Convert datasets to av1 encoding (#302)

lerobot/common/datasets/push_dataset_to_hub/utils.py

@@ -13,6 +13,7 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
+import inspect
 from concurrent.futures import ThreadPoolExecutor
 from pathlib import Path
 
@@ -20,6 +21,8 @@ import numpy
 import PIL
 import torch
 
+from lerobot.common.datasets.video_utils import encode_video_frames
+
 
 def concatenate_episodes(ep_dicts):
     data_dict = {}
@@ -51,3 +54,21 @@ def save_images_concurrently(imgs_array: numpy.array, out_dir: Path, max_workers
     num_images = len(imgs_array)
     with ThreadPoolExecutor(max_workers=max_workers) as executor:
         [executor.submit(save_image, imgs_array[i], i, out_dir) for i in range(num_images)]
+
+
+def get_default_encoding() -> dict:
+    """Returns the default ffmpeg encoding parameters used by `encode_video_frames`."""
+    signature = inspect.signature(encode_video_frames)
+    return {
+        k: v.default
+        for k, v in signature.parameters.items()
+        if v.default is not inspect.Parameter.empty and k in ["vcodec", "pix_fmt", "g", "crf"]
+    }
+
+
+def check_repo_id(repo_id: str) -> None:
+    if len(repo_id.split("/")) != 2:
+        raise ValueError(
+            f"""`repo_id` is expected to contain a community or user id `/` the name of the dataset
+            (e.g. 'lerobot/pusht'), but contains '{repo_id}'."""
+        )