Open XiShuFan opened 9 months ago
Hello! I have a question for your inspiring work. Did you set batch size to 1 when training? Cause I find that you use BatchNorm in your network
Yes I set batch size 1 which would be the same as layer normalization... Due to my limited gpu vram, i wanna set more batch size but i couldn`t do that..
Hello! I have a question for your inspiring work. Did you set batch size to 1 when training? Cause I find that you use BatchNorm in your network