Woodszp

icon indicating a website link https://woodszp.github.io/

icon company Nanjing University icon location China icon location I am focus on hierarchical uncertainty-aware, feature fusion, and clustering for few-shot learning.

Results 2 comments of Woodszp

Swin Transformer cannot cam-->grad can be implicitly created only for scalar outputs

### Issue Resolved If you are using the Swin Transformer, you may need to modify or add the following code: Please add this code at the end. ``` def forward():...

Hi, I've been using KAN+ResNet for classification, but I have some questions arising from it.

I want to use KAN conv instead of ResNet conv, how can i do it? First, `from kan_convolutional.KANConv import KAN_Convolutional_Layer` from https://github.com/AntonioTepsich/Convolutional-KANs. Second, change the ResNet conv But there is...