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