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.
This fork
Nothing special about it. Just my playground to experiment with FSRCNNX's distortion capabilities. See DISTORT.md for more infos.
Prerequisites
- Python 3
- TensorFlow-gpu >= 1.8
- CUDA & cuDNN >= 6.0
- Pillow
- ImageMagick (optional)
- Wand (optional)
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
Result
Original butterfly image:
Ewa_lanczos interpolated image:
Super-resolved image:
Additional datasets
TODO
- Add RGB support (Increase each layer depth to 3)