mirror of
https://github.com/huggingface/lerobot.git
synced 2026-06-01 03:11:29 +00:00
b540fa94a9
log_rerun_data now accepts an optional `features` dict and uses the `video.is_depth_map=True` info marker to detect depth observations. Matching 2D arrays are logged as `rr.DepthImage(arr, meter=1.0, colormap=rr.components.Colormap.Viridis)` and are never JPEG-compressed (compression is lossy on float32 metric depth). Detection covers both the namespaced dataset key (e.g. `observation.depth.front`) and the raw observation keys the robot emits (`front`, `front_depth`), so it works for both the typed LeRobotDataset.features dict and the plain robot observation flow. When `features` is None the previous behaviour is preserved (depth arrays fall back to the generic `rr.Image` path), so non-depth recordings and existing call sites are unaffected. lerobot-record now forwards `dataset.features` so depth keys are picked up automatically when `--display_data=true`. Made-with: Cursor