search

Baisonm-Li / HSR-KAN

The code of "HSR-KAN: Hyperspectral Image Super-Resolution based on Kolmogorov-Arnold Networks"
13 stars 1 forks source link

loss function #1

Open vq12 opened 2 months ago

vq12 commented 2 months ago

Hello, I want to commend you on the exceptional work you have done on hyperspectral image super-resolution. I observed that the paper mentions the use of sparse loss, but I couldn't locate the corresponding code implementation in the 'main.py' file. Could you kindly provide some insight into the reason behind this discrepancy?
Thank you for your attention.

Baisonm-Li commented 2 months ago

Hello, I want to commend you on the exceptional work you have done on hyperspectral image super-resolution. I observed that the paper mentions the use of sparse loss, but I couldn't locate the corresponding code implementation in the 'main.py' file. Could you kindly provide some insight into the reason behind this discrepancy? Thank you for your attention.

main.py is a general training script designed for convenient comparison with other methods. If you want to train KANFormer, please appropriately invoke regularization_loss within the KANFormer module. We will update the code structure soon to improve readability and reproducibility. Thank you for your interest in our work.