Samarth Brahmbhatt

@anilesec I am not sure why annotations are present for that camera, but images are not. Can you see if the `download_data.py` script has a Dropbox link for that camera's...

Yes that is rare but possible. In `annotations.json` for full2_handoff-apple, look at the `cameras` section. Do they have `valid: True`?

> Thanks, @samarth-robo for the response. I think I understand what you mean. This means that MANO pose and shape parameters are the same for all the frames (as hand...

> I understood how to get the meshes(of hand) for each frame. But, I am interested in mano parameters for each frame( the meshes of each frame are trivial for...

@anilesec I don't understand fully. Can you please elaborate?

@anilesec we don't have that, sorry. But background subtraction (or foreground extraction) should not be too difficult if you start from the example we have provided for cropping the area...

@anilesec it has been a while since I looked at the code, but if you look after this line https://github.com/facebookresearch/ContactPose/blob/main/scripts/preprocess_images.py#L101, the foreground mask is derived from colour and depth thresholding....

@QuantHao thanks for the pointer. I was experiencing this issue while trying to run parallel TF-Agents drivers using mpi4py. Just adding `env.close()` at the end of my script solved it...

For observations, it seems like the replay buffer is expecting a batch of `[1, 160, 260, 3]` elements of `batch_size = 1` i.e. a tensor of dims `[1, 1, 160,...

The issue is with how [`ppo_utils.get_distribution_params()`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/agents/ppo/ppo_utils/get_distribution_params?hl=en) is used inside the `PPOPolicy` class. When the `PPOClipAgent` has an `ActorDistributionNetwork`, the `scale` parameter of the output distribution is (for some reason) not...