Add dataset cards (#363)

lerobot/scripts/control_robot.py

@@ -130,7 +130,12 @@ from lerobot.common.robot_devices.robots.factory import make_robot
 from lerobot.common.robot_devices.robots.utils import Robot
 from lerobot.common.utils.utils import get_safe_torch_device, init_hydra_config, init_logging, set_global_seed
 from lerobot.scripts.eval import get_pretrained_policy_path
-from lerobot.scripts.push_dataset_to_hub import push_meta_data_to_hub, push_videos_to_hub, save_meta_data
+from lerobot.scripts.push_dataset_to_hub import (
+    push_dataset_card_to_hub,
+    push_meta_data_to_hub,
+    push_videos_to_hub,
+    save_meta_data,
+)
 
 ########################################################################################
 # Utilities
@@ -292,6 +297,7 @@ def record(
     video=True,
     run_compute_stats=True,
     push_to_hub=True,
+    tags=None,
     num_image_writers=8,
     force_override=False,
 ):
@@ -647,6 +653,7 @@ def record(
     if push_to_hub:
         hf_dataset.push_to_hub(repo_id, revision="main")
         push_meta_data_to_hub(repo_id, meta_data_dir, revision="main")
+        push_dataset_card_to_hub(repo_id, revision="main", tags=tags)
         if video:
             push_videos_to_hub(repo_id, videos_dir, revision="main")
         create_branch(repo_id, repo_type="dataset", branch=CODEBASE_VERSION)
@@ -758,6 +765,12 @@ if __name__ == "__main__":
         default=1,
         help="Upload dataset to Hugging Face hub.",
     )
+    parser_record.add_argument(
+        "--tags",
+        type=str,
+        nargs="*",
+        help="Add tags to your dataset on the hub.",
+    )
     parser_record.add_argument(
         "--num-image-writers",
         type=int,

lerobot/scripts/push_dataset_to_hub.py

@@ -56,7 +56,7 @@ from safetensors.torch import save_file
 from lerobot.common.datasets.compute_stats import compute_stats
 from lerobot.common.datasets.lerobot_dataset import CODEBASE_VERSION, LeRobotDataset
 from lerobot.common.datasets.push_dataset_to_hub.utils import check_repo_id
-from lerobot.common.datasets.utils import create_branch, flatten_dict
+from lerobot.common.datasets.utils import create_branch, create_lerobot_dataset_card, flatten_dict
 
 
 def get_from_raw_to_lerobot_format_fn(raw_format: str):
@@ -114,6 +114,14 @@ def push_meta_data_to_hub(repo_id: str, meta_data_dir: str | Path, revision: str
     )
 
 
+def push_dataset_card_to_hub(
+    repo_id: str, revision: str | None, tags: list | None = None, text: str | None = None
+):
+    """Creates and pushes a LeRobotDataset Card with appropriate tags to easily find it on the hub."""
+    card = create_lerobot_dataset_card(tags=tags, text=text)
+    card.push_to_hub(repo_id=repo_id, repo_type="dataset", revision=revision)
+
+
 def push_videos_to_hub(repo_id: str, videos_dir: str | Path, revision: str | None):
     """Expect mp4 files to be all stored in a single "videos" directory.
     On the hugging face repositery, they will be uploaded in a "videos" directory at the root.
@@ -213,6 +221,7 @@ def push_dataset_to_hub(
     if push_to_hub:
         hf_dataset.push_to_hub(repo_id, revision="main")
         push_meta_data_to_hub(repo_id, meta_data_dir, revision="main")
+        push_dataset_card_to_hub(repo_id, revision="main")
         if video:
             push_videos_to_hub(repo_id, videos_dir, revision="main")
         create_branch(repo_id, repo_type="dataset", branch=CODEBASE_VERSION)