Shivani Mall

Hello, does the action space also include amount of force to apply at each position / orn? thanks for your help and making this available.

Hello, Is it there an example of loading partnet objects in mujoco simulator? Or do you advise to use pybullet sim? Many thanks for your help.

getting results over different seeds

3

Hello, New to this library, wondering how can I get results averaged over various seeds passed as filter by exp_name (seen in the picture below)  Also, is there a...

TAPIR loss computation clarification

4

Hello, I saw in a comment in `tapir_model.py` code that says: `At training time there's only one iteration, so we'll just get the final refined output.` However, in the paper,...

Get Query Features in TAPIR

1

Is there a reason why the return value for `get_query_feats` is not supported in TAPIR as the value is already present in `interp_feats`? https://github.com/google-deepmind/tapnet/blob/main/tapnet/torch/tapir_model.py#L174

TAPIR training time stats

2

I am using TAPIR as backbone architecture, and starting from the checkpoint version. I have to further train it for my case. Do you have any suggestions for what training...

Hello, I wonder if you have the visualisation for homography / H-patches experiments? thank you!