How to train with many references image without running out of memory?
mfrashad opened this issue · comments
Muhammad Fathy Rashad commented
Currently, I keep getting CUDA run out of memory error if I use more than 4 reference image with 16GB GPU. Is there a way to train with more images? I'd like the model to be more general.
Min Jin Chong commented
You could write a dataloader and load the images in batch size of 4.