admin/lerobot
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-07-22 17:32:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore(annotation): excluding depth from the annotation pipeline

Browse Source
This commit is contained in:
CarolinePascal
2026-06-24 21:23:13 +02:00
parent 2f30584799
commit 5efeef3c2c
1 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/lerobot/annotations/steerable_pipeline/frames.py
+5 -3
View File
@@ -36,7 +36,7 @@ from typing import Any, Protocol
import PIL.Image import PIL.Image
import torch import torch
from lerobot.configs import VideoEncoderConfig from lerobot.configs import RGBEncoderConfig
from lerobot.datasets.video_utils import decode_video_frames, reencode_video from lerobot.datasets.video_utils import decode_video_frames, reencode_video
from .reader import EpisodeRecord, snap_to_frame from .reader import EpisodeRecord, snap_to_frame
@@ -164,7 +164,9 @@ class VideoFrameProvider:
# only for video-stored cameras. Image-stored cameras (also in # only for video-stored cameras. Image-stored cameras (also in
# ``camera_keys``) would KeyError, so restrict the list — and the # ``camera_keys``) would KeyError, so restrict the list — and the
# default — to video keys. # default — to video keys.
keys = list(self._meta.video_keys) # Depth cameras are excluded from the annotation pipeline for now.
depth_keys = set(self._meta.depth_keys)
keys = [key for key in self._meta.video_keys if key not in depth_keys]
# Last-resort fallback: if metadata didn't surface any video keys but # Last-resort fallback: if metadata didn't surface any video keys but
# the caller explicitly named a camera (``--vlm.camera_key=...``), # the caller explicitly named a camera (``--vlm.camera_key=...``),
# trust them — the key is by definition known to exist on the dataset. # trust them — the key is by definition known to exist on the dataset.
@@ -276,7 +278,7 @@ class VideoFrameProvider:
from_timestamp = float(ep[f"videos/{self.camera_key}/from_timestamp"]) from_timestamp = float(ep[f"videos/{self.camera_key}/from_timestamp"])
to_timestamp = float(ep[f"videos/{self.camera_key}/to_timestamp"]) to_timestamp = float(ep[f"videos/{self.camera_key}/to_timestamp"])
src = self.root / self._meta.get_video_file_path(record.episode_index, self.camera_key) src = self.root / self._meta.get_video_file_path(record.episode_index, self.camera_key)
encoder = VideoEncoderConfig(vcodec="h264", pix_fmt="yuv420p", g=None, crf=23, preset="ultrafast") encoder = RGBEncoderConfig(vcodec="h264", pix_fmt="yuv420p", g=None, crf=23, preset="ultrafast")
try: try:
reencode_video( reencode_video(
src, src,