Skip to content

sachin327/Underwater-image-enhancement

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

21 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Underwater image enhancement

Generater model : structure of generator model is taken from UWGAN

alt text

here we used skip connections and msdb layers to improve performance of our model.

MSDB LAYERS

alt text alt text alt text

Discriminator model : For discriminator model I have used the inception model cause it is very good at discriminating images even if they are almost same.

Loss function :

loss = Lgan (D, G) + λ1 * L1(G)

Lgan = Ex [log D(x)] + Ey[log(1 − D(G(y)))]

L1 is abslute distance between the original image and the generated image.

λ1 is set to 50

How to Run

Download and run GAN.ipynb file in google colab

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published