VITA-Group/DeblurGANv2

What batch size do you use when training?

thesby opened this issue · 1 comments

I find that the batch size in config.yaml is 1, but 1 is not good for batch normalization. So I want to know the batch size to use when training.

I find that the batch size in config.yaml is 1, but 1 is not good for batch normalization. So I want to know the batch size to use when training.

i use 8 but seems slower than 1 ,so use 1