Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

A PyTorch reproduction of koncept512 code #3

Open
ZhengyuZhao opened this issue Jun 5, 2020 · 7 comments
Open

A PyTorch reproduction of koncept512 code #3

ZhengyuZhao opened this issue Jun 5, 2020 · 7 comments

Comments

@ZhengyuZhao
Copy link

ZhengyuZhao commented Jun 5, 2020

Hi! Your work is interesting.

I just reproduce your Keras code for koncept512 model using PyTorch.
The new results (SRCC: 0.912 | PLCC: 0.927) are very close to what you have got (SRCC: 0.919 | PLCC: 0.932) in koncept512_train_test_py3.ipynb.

If you want, feel free to post the following code link into your official repository :-)
https://github.com/ZhengyuZhao/koniq-PyTorch

@subpic
Copy link
Owner

subpic commented Jun 7, 2020

Thanks for sharing! :)

@zakajd
Copy link

zakajd commented Jun 25, 2020

@ZhengyuZhao Thanks! You saved my time 😄

@ZhengyuZhao
Copy link
Author

@ZhengyuZhao Thanks! You saved my time 😄

Enjoy!

@Sissuire
Copy link

have you ever done the cross-dataset comparison (trained on KoN-10k, and tested on LIVE-Challenge) ?

@subpic
Copy link
Owner

subpic commented Jan 16, 2021

Yes, please check the KonIQ-10k paper; Look for LIVE-itw (in-the-wild), which is the LIVE-Challenge database.

@hulkds
Copy link

hulkds commented Oct 31, 2022

Hey the link for inceptionresnetv2 pretrained weights is die !

@ZhengyuZhao
Copy link
Author

Hey the link for inceptionresnetv2 pretrained weights is die !

Are you using this link: https://surfdrive.surf.nl/files/index.php/s/oeGv7wEyyMwwbIO?
It seems working for me...

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

5 participants