Skip to content

ChristosKonstantas/Super_Resolution_Convolutional_Neural_Network

Repository files navigation

Super Resolution Convolutional Neural Network

This project is an implementation of Image Super-Resolution Using Deep Convolutional Networks .

You can study the paper provided above and srcnn_report.pdf file to understand the underlying theoretical concepts.

Prerequisites

Instructions

git clone https://github.com/ChristosKonstantas/Super_Resolution_Convolutional_Neural_Network.git

Windows

python -m venv venv
.\venv\Scripts\activate
pip install -r requirements.txt

Unix/Linux/Mac

python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt

Training

In src folder

python train.py --train_dir "\path\to\DIV2K_train_HR" --eval_dir "\path\to\DIV2K_valid_HR" --output_dir "\path\to\output_dir"

Evaluation

Execute scripts

python infer.py --model_path "..\pretrained\model.pth" --image_path "your\path\to\pngFile"

to see how good your training performed given a good image and compare it versus its bicubic interpolated counterpart.

or

python sisr.py --train_dir "\path\to\DIV2K_train_HR" --eval_dir "\path\to\DIV2K_valid_HR" --first_image "D:\Datasets\DIV2K_train_HR\DIV2K_train_HR\0001.png"

for Single Image Super Resolution (SISR).

About

This project is an implementation of a Super Resolution Convolutional Neural Network as a personal project for Machine Learning graduate course of Technical University of Crete.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages