YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone icon indicating copy to clipboard operation
YOLOv3v4-ModelCompression-MultidatasetTraining-Multibackbone copied to clipboard

Published 20 hours ago • verified publisher icon SpursLipu

train.py 437行，为什么最终的loss要乘batch_size / 64?( loss *= batch_size / 64 # scale loss)

Open TaoZhang1993 opened this issue 3 years ago • 0 comments

TaoZhang1993 avatar May 17 '22 13:05 TaoZhang1993