Devin147

problem about code

15

# Increase gradient of the probability prob = F.softmax(score, axis=1) prob = prob - 0.5 prob = self.prob_scale(prob) prob = F.clip(prob, -0.5, 0.5) prob = prob + 0.5 #in __init__():...

get bad results on LV-MHP-v2 val

1

I have downloaded the pretrained model and the related bbox/mask provided by your. However, I get the bad results on LV-MHP-v2 and CIHP val dataset. @RanTaimu @liutinglt ![Screenshot from 2019-05-08...