8000 Use compressed mp4 file when available to save 98% on storage, and 99% in memory by jtmckay · Pull Request #1035 · huggingface/lerobot · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Use compressed mp4 file when available to save 98% on storage, and 99% in memory #1035

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 6 commits into
base: main
Choose a base branch
8000
from
+30 −4
Open

Use compressed mp4 file when available to save 98% on storage, and 99% in memory #1035

Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
65597de
Use compressed mp4 file when available to save 98% on memory/storage
jtmckay Apr 25, 2025
d7f8310
Remove white space
jtmckay Apr 25, 2025
3d27d1e
Merge branch 'main' into feature/compressed-video
jtmckay Apr 28, 2025
b6e0b21
Merge branch 'main' into feature/compressed-video
jtmckay Apr 30, 2025
27b3a14
Merge branch 'main' into feature/compressed-video
jtmckay May 6, 2025
f63c7b3
Merge branch 'main' into feature/compressed-video
jtmckay May 11, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
34 changes: 30 additions & 4 deletions lerobot/scripts/visualize_dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,6 +134,30 @@ def visualize_dataset(
spawn_local_viewer = mode == "local" and not save
rr.init(f"{repo_id}/episode_{episode_index}", spawn=spawn_local_viewer)

# Track which keys have video files
keys_with_videos = set()

# Log video assets first
for key in dataset.meta.camera_keys:
video_path = dataset.root / dataset.meta.get_video_file_path(episode_index, key)
if not video_path.exists():
logging.warning(f"Video file not found: {video_path}")
continue

video_asset = rr.AssetVideo(path=str(video_path))
rr.log(key, video_asset, static=True)
keys_with_videos.add(key)

# Get frame timestamps in nanoseconds from video
frame_timestamps_ns = video_asset.read_frame_timestamps_ns()

# Ensure metrics data aligns with video frames
rr.send_columns(
key,
indexes=[rr.TimeNanosColumn("frame_index", frame_timestamps_ns)],
columns=rr.VideoFrameReference.columns_nanoseconds(frame_timestamps_ns),
)

# Manually call python garbage collector after `rr.init` to avoid hanging in a blocking flush
# when iterating on a dataloader with `num_workers` > 0
# TODO(rcadene): remove `gc.collect` when rerun version 0.16 is out, which includes a fix
Expand All @@ -147,13 +171,15 @@ def visualize_dataset(
for batch in tqdm.tqdm(dataloader, total=len(dataloader)):
# iterate over the batch
for i in range(len(batch["index"])):
rr.set_time_sequence("frame_index", batch["frame_index"][i].item())
# Convert timestamp to nanoseconds for alignment
timestamp_ns = int(batch["timestamp"][i].item() * 1e9)
rr.set_time_nanos("frame_index", timestamp_ns)
rr.set_time_seconds("timestamp", batch["timestamp"][i].item())

# display each camera image
# Only show individual frames for keys without video files
for key in dataset.meta.camera_keys:
# TODO(rcadene): add `.compress()`? is it lossless?
rr.log(key, rr.Image(to_hwc_uint8_numpy(batch[key][i])))
if key not in keys_with_videos:
rr.log(key, rr.Image(to_hwc_uint8_numpy(batch[key][i])))

# display each dimension of action space (e.g. actuators command)
if "action" in batch:
Expand Down
0