Open ybu-lxd opened 4 months ago
pls show me more details
pls show me more details
When I use fastKan, the memory usage is extremely high, which occurs when the number of tokens reaches 4096. CUDA out of memory.
fkan1 = NaiveFourierKANLayer(768, 768, 300).to("cuda")
x = torch.rand(size=(4,49,768)).to("cuda")
print(fkan1(x).shape)
Yes, it's normal, that's why I can only set the hidden layer very small on my local computer, like 192, I'm sure more work will be done in the near future to lighten up the GPU memory usage, but not now!
Yes, the number of tokens will affect the performance of the network. I think kan is doing a good job, but it is now limited by engineering.
I'm trying to use kan for image generation, but the effect has been poor due to the limitation of the number of tokens.
Yes, I'm not currently getting good classification accuracy either, need to experiment more.
Hello, I found that when the number of tokens reaches a certain size, the following situation will occur.