mshab
A Benchmark for Low-Level Manipulation in Home Rearrangement Tasks
File Explorer
Download Latest Version (.zip)- bc_pick.yml
- dp_pick.yml
- evaluate.yml
- ppo_pick.yml
- sac_pick.yml
- Dockerfile
- nvidia_icd.json
- nvidia_layers.json
- bulma-carousel.min.css
- bulma-slider.min.css
- bulma.css.map.txt
- bulma.min.css
- fontawesome.all.min.css
- index.css
- Geist-Regular.woff
- PPSupplySans-Regular.woff
- footer-bg.webp
- ms_hab2.0_interact_benchmark.png
- mshab_banner.png
- mshab_banner_fullsize.jpg
- mshab_progressive_completion_rates.jpg
- mshab_twitter_banner.png
- mshab_twitter_card.png
- bulma-carousel.js
- bulma-carousel.min.js
- bulma-slider.js
- bulma-slider.min.js
- fontawesome.all.min.js
- index.js
- Favicon.svg
- HillbotLogo.svg
- Icon-arxiv.svg
- Icon-ckpt.svg
- Icon-code.svg
- Icon-data.svg
- Icon-paper.svg
- LinkedInWhite.svg
- Logo.svg
- StateDefault.svg
- XWhite.svg
- mshab_renders.mp4
- mshab_rollouts.mp4
- mshab_zoom_outs.mp4
- index.html
- __init__.py
- agent.py
- __init__.py
- agent.py
- conditional_unet1d.py
- evaluate.py
- make_env.py
- plain_conv.py
- utils.py
- __init__.py
- agent.py
- memory.py
- __init__.py
- agent.py
- misc.py
- modules.py
- replay.py
- __init__.py
- record_episode_statistics.py
- __init__.py
- action.py
- collect_data.py
- debug_video_gpu.py
- observation.py
- record.py
- record_seq_task.py
- __init__.py
- close.py
- make.py
- navigate.py
- open.py
- pick.py
- place.py
- planner.py
- sequential_task.py
- subtask.py
- scene_configs.json
- autumn_field_puresky_4k.hdr
- fetch_1cam.py
- scene_builder_fetch_1cam.py
- mshab.py
- omnigibson.py
- README.md
- interact.yaml
- interact_scene_builder.py
- README.md
- run.py
- gen_data.py
- gen_data_sequential_task.py
- gen_spawn_positions.py
- gen_task_plans.py
- array.py
- config.py
- dataclasses.py
- dataset.py
- io.py
- label_dataset.py
- logger.py
- profile.py
- time.py
- video.py
- evaluate.py
- train_bc.py
- train_diffusion_policy.py
- train_ppo.py
- train_sac.py
- bench.sh
- evaluate_sequential_task.sh
- gen_dataset.sh
- gen_dataset_sequential_task.sh
- train_bc.sh
- train_diffusion_policy.sh
- train_ppo.sh
- train_sac.sh
- .gitignore
- .pre-commit-config.yaml
- pyproject.toml
- README.md
- setup.py
# Installation Guide
1. Get the code
git clone https://github.com/arth-shukla/mshab
Downloads the entire project code from GitHub to your computer.
cd mshab
Moves into the project folder you just downloaded.
2. Docker
Easy RecommendedPrerequisites
- Git Needed to download the project code from GitHub.
- Docker Desktop Needed to build and run containers. Install it and keep it running in the background.
docker build -f docker/Dockerfile -t mshab .
Builds a runnable image based on the Dockerfile.
docker run -p 8080:80 mshab
Runs the built image as an actual container.
Run docker compose ps to check the containers are Up. If the README mentions a port, open http://localhost:PORT in your browser.
3. Python
EasyPrerequisites
pip install -e ManiSkill
Installs the Python libraries listed in requirements.txt (or similar).
pip install -e . # NOTE: you can optionally install train and dev dependencies via `pip install -e .[train,dev]`
Installs the Python libraries listed in requirements.txt (or similar).
for dataset in ycb ReplicaCAD ReplicaCADRearrange; do python -m mani_skill.utils.download_asset "$dataset"; done
Runs the Python script (or module).
pip install -e .[train]
Installs the Python libraries listed in requirements.txt (or similar).
pip install -e .[dev]
Installs the Python libraries listed in requirements.txt (or similar).
If it runs without errors and prints output in the terminal, it worked.
Pulled directly from this repo's README.
// repository documentation
Was this content helpful?
(0 ratings)