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

Unified Pre-training for Self-Supervised Learning and Supervised Learning for ASR

DeepLab is a state-of-art deep learning system for semantic image segmentation built on top of Caffe.

Super Resolution for images using deep learning.

A bare-bones TensorFlow framework for Bayesian deep learning and Gaussian process approximation

An auto discord account and token generator. Automatically verifies the phone number. Works without proxy. Bypasses captcha.

An attempt at the implementation of Glom, Geoffrey Hinton's new idea that integrates neural fields, predictive coding, top-down-bottom-up, and attention (consensus between columns)

Spatial-Temporal Transformer for Dynamic Scene Graph Generation, ICCV2021

An inofficial PyTorch implementation of PREDATOR based on KPConv.

Pytorch implementation of Distributed Proximal Policy Optimization: https://arxiv.org/abs/1707.02286

Neural Network to colorize grayscale images

Lightweight stereo matching network based on MobileNetV1 and MobileNetV2

Reinforcement learning library in JAX.

TransMorph: Transformer for Medical Image Registration

Checking fibonacci - Generating the Fibonacci sequence is a classic recursive problem

Tutorial materials for Part of NSU Intro to Deep Learning with PyTorch.

Shape Matching of Real 3D Object Data to Synthetic 3D CADs (3DV project @ ETHZ)

Deep Learning Models for Causal Inference

Official PyTorch code for Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling (HCFlow, ICCV2021)

TensorFlow2 Classification Model Zoo playing with TensorFlow2 on the CIFAR-10 dataset.

A Closer Look at Structured Pruning for Neural Network Compression