Abhijat
Abhijat
Alright, so I was able to get the train script to run with theano 0.7 (nothing newer works). (Worth adding in the README, maybe? I'm trying to add more instructions...
Okay, thanks! :) Meanwhile, I ran the testing code for just the MAML training output. [This assertion](https://github.com/cbfinn/maml_rl/blob/master/maml_examples/test_maml_point.py#L102) always returns false. The last column of the csv is, in fact "AveragePolicyStd"...
@cbfinn Hi, sorry did you have any time to look at the bug?
Hi, just asking again if you had any time to look at this @cbfinn !
Yeah, just found your comments on the other issues. Will leave this open if someone decides to fix everything for some reason.
Try it without the `-j8` flag and see if you still get the error.
Try it without the `-j8` flag and see if you still get the error.
@danyhaddad The problem is that libnative_camera_r5.0.0.so doesn't exist in openCV (or it didn't when I made this project). You can try to see if one exists with the newer versions...
@KevinQian97 @ArashHosseini for (2), I think the assumption is that the first pose is always well-recovered. `before_pose` is the last predicted 3d pose. Essentially, if the predicted pose looks wayy...
Hi @lucasnmatias, is this a PR I can find somewhere already? Thanks! :)