pytorch implementation for Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802

Last update: Jan 09, 2023

Overview

PyTorch SRResNet

Implementation of Paper: "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network"(https://arxiv.org/abs/1609.04802) in PyTorch

Usage

Training

usage: main_srresnet.py [-h] [--batchSize BATCHSIZE] [--nEpochs NEPOCHS]
                        [--lr LR] [--step STEP] [--cuda] [--resume RESUME]
                        [--start-epoch START_EPOCH] [--threads THREADS]
                        [--pretrained PRETRAINED] [--vgg_loss] [--gpus GPUS]

optional arguments:
  -h, --help            show this help message and exit
  --batchSize BATCHSIZE
                        training batch size
  --nEpochs NEPOCHS     number of epochs to train for
  --lr LR               Learning Rate. Default=1e-4
  --step STEP           Sets the learning rate to the initial LR decayed by
                        momentum every n epochs, Default: n=500
  --cuda                Use cuda?
  --resume RESUME       Path to checkpoint (default: none)
  --start-epoch START_EPOCH
                        Manual epoch number (useful on restarts)
  --threads THREADS     Number of threads for data loader to use, Default: 1
  --pretrained PRETRAINED
                        path to pretrained model (default: none)
  --vgg_loss            Use content loss?
  --gpus GPUS           gpu ids (default: 0)

An example of training usage is shown as follows:

python main_srresnet.py --cuda --vgg_loss --gpus 0

demo

usage: demo.py [-h] [--cuda] [--model MODEL] [--image IMAGE]
               [--dataset DATASET] [--scale SCALE] [--gpus GPUS]

optional arguments:
  -h, --help         show this help message and exit
  --cuda             use cuda?
  --model MODEL      model path
  --image IMAGE      image name
  --dataset DATASET  dataset name
  --scale SCALE      scale factor, Default: 4
  --gpus GPUS        gpu ids (default: 0)

We convert Set5 test set images to mat format using Matlab, for simple image reading An example of usage is shown as follows:

python demo.py --model model/model_srresnet.pth --dataset Set5 --image butterfly_GT --scale 4 --cuda

Eval

usage: eval.py [-h] [--cuda] [--model MODEL] [--dataset DATASET]
               [--scale SCALE] [--gpus GPUS]

optional arguments:
  -h, --help         show this help message and exit
  --cuda             use cuda?
  --model MODEL      model path
  --dataset DATASET  dataset name, Default: Set5
  --scale SCALE      scale factor, Default: 4
  --gpus GPUS        gpu ids (default: 0)

We convert Set5 test set images to mat format using Matlab. Since PSNR is evaluated on only Y channel, we import matlab in python, and use rgb2ycbcr function for converting rgb image to ycbcr image. You will have to setup the matlab python interface so as to import matlab library. An example of usage is shown as follows:

python eval.py --model model/model_srresnet.pth --dataset Set5 --cuda

Prepare Training dataset

Please refer Code for Data Generation for creating training files.
Data augmentations including flipping, rotation, downsizing are adopted.

Performance

We provide a pretrained model trained on 291 images with data augmentation
Instance Normalization is applied instead of Batch Normalization for better performance
So far performance in PSNR is not as good as paper, any suggestion is welcome

Dataset	SRResNet Paper	SRResNet PyTorch
Set5	32.05	31.80
Set14	28.49	28.25
BSD100	27.58	27.51

Result

From left to right are ground truth, bicubic and SRResNet

pytorch implementation for Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network arXiv:1609.04802

Related tags

Overview

PyTorch SRResNet

Usage

Training

demo

Eval

Prepare Training dataset

Performance

Result

Owner

Jiu XU

State-of-the-art data augmentation search algorithms in PyTorch

Training and Evaluation Code for Neural Volumes

Localizing Visual Sounds the Hard Way

PyTorch implementation of the paper: "Preference-Adaptive Meta-Learning for Cold-Start Recommendation", IJCAI, 2021.

This project demonstrates the use of neural networks and computer vision to create a classifier that interprets the Brazilian Sign Language.

Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation (CVPR 2020)

Code for NeurIPS 2020 article "Contrastive learning of global and local features for medical image segmentation with limited annotations"

source code of Adversarial Feedback Loop Paper

Causal Imitative Model for Autonomous Driving

[CVPR 2016] Unsupervised Feature Learning by Image Inpainting using GANs

PyTorch code for DriveGAN: Towards a Controllable High-Quality Neural Simulation

a practicable framework used in Deep Learning. So far UDL only provide DCFNet implementation for the ICCV paper (Dynamic Cross Feature Fusion for Remote Sensing Pansharpening)

Official code for "End-to-End Optimization of Scene Layout" -- including VAE, Diff Render, SPADE for colorization (CVPR 2020 Oral)

OpenL3: Open-source deep audio and image embeddings

A very lightweight monitoring system for Raspberry Pi clusters running Kubernetes.

Vrcwatch - Supply the local time to VRChat as Avatar Parameters through OSC

IsoGCN code for ICLR2021

AITom is an open-source platform for AI driven cellular electron cryo-tomography analysis.

Constructing Neural Network-Based Models for Simulating Dynamical Systems

Styled Augmented Translation