Junran Peng

Thank you for your response, I will try with your advice. : )

I tried to train the panet on res50-fpn without using any gn to get a precise evaluation on the influence of PA-structure and get the 37.1 bbox mAP. I find...

Thanks for your reply. I will try to train a model with BN-backbone and gn-FPN/heads without using PA-structure to compare with the PA-net to give a better evaluation on this...

@Panxj I find that baseline of this implementation is higher than baseline of Detectron.pytorch by Roy. For example, res50-FPN without GN in this implementation has a 38.3box AP while it...

@KaiChen1998 I have met the same cases. Have you ever resolved it?