Update description of torch-conv-kan project

IvanDrokin · web-flow · commit dc18e5dc084b · 2024-05-21T10:16:04.000+03:00
diff --git a/README.md b/README.md
@@ -65,7 +65,7 @@ A curated list of awesome libraries, projects, tutorials, papers, and other reso
 ### ConvKANs
 
 - [Convolutional-KANs](https://github.com/AntonioTepsich/Convolutional-KANs) : This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN) to the Convolutional Layers, changing the classic linear transformation of the convolution to non linear activations in each pixel. ｜ ![Github stars](https://img.shields.io/github/stars/AntonioTepsich/Convolutional-KANs.svg)
-- [Conv-KAN](https://github.com/IvanDrokin/torch-conv-kan) : This repository implements Convolutional Kolmogorov-Arnold Layers with various basis functions. ｜ ![Github stars](https://img.shields.io/github/stars/IvanDrokin/torch-conv-kan.svg)
+- [Conv-KAN](https://github.com/IvanDrokin/torch-conv-kan) : This repository implements Convolutional Kolmogorov-Arnold Layers with various basis functions. The repository includes implementations of 1D, 2D, and 3D convolutions with different kernels, ResNet-like, Unet-like, and DenseNet-like models, training code based on accelerate/PyTorch, and scripts for experiments with CIFAR-10/100 and Tiny ImageNet.｜ ![Github stars](https://img.shields.io/github/stars/IvanDrokin/torch-conv-kan.svg)
 - [convkan](https://github.com/StarostinV/convkan) : Implementation of convolutional layer version of KAN (drop-in replacement of Conv2d) ｜ ![Github stars](https://img.shields.io/github/stars/StarostinV/convkan.svg)
 - [KA-Conv](https://github.com/XiangboGaoBarry/KA-Conv) : Kolmogorov-Arnold Convolutional Networks with Various Basis Functions (Optimization for Efficiency and GPU memory usage) | ![Github stars](https://img.shields.io/github/stars/XiangboGaoBarry/KA-Conv.svg)
  - [KAN-Conv2D](https://github.com/omarrayyann/KAN-Conv2D) : Drop-in Convolutional KAN built on multiple implementations ([Original pykan](https://github.com/KindXiaoming/pykan) / [efficient-kan](https://github.com/Blealtan/efficient-kan) / [FastKAN](https://github.com/ZiyaoLi/fast-kan)) to support the original paper hyperparameters. | ![Github stars](https://img.shields.io/github/stars/omarrayyann/KAN-Conv2D.svg)
