Skip to content

An implementation of the Fast Super-Resolution Convolutional Neural Network in TensorFlow

License

GPL-3.0, MIT licenses found

Licenses found

GPL-3.0
LICENSE
MIT
LICENSE.MIT
Notifications You must be signed in to change notification settings

igv/FSRCNN-TensorFlow

Folders and files

NameName
Last commit message
Last commit date
Mar 2, 2017
Jul 23, 2017
Jul 23, 2017
Jul 23, 2017
Mar 2, 2017
Jul 23, 2017
Jul 27, 2017
Sep 10, 2017
Sep 10, 2017
Sep 10, 2017
Sep 10, 2017

Repository files navigation

FSRCNN-TensorFlow

TensorFlow implementation of the Fast Super-Resolution Convolutional Neural Network (FSRCNN). This implements two models: FSRCNN which is more accurate but slower and FSRCNN-s which is faster but less accurate. Based on this project.

Prerequisites

  • Python 3
  • TensorFlow-gpu >= 1.3
  • CUDA & cuDNN >= 6.0
  • h5py
  • Pillow

Usage

For training: python main.py
For testing: python main.py --train False

To use FSCRNN-s instead of FSCRNN: python main.py --fast True

Can specify epochs, learning rate, data directory, etc:
python main.py --epoch 100 --learning_rate 0.0002 --data_dir Train
Check main.py for all the possible flags

Also includes script expand_data.py which scales and rotates all the images in the specified training set to expand it

Result

Original butterfly image:

orig

Ewa_lanczos interpolated image:

ewa_lanczos

Super-resolved image:

fsrcnn

Additional datasets

TODO

  • Add RGB support (Increase each layer depth to 3)
  • Speed up pre-processing for large datasets

References

About

An implementation of the Fast Super-Resolution Convolutional Neural Network in TensorFlow

Resources

License

GPL-3.0, MIT licenses found

Licenses found

GPL-3.0
LICENSE
MIT
LICENSE.MIT

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Python 100.0%