CYYJL

@duncanriach HI,i use you approch to install the causal-conv1d ,but i have a new issue `Building wheels for collected packages: causal-conv1d Building wheel for causal-conv1d (setup.py) ... error error: subprocess-exited-with-error...

> In my experience (Windows 11 with Nvidia GPU) I didn't have CUDA installed so had to install that from [here](https://developer.nvidia.com/cuda-downloads?target_os=Windows&target_arch=x86_64&target_version=11&target_type=exe_network) as well as getting Pytorch CUDA versions and this...

> You'd need this as well if you're on Windows [openai/triton#1057 (comment)](https://github.com/openai/triton/issues/1057#issuecomment-1624240321) triton, this package is seem need to be installed in Ubuntu, not windos I try to install in...

> Hey @CYYJL > > Dataset conversion into nnUNet_raw format is always very specific to the respective dataset. Take a look at these helper functions for the [conversion of different...

> Please share your folder structure (where your trainer is) and the trainer itself is possible. If your trainer is located in a separate subfolder, make sure that this folder...

Hi，Fabian，I found something interesting: when I named my file nnUNetTestUnet.py, I got an error saying the file doesn't exist. However, when I created another folder and named it nnUNetTrainerSegmamba.py, the...

> So it does work now? I am not sure what was happening before that tbh Hi，Fabian Of course, when I renamed the file uuUNetTest.py to uuUNetTrainerTest.py, the code ran...

@lxy51 Hi，Check if the training function of your used nnUNetTrainer matches the name of the Python file. If they do not match, please modify them to be consistent before proceeding...

Hi, thank you very much for your advice. I have solved this problem according to your method. Thank you very much. Best!!! CYYJL

Hi, as to why KAN[64,16,10] is used instead of a linear layer, my idea is to combine ResNet and KAN to test whether it can run in a normal environment,...