ydy0615/lerobot-clone
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-06-02 03:41:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(audio visualization): making audio visualization robust to multiple channel audio data

Browse Source
This commit is contained in:
CarolinePascal
2025-10-27 14:28:12 +01:00
parent 6bd40ca219
commit 1ee4d84f07
1 changed files with 19 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
src/lerobot/utils/visualization_utils.py
View File

@@ -152,22 +152,25 @@ def log_rerun_data(
for i, vi in enumerate(arr):
rr.log(f"{key}_{i}", rr.Scalars(float(vi)))
elif arr.ndim == 2:
rr.send_columns(
"audio/" + key,
indexes=[
rr.TimeSecondsColumn(
"episode_time",
times=log_time
+ np.linspace(
-DEFAULT_AUDIO_CHUNK_DURATION,
0,
len(observation[key]),
endpoint=False,
),
)
],
columns=rr.Scalar.columns(scalar=np.mean(observation[key], axis=1)),
)
for i, channel_arr in enumerate(arr.T):
rr.send_columns(
"audio/"
+ key
+ f"_channel_{i}", # TODO(CarolinePascal): Get actual channel number/name
indexes=[
rr.TimeSecondsColumn(
"episode_time",
times=log_time
+ np.linspace(
-DEFAULT_AUDIO_CHUNK_DURATION,
0,
len(channel_arr),
endpoint=False,
),
)
],
columns=rr.Scalar.columns(scalar=channel_arr),
)
elif arr.ndim == 3:
rr.log(key, rr.Image(arr), static=True)
else: