IvanDrokin / torch-conv-kan

This project is dedicated to the implementation and research of Kolmogorov-Arnold convolutional networks. The repository includes implementations of 1D, 2D, and 3D convolutions with different kernels, ResNet-like and DenseNet-like models, training code based on accelerate/PyTorch, as well as scripts for experiments with CIFAR-10 and Tiny ImageNet.
MIT License
252 stars 14 forks source link

About Visualize experiments #5

Open Guoli-w opened 2 weeks ago

Guoli-w commented 2 weeks ago

Hello and thank you for your very meaningful work! I've been exploring how to do visualization experiments with KAN lately, do you have any good suggestions? Looking forward to hearing from you. Best regards.

IvanDrokin commented 2 weeks ago

@Guoli-w Hi there, thanks for the feedback!

Could you please elaborate on what kind of visualization you need?

Guoli-w commented 2 weeks ago

Thank you for your response. I apologize that I didn't express myself clearly. I would like to visualize this effect. image