Refactor datasets into LeRobotDataset (#91)

Co-authored-by: Alexander Soare <alexander.soare159@gmail.com>
This commit is contained in:
Remi
2024-04-25 12:23:12 +02:00
committed by GitHub
parent e760e4cd63
commit 659c69a1c0
90 changed files with 167 additions and 352 deletions

View File

@@ -73,15 +73,14 @@ environments ([aloha](https://github.com/huggingface/gym-aloha),
[pusht](https://github.com/huggingface/gym-pusht))
and follow the same api design.
When implementing a new dataset class (e.g. `AlohaDataset`) follow these steps:
- Update `available_datasets` in `lerobot/__init__.py`
- Copy it in the required `available_datasets` class attribute
When implementing a new dataset loadable with LeRobotDataset follow these steps:
- Update `available_datasets_per_env` in `lerobot/__init__.py`
When implementing a new environment (e.g. `gym_aloha`), follow these steps:
- Update `available_envs`, `available_tasks_per_env` and `available_datasets` in `lerobot/__init__.py`
- Update `available_tasks_per_env` and `available_datasets_per_env` in `lerobot/__init__.py`
When implementing a new policy class (e.g. `DiffusionPolicy`) follow these steps:
- Update `available_policies` in `lerobot/__init__.py`
- Update `available_policies` and `available_policies_per_env`, in `lerobot/__init__.py`
- Set the required `name` class attribute.
- Update variables in `tests/test_available.py` by importing your new Policy class