Kaizhi Zheng

Same to me on AI2THOR 3.1.0 and NVIDIA A6000 GPU. When I run multiple instances on a headless GPU server, the RGB images will occur across different instances.

I think AI2THOR 3.1.0 cannot support cloud rendering, right?

Since I'm working on [TEACh](https://github.com/alexa/teach) dataset and their codes need to use AI2THOR 3.1.0, I think I cannot upgrade to a newer version.

I just quoted from their repo. https://github.com/alexa/teach/blob/2e5be94ebdef4910a61cb1bce069d80b0079d1d3/src/teach/simulators/simulator_THOR.py#L30 ``` COMMIT_ID = "fdc047690ee0ab7a91ede50d286bd387d379713a" class TEAChController(Controller): def __init__(self, base_dir: str, **kwargs): self._base_dir = base_dir os.makedirs(base_dir, exist_ok=True) super().__init__(**kwargs) @staticmethod def build_local_executable_path(base_dir: str, commit_id: str,...

> I see. Makes sense. Can you share your Controller initialization code? I can run the multiple processes on AWS with ubuntu 18.04 and Nvidia V100 GPUs, but the same...

> > Hi, I faced the problem that I want to export multiple tags of the same AnnotatedActor to .json file, i.e. a cup can also be a container, but...

I remember this issue was fixed after I wrote a new startx.py

I think this issue comes from Xorg. One possible way to solve this is to create a new Xorg

Since the Gaussian kernel will exponentially fall off from the mean, there will be some color outperforming 1. Here is the code I used to deal with this: ```python plydata...

> I am relatively new to coding. for the line with opacities=self.sigmoid(opacities). What is the self and which class is it from? It is just a sigmoid function by using...