EDSR-tensorflow2

Tensorflow 2 implementation of Learning a Deep Convolutional Network for Image Super-Resolution.
Most of the existing codes performed data augmentation using matlab, opencv, and numpy. This was replaced by tensorflow's ImageDataGenerator, and tensorflow 2's methods were used as a whole.

Usage

$ python main.py [-h] N_TRAIN_DATA N_TEST_DATA BATCH_SIZE EPOCHS 

DIV2K example

$ python main.py 800 100 16 200

Prerequisites

• Python 3.7
• Tensorflow 2
• Numpy

Directory

EDSR-tensorflow2
├── main.py              // main program
├── model.py             // srcnn model
├── data_generator.py    // data augmentation
└── utils.py             // psnr

Sample Results

• trained by DIV2K
• test image set is Set14