No 3dpose visualization in demo
tiffany0117 opened this issue · 7 comments
Hi,
Thanks for your wonderful works, but when I try the code in README for quick demo, there is no skeleton of 3dpose in visualization, and I found something strange at the end of training.
-
Operating system : windows 10
-
Tensorflow version : 2.3.0
-
Python version : 3.8.8
-
The stack trace of the error that you see
=============================
Global step: 24371
Learning rate: 9.90e-04
Train loss avg: 0.1195
=============================
===Action=== ==mm==
Directions nan
Discussion nan
Eating nan
Greeting nan
Phoning nan
Photo nan
Posing nan
Purchases nan
Sitting nan
SittingDown nan
Smoking nan
Waiting nan
WalkDog nan
Walking nan
WalkTogether nan
Average nan
===================
Saving the model... done in 1979.55 ms
I have same problem.Help me,please!
@tiffany0117 were you able to solve the problem?
@shin-ka I found that this problem is caused by the result of the predicted joints are not those we want like below :
#77 (comment)
the result are the other 16 static joints.
However, I have no idea how to solve this problem.
It is likely that a library we depend on changed and it's affecting the results. I'd recommend trying with older version of pytorch. I'll try to put together a docker image for this as well.
@una-dinosauria thanks for the suggestion! I downgraded to tensorflow 1.12 and it works.
@tiffany0117 fyi
Sorry, I meant tensorflow
, not pytorch
. Thanks for finding the fix @shin-ka!
@shin-ka @una-dinosauria Thanks a lot !