Skip to content

scoudev/WaterSNet

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

WaterSNet

A Robust Object Segmentation Network for Under Water Scenes. Accepted by ICASSP 2022. [paper]

Usage:

The configuration file is config.yaml. You can modify this file to change Hyperparameters.

The code is in the scripts directory.

Train:

run python train.py to train the model.

Test:

run python test.py to obtain the testing results of the model as well as evaluation metrics.

Our pre-trained model: [Pre-trained Model]

Correction of a formula error in the paper:

Equation 5 should be F

where F and F represent the amplitude and phase components of the Fourier transform.

About

A Robust Object Segmentation Network for Under Water Scenes

Resources

Stars

Watchers

Forks

Packages

No packages published

Languages