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

Python scripts to detect faces in Python with the BlazeFace Tensorflow Lite models

The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training

Optical machine for senses sensing using speckle and deep learning

[NeurIPS 2021] Well-tuned Simple Nets Excel on Tabular Datasets

Image Classification - A research on image classification and auto insurance claim prediction, a systematic experiments on modeling techniques and approaches

Angora is a mutation-based fuzzer. The main goal of Angora is to increase branch coverage by solving path constraints without symbolic execution.

Stereo Radiance Fields (SRF): Learning View Synthesis for Sparse Views of Novel Scenes

General Vision Benchmark, a project from OpenGVLab

Learning to Segment Instances in Videos with Spatial Propagation Network

It's A ML based Web Site build with python and Django to find the breed of the dog

How to Train a GAN? Tips and tricks to make GANs work

Simple converter for deploying Stable-Baselines3 model to TFLite and/or Coral

Single-Shot Motion Completion with Transformer

E-Ink Magic Calendar that automatically syncs to Google Calendar and runs off a battery powered Raspberry Pi Zero

PyTorch implementation for "Sharpness-aware Quantization for Deep Neural Networks".

Vehicle detection using machine learning and computer vision techniques for Udacity's Self-Driving Car Engineer Nanodegree.

A Confidence-based Iterative Solver of Depths and Surface Normals for Deep Multi-view Stereo

DC540 hacking challenge 0x00005a.

Camera-caps - Examine the camera capabilities for V4l2 cameras

Canonical Appearance Transformations