Awesome
Shallow-UWnet
Implementation of the paper Shallow-UWnet : Compressed Model for Underwater Image Enhancement
Introduction
In this project we have proposed a shallow neural network architecture, Shallow-UWnet which maintains performance and has fewer parameters than the state-of-art underwater image enhancement model. We have demonstrated the generalization of our model by benchmarking its performance on combination of synthetic and real-world datasets.
Train the Model
python training.py
Test the Model
python test.py
Pretrained Model
The pretrained Shallow-UWnet model is available at model.ckpt