Xu Jing zhao
Xu Jing zhao
@nikkou Thanks for your help , I run it successful. :)
Mee, too . What if there exist a most powerful Optimizer , the code's endpoint must be stay with no any Augment I think .
why can't you speak in English ?
> the new avg mAP: 0.43364948014325755 , the model is trained 247 epoaches on VOC0712 But it seems still too low if your avg mAP caculated on VOC2007 .
@HannH emmmmmmm , why is just 0.3 map , did you train it enough epoch to convergence ?
Your result looks very nice , I can't waitting anymore , I want to see your code . Xiong Di.
Thanks for your help !
@CharlesShang Thanks for reply
By the way , my pytorch version is 1.1.0 , does it affects the result that should I dowdgrade it to 1.0.0?
> > When I successful sh 'make.sh', I got this import error , is there anyone who have met the same problem before? > > Can you tell me how...