FoolishMao
FoolishMao
@LimBee @wuguangbin1230 @lxtGH @XuSen123 what the performance did you get?
@terasakisatoshi @lxy5513 Have you evaluated in COCO dataset?
@terasakisatoshi Thanks for your works! and I will try too.
@dragonfly90 'Average Precision (AP) @[ IoU=0.50 | area= all | maxDets= 20 ] = 0.801'。I have a tensorflow model about openpose. but when evaluation the model, I can't reproduce the...
@zhanghang1989 I think this package will have great impact.
what your train/val loss looks like?
不能同意的更多
what your loss curve looks like? My is a bit wired!! train loss is very little,and validation loss is always 0.0.