Thank you for your work and code, this is really cool!
I've been running some experiments with your code and I noticed the gradient_bias option inside the Patchifier network to bias patch selection towards regions with high gradient.
However when I enable this option the training exits with an error:
RuntimeError: CUDA error: an illegal memory access was encountered
I think this is happening because of a shape mismatch inside the patchify_forward_kernel cuda kernel coming from the gradient images, but I wanted to check if you are aware of this error?
Hi,
Thank you for your work and code, this is really cool!
I've been running some experiments with your code and I noticed the
gradient_bias
option inside the Patchifier network to bias patch selection towards regions with high gradient.However when I enable this option the training exits with an error:
I think this is happening because of a shape mismatch inside the
patchify_forward_kernel
cuda kernel coming from the gradient images, but I wanted to check if you are aware of this error?