Iris

@Abdul-Mukit can you upload several dataset, just a very small part of dataset, ten groups of images maybe ok? the network speed is very slow in my country. But I...

@Abdul-Mukit thanks a lot ! do you mean `Deep Object Pose Estimation (DOPE) – ROS inference (CoRL 2018)`？　i don't try it. but thanks for information, but I will have...

@wangg12 @Abdul-Mukit thanks for dataset sharing !!

I use rtx3090 and create docker with the command `docker build -t my-tag`, the dockerfile put at the current path. all is fine.

I met this ram issue as well, when using 8 gpus with the ddp way to train the 3ddet; it cost more than 500GB of RAM, 500G reaches my RAM...

I solved the issue by using the mentioned mmdet3d version ``` mmcv-full=1.5.0 mmdet= 2.19.0 mmdet3d=1.1.0rc1 mmsegmentation=0.20.0 cuda=11.3 ``` When meeting error, just comment the scannet-related code 

I found vllm has supported internvl2? details in: https://github.com/vllm-project/vllm/releases/tag/v0.5.4

pip install gradio==3.40.1 solved it for me accoring to this issue: https://github.com/lllyasviel/ControlNet/issues/492#issuecomment-1675073320