SimoSbara
SimoSbara
The problem is about characters with accents from SAMP to Discord, they are using different character encoding...
I also tried a simple implementation of LeNet but with KAN as classifier: https://github.com/SimoSbara/kan-lenet KAN receives flatten data from convolution.
> I think a combination of them(nn.Linear,KAN) works fine for the MNIST task: > ``` > import torchvision > import torch > from torchvision import transforms > import torch.nn as...
It's solved, check #98.
I'll give you some news: `RuntimeError: expected scalar type Double but found Float` was my fault because the normalized images were saved in `dtype=float64` About the device choice for training,...
> Could you please take the time to review #98? Because it does exactly what you mentioned and more. Probably you could have saved some migraine! Wooops, sorry XD. Yes,...
> I am trying to run the given example of KAN in colab with @AlessandroFlati AlessandroFlati:develop implementation: > > Still getting the above error. I used the following requirements: matplotlib==3.6.2...
> Thanks, now I am able to run on colab GPU. But the CPU problem persists. This pull request solves it, you can try to modify pykan like in those...
This problem is referenced in those two issues #75 #98.
After some debugging of the vehicle death event I observed that: If a vehicle's health were set at **value