DDPAE-video-prediction icon indicating copy to clipboard operation
DDPAE-video-prediction copied to clipboard

Published 20 hours ago • verified publisher icon jthsieh

possibly a bug?

Open WendyShang opened this issue 4 years ago • 5 comments

in pose_rnn.py, L80:

#h = torch.cat([hidden[0][0:1], hidden[0][1:]], dim=2)
#c = torch.cat([hidden[1][0:1], hidden[1][1:]], dim=2)
# these 2 lines throw a dim error, is it supposed to be:  
h = hidden[0] 
c = hidden[1]

WendyShang avatar Oct 08 '19 19:10 WendyShang

I met the same problem. Did you solved the bug?

dreamingshao avatar Oct 14 '19 13:10 dreamingshao

yes, as i have already posted, use h = hidden[0], c = hidden[1]

WendyShang avatar Oct 14 '19 17:10 WendyShang

thanks!

dreamingshao avatar Oct 15 '19 03:10 dreamingshao

Thanks a lot. Just tried the code and wondering if this is a bug.

NanboLi avatar Oct 30 '19 07:10 NanboLi

Thanks, same problem. Have you got reasonable results after changing the code?

zyong812 avatar Jan 09 '20 14:01 zyong812