DATM
DATM copied to clipboard
cpu memory requirement for ZCA
Hi, appreciate your work. I got a problem when I try to apply your method to larger dataset of 90,000 images with 224*224 size. It seems that during buffer, the loading of images will automatically be killed at round 1800/90000 at "Train ZCA". Is there any way to solve such problem?
Sorry for the late response. Unfortunately, we didn't solve that. BTW, according to my experiments, ZCA might not be that useful in high-resolution cases. You might even see a performance improvement when performing the distillation on Tiny ImageNet without using ZCA