Implementation of paper: "Image Super-Resolution Using Dense Skip Connections" in PyTorch

Last update: Nov 26, 2022

Overview

SRDenseNet-pytorch

Implementation of paper: "Image Super-Resolution Using Dense Skip Connections" in PyTorch (http://openaccess.thecvf.com/content_ICCV_2017/papers/Tong_Image_Super-Resolution_Using_ICCV_2017_paper.pdf)

Usage

Training

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

Pytorch SRDenseNet train

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
                        10 every n epochs, Default: n=30
  --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)

Test

usage: test.py [-h] [--cuda] [--model MODEL] [--imageset IMAGESET] [--scale SCALE]

Pytorch SRDenseNet Test

optional arguments:
  -h, --help     show this help message and exit
  --cuda         use cuda?
  --model MODEL  model path
  --imageset IMAGESET  imageset name
  --scale SCALE  scale factor, Default: 4

Prepare Training dataset

The training data is generated with Matlab Bicubic Interplotation, please refer Code for Data Generation for creating training files.

Prepare Test dataset

The test imageset is generated with Matlab Bicubic Interplotation, please refer Code for test for creating test imageset.

Performance

We provide a pretrained .SRDenseNet x4 model trained on DIV2K images from [DIV2K_train_HR] (http://data.vision.ee.ethz.ch/cvl/DIV2K/DIV2K_train_HR.zip).While I use the SR_DenseNet to train this model, so the performance is test based on this code.

Non-overlapping sub-images with a size of 96 × 96 were cropped in the HR space. Other settings is the same as the original paper

Performance in PSNR on Set5, Set14, and BSD100

DataSet/Method	Paper	PyTorch
Set5	32.02/0.893	31.57/0.883
Set14	28.50/0.778	28.11/0.771
BSD100	27.53/0.733	27.32/0.729

Implementation of paper: "Image Super-Resolution Using Dense Skip Connections" in PyTorch

Related tags

Overview

SRDenseNet-pytorch

Usage

Training

Test

Prepare Training dataset

Prepare Test dataset

Performance

Owner

wxy

Styled text-to-drawing synthesis method. Featured at the 2021 NeurIPS Workshop on Machine Learning for Creativity and Design

PyTorch implementation of "Simple and Deep Graph Convolutional Networks"

Nerf pl - NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning

A collection of IPython notebooks covering various topics.

Malmo Collaborative AI Challenge - Team Pig Catcher

Material del curso IIC2233 Programación Avanzada 📚

It is a simple library to speed up CLIP inference up to 3x (K80 GPU)

Training and Evaluation Code for Neural Volumes

JAX code for the paper "Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation"

MAVE: : A Product Dataset for Multi-source Attribute Value Extraction

QI-Q RoboMaster2022 CV Algorithm

audioLIME: Listenable Explanations Using Source Separation

Implementation of popular bandit algorithms in batch environments.

This is a template for the Non-autoregressive Deep Learning-Based TTS model (in PyTorch).

This is a custom made virus code in python, using tkinter module.

Train neural network for semantic segmentation (deep lab V3) with pytorch in less then 50 lines of code

DropNAS: Grouped Operation Dropout for Differentiable Architecture Search

[CVPR 21] Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2021.

Create images and texts with the First Order Generative Adversarial Networks

TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.

Implementation of paper: "Image Super-Resolution Using Dense Skip Connections" in PyTorch

Related tags

Overview

SRDenseNet-pytorch

Usage

Training

Test

Prepare Training dataset

Prepare Test dataset

Performance

Owner

wxy

Styled text-to-drawing synthesis method. Featured at the 2021 NeurIPS Workshop on Machine Learning for Creativity and Design

PyTorch implementation of "Simple and Deep Graph Convolutional Networks"

Nerf pl - NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning

A collection of IPython notebooks covering various topics.

Malmo Collaborative AI Challenge - Team Pig Catcher

Material del curso IIC2233 Programación Avanzada 📚

It is a simple library to speed up CLIP inference up to 3x (K80 GPU)

Training and Evaluation Code for Neural Volumes

JAX code for the paper "Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation"

MAVE: : A Product Dataset for Multi-source Attribute Value Extraction

QI-Q RoboMaster2022 CV Algorithm

audioLIME: Listenable Explanations Using Source Separation

Implementation of popular bandit algorithms in batch environments.

This is a template for the Non-autoregressive Deep Learning-Based TTS model (in PyTorch).

This is a custom made virus code in python, using tkinter module.

Train neural network for semantic segmentation (deep lab V3) with pytorch in less then 50 lines of code

DropNAS: Grouped Operation Dropout for Differentiable Architecture Search

[CVPR 21] Vectorization and Rasterization: Self-Supervised Learning for Sketch and Handwriting, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2021.

Create images and texts with the First Order Generative Adversarial Networks

​TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.

TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.