Why does your model get a big gap with 4 GPUs and 1 GPU #3
Description
HI！ i wanna ask why i use your model with 4 GPUs can get 93.7% Rank1 and 83.3% mAP, but with 1 GPU, it reduce to 91.2% Rank1 and 81.5% mAP？ what numbers of GPU you use in your own model?
(i use 4 GPUs with DataParallel)