wffgan

Wavelet-based feature fusion generative adversarial network for single image super-resolution

https://github.com/supereeeee/wffgan

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (11.2%) to scientific vocabulary
Last synced: 9 months ago · JSON representation

Repository

Wavelet-based feature fusion generative adversarial network for single image super-resolution

Basic Info
  • Host: GitHub
  • Owner: Supereeeee
  • Language: Python
  • Default Branch: master
  • Size: 608 MB
Statistics
  • Stars: 2
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 2 years ago · Last pushed almost 2 years ago
Metadata Files
Readme License Citation

README.md

Wavelet-based feature fusion generative adversarial network for single image super-resolution(WFFGAN)

Environment in our experiments

[python 3.8]

[Ubuntu 18.04]

BasicSR 1.4.2

PyTorch 1.13.0, Torchvision 0.14.0, Cuda 11.7

Installation

git clone https://github.com/Supereeeee/WFFGAN.git pip install -r requirements.txt python setup.py develop

How To Test

Refer to ./options/test for the configuration file of the model to be tested and prepare the testing data.

The pre-trained models have been palced in ./experiments/pretrained_models/ floder.

You can test the results of PSNR-oriented WFFGAN by running the follwing codes:
python basicsr/test.py -opt options/test/test_WFFGAN_PSNR_x4.yml You can test the results of perception-oriented WFFGAN by running the follwing codes:
python basicsr/test.py -opt options/test/test_WFFGAN_x4.yml All testing results will be saved in the ./results folder.

How To Train

Refer to ./options/train for the configuration file of the model to train.

Preparation of training data can refer to this page. All datasets can be downloaded at the official website.

Note that the default training dataset is based on lmdb, refer to docs in BasicSR to learn how to generate the training datasets.

We divide the training process into two stages: A PSNR-oriented generator for pre-training and a perception-oriented WFFGAN using pre-trained generator

The training command for PSNR-oriented generator is like:
python basicsr/train.py -opt options/train/train_WFFGAN_PSNR_x4.yml The training command for perception-oriented WFFGAN using pre-trained generator is like:
python basicsr/train.py -opt options/train/train_WFFGAN_x4.yml For more training commands and details, please check the docs in BasicSR

Inference

You can run ./inference/inference_WFFGAN.py for your own images.

Results

The results of PSNR-oriented WFFGAN and perception-oriented WFFGAN on benchmark datasets have been placed in ./results floder.

Acknowledgement

This code is based on BasicSR toolbox. Thanks for the awesome work.

Contact

If you have any question, please email 1051823707@qq.com.

Owner

  • Name: Quanwei
  • Login: Supereeeee
  • Kind: user

Bittersweet.

GitHub Events

Total
  • Watch event: 1
Last Year
  • Watch event: 1