Git Product home page Git Product logo

pksvision / deep-wavenet-underwater-image-restoration Goto Github PK

View Code? Open in Web Editor NEW
73.0 73.0 23.0 90.48 MB

Wavelength-based Attributed Deep Neural Network for Underwater Image Restoration

License: Other

Jupyter Notebook 68.30% Python 30.84% MATLAB 0.85%
deep-learning pytorch super-resolution underwater-image-enhancement underwater-image-restoration underwater-image-super-resolution underwater-images

deep-wavenet-underwater-image-restoration's People

Contributors

pksvision avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

deep-wavenet-underwater-image-restoration's Issues

About epoch

Dear sir,
I would like to ask if this 295 weight file has run 295 epochs, but the same epochs I trained myself did not have the same effect.What is the reason for this?

UIEB test set sharelink invalid

Seems like the googledrive link of the UIEB test set is invalid somehow, got a 404 error, could you please renew the google drive sharing?
checked several times it doesn't look like to be my own connecting problem.

Strange MSE results

Hi, sorry to bother.
I'm trying to implement the MSE (I followed the rmse formula in PSNR) but it always gives me high values. All the other evaluation terms give me correct results. Did you normalize any of the parameters or did you do anything else to achieve the results in Table 1?

How can i Use it for my underwater images

HI
I am a Novice and trying to use your code for underwater images of other datasets. Can you guide me how to use your model for my datasets please with reference to coding.

HI, HI, In UIEB dataset, I used your "checkpoints-netG_295.pt" to test the 90 images I selected many times, but the SSIM and PSNR were 0.91 and 25.37 respectively (0.80 and 21.57 in Table 2). So, can you share your selected test set? Or do I have a wrong understanding of the division of the data set? please!

HI, In UIEB dataset, I used your "checkpoints-netG_295.pt" to test the 90 images I selected many times, but the SSIM and PSNR were 0.91 and 25.37 respectively (0.80 and 21.57 in Table 2). So, can you share your selected test set? Or do I have a wrong understanding of the division of the data set? please!

PSNR and MSE

Hi, In tabel Ⅳ, I calculated the value of PSNR and MSE , but I found it don't meet the formula : psnr=20*math.log10(255.0/rmse),do i have a wrong understanding of that?

Out of memory

Hello!
I want to know your video memory configuration during training and why my 11G video memory is always displayed out of memory during testing?

About Number of parameters.

Dear sir,
I am going to cite your paper deep-waveNet, but I need the number of parameters and flops. I am getting around 2M parameters is it right?
Can you provide me the exact number of parameters and flops? It really helps me a lot...

Thanks & regards

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.