search

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
267 stars 16 forks source link

Symbolic visualization #2

Open NQTri00 opened 1 month ago

NQTri00 commented 1 month ago

Hello, so i found this repo really fascinating but can i extract params from each layer and somehow visualize it like in the kan paper or do you plan working on this later?

IvanDrokin commented 1 month ago

Hi there, @NQTri00 ! Thanks for your feedback. It seems a nice and helpful feature, I'll add this in the next few days, thanks for your suggestion

Guoli-w commented 3 weeks ago

Looking forward to your open-source visualization code！