Sign inSign up

wtyyy/isaacsim

By wtyyy

•Updated over 2 years ago

This image is based on nvcr.io/nvidia/isaac-sim:4.0.0 with python environment.

Image
Machine learning & AI
0

2.7K

wtyyy/isaacsim repository overview

This image is based on nvcr.io/nvidia/isaac-sim:4.0.0⁠, and added some utility packages (zsh, tmux, vim, git, ...).

Python: conda environment (mambaforge), support IsaacLab⁠ and OmniIsaacGymEnvs⁠.

⁠Run container

Command reference⁠ (using zsh instead of bash)

docker run --name isaac-sim --entrypoint zsh -it --runtime=nvidia --gpus all -e "ACCEPT_EULA=Y" --rm --network=host \
    -v ~/docker/isaac-sim/cache/kit:/isaac-sim/kit/cache:rw \
    -v ~/docker/isaac-sim/cache/ov:/root/.cache/ov:rw \
    -v ~/docker/isaac-sim/cache/pip:/root/.cache/pip:rw \
    -v ~/docker/isaac-sim/cache/glcache:/root/.cache/nvidia/GLCache:rw \
    -v ~/docker/isaac-sim/cache/computecache:/root/.nv/ComputeCache:rw \
    -v ~/docker/isaac-sim/logs:/root/.nvidia-omniverse/logs:rw \
    -v ~/docker/isaac-sim/data:/root/.local/share/ov/data:rw \
    -v ~/docker/isaac-sim/documents:/root/Documents:rw \
    wtyyy/isaacsim:latest

⁠Run RL Demos

If you stuck at Task Device: cuda:0, RL device: cuda:0, try to use proxy configuration function proxy_on in vim ~/.zshrc (default proxy is 127.0.0.1:7890). How to set proxy on server, see MyBlog - 在服务器上配置Clash代理⁠

⁠OmniIsaacGymEnvs

proxy_on  # If you need proxy to connect nvidia website
cd ~/OmniIsaacGymEnvs/omniisaacgymenvs
conda activate isaaclab
python scripts/rlgames_train.py task=Cartpole headless=True  # change task to Ant, Humanoid

⁠IsaacLab

proxy_on  # If you need proxy to connect nvidia website
cd ~/IsaacLab
conda activate isaaclab
python source/standalone/workflows/rl_games/train.py --task Isaac-Cartpole-v0 --headless

Tag summary

Content type

Image

Digest

sha256:7f254967b…

Size

17.1 GB

Last updated

over 2 years ago

docker pull wtyyy/isaacsim