IvanDrokin / torch-conv-kanLinks
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 ImageN…
☆531Updated last year
Alternatives and similar repositories for torch-conv-kan
Users that are interested in torch-conv-kan are comparing it to the libraries listed below
Sorting:
- This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN) to the Convolutional Layers, changing th…☆908Updated 8 months ago
- KAN for Vision Transformer☆255Updated last year
- FastKAN: Very Fast Implementation of Kolmogorov-Arnold Networks (KAN)☆456Updated last year
- Convolutional layer for Kolmogorov-Arnold Network (KAN)☆111Updated 8 months ago
- ikan: many kan variants for every body☆292Updated 5 months ago
- This repository contains the codes to replicate the simulations from the paper: "Wav-KAN: Wavelet Kolmogorov-Arnold Networks". It showca…