IvanDrokin/torch-conv-kan Issues
About loading checkpoint weights
Closed 2About Visualize experiments
Updated 2a small problem
Closed 1Pruning and interpretability
Updated 1Symbolic visualization
Updated 2
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.