Open Dantju opened 4 years ago
train pose estimation from scratch, sorry get a spelling error
Thanks for raising this up. I have tried and also observed better results. The new results will be updated in the next revision.
@xingyizhou I observed a better result on PE ,but PD get a lit worse,do u have some idear to improve PD?
@xingyizhou I find use multi_pose to train PD by setting PE's loss weight as 0,the result is worse than using ctdet to train PD ,do u have any idea?
Hi, I train dla_34 and resdcn_18 on UA-DETRAC using ImageNet pretrained backbone but not loading coco-pretrained model. The AP50 is always 0 for 50+ epoch. Do you know how to solve it? Thx!
@xingyizhou I find use multi_pose to train PD by setting PE's loss weight as 0,the result is worse than using ctdet to train PD ,do u have any idea?
@xingyizhou ,have u train PE from strach but not finetune on OD? I did this ,and get a better result,i want to know,why u train PE finetuned on OD?