9b72f454e9
test(dataset tools): adding missing tests for new dataset edition tools features
2026-06-15 17:56:32 +02:00
f2a6838909
test(fix): fixing depth tests
2026-06-15 17:56:32 +02:00
435465b00c
docs(depth): improving depth maps docs
2026-06-15 17:56:32 +02:00
05e1aad501
chore(format): formatting code
2026-06-15 17:56:31 +02:00
243adf6695
test(depth encoding): updating and cleaning video/depth encoding tests
2026-06-15 17:56:31 +02:00
06e9442149
test(depth): cleaning up depth tests
2026-06-15 17:56:31 +02:00
05c9a9c095
feat(output unit): adding support for output unit specification at dataset reading/training time
...
Co-authored-by: Wensi (Vince) Ai <59036629+wensi-ai@users.noreply.github.com >
2026-06-15 17:56:31 +02:00
6181d6b694
fix(depth units): fixing depth units output for the realsense cameras
2026-06-15 17:56:31 +02:00
971d7ea85b
fix(is_depth): adding missing doctrings and is_depth arguments in video decoding functions
...
Co-authored-by: Wensi (Vince) Ai <59036629+wensi-ai@users.noreply.github.com >
2026-06-15 17:56:31 +02:00
56231b17d1
fix(typo): fixing typo
2026-06-15 17:56:31 +02:00
12a66324fb
fix(from_video_info): fixing early validation issue in from_video_info
2026-06-15 17:56:31 +02:00
0cb8970283
test(cleaning): cleaning up tests
2026-06-15 17:56:31 +02:00
5498bac1b0
test(aggregate): extending aggregation tests to depth frames
2026-06-15 17:56:31 +02:00
05d2a6062d
feat(tools): adding depth support in LeRobotDataset edition tools
2026-06-15 17:56:31 +02:00
a1ec48d3a9
feat(batched dequantization): optimizing dequantize_depth for torch based batched dequantization
2026-06-15 17:56:31 +02:00
c0d19ef35b
fix(TIFF): add missing quantization and cleanup for TIFF files
2026-06-15 17:56:31 +02:00
dd20029f4b
fix(typo): fixing typo
2026-06-15 17:56:30 +02:00
e961f8fec0
fix(normalization): restricting 255 normalization to non depth/uint8 images only
2026-06-15 17:56:30 +02:00
ba7f23adf9
fix(realsense): fixing typo in realsense serial number
2026-06-15 17:56:30 +02:00
a062ffb45c
tests(typos): fixing typos in tests
2026-06-15 17:56:30 +02:00
dfdeac1339
fix(info): fixing info metadata update when is_depth_map was set
2026-06-15 17:56:30 +02:00
beaaaa3d99
fix(pre-commit): fixing mutable defautl value
2026-06-15 17:56:30 +02:00
8afd367c6a
feat(refactor): refactor DepthEncoderConfig quantization pipeline, so that the methods do not live in the config class. Add pixel format - channels validation.Move the default pixel format for depth in the config file.
2026-06-15 17:56:30 +02:00
3c2a990ac3
feat(pix_fmt channels): use PyAv to check get pixel formats number of channels
2026-06-15 17:56:30 +02:00
4610d78c8c
tests(depth): adding new tests for depth integration validation
2026-06-15 17:56:30 +02:00
30dbe0a71b
test(fix): fixing exisiting tests to still work with latest features
2026-06-15 17:56:30 +02:00
7460d2a796
chore(typos): fixing typos
2026-06-15 17:56:30 +02:00
3cbde39767
fix(plumbing): fixing missing parts in the depth maps pipeline
2026-06-15 17:56:30 +02:00
d818a68177
fix(stop_event): fixing stop_event race condition in camera classes
2026-06-15 17:56:30 +02:00
e227adb64f
feat(is_depth): simplifying is_depth nested name + legacy support
2026-06-15 17:56:29 +02:00
90f6f4c1d7
feat(depth shape): ensuring depth maps shape is always including the channel
2026-06-15 17:56:29 +02:00
597f7b063c
chore(format): format code
2026-06-15 17:56:29 +02:00
ea7bb153e0
feat(depth maps writer): adding support for raw depth maps recording with image writer
2026-06-15 17:56:29 +02:00
a930fa8ca5
feat(viz): render depth observations as rr.DepthImage in Viridis
2026-06-15 17:56:29 +02:00
e7191fc3ad
feat(record): plumb DepthEncoderConfig through lerobot-record
2026-06-15 17:56:29 +02:00
712912d946
feat(robots/so_follower): emit + populate depth keys when use_depth
2026-06-15 17:56:29 +02:00
3826531a95
feat(features): route 2D camera shapes to observation.depth.<key>
2026-06-15 17:56:29 +02:00
325b351ff2
feat(cameras/realsense): expose async depth in metric meters
2026-06-15 17:56:29 +02:00
44461eaadc
feat(depth): wire DatasetReader to decode_depth_frames
2026-06-15 17:56:29 +02:00
330f63bf87
feat(depth): wire StreamingVideoEncoder + writer to depth encoder
2026-06-15 17:56:29 +02:00
5d56804d81
feat(depth): plumb DepthEncoderConfig through LeRobotDataset and DatasetWriter
2026-06-15 17:56:29 +02:00
a6e95c4d26
feat(depth): extend quantization tools to better fit the encoding/decoding pipeline
2026-06-15 17:56:28 +02:00
10bb300e8a
feat(depth): persist depth metadata
2026-06-15 17:56:28 +02:00
e5e241e2cb
feat(video): add ffv1 to supported codecs
2026-06-15 17:56:28 +02:00
b8ddd64120
feat(depth): add depth quantization helpers and tests
2026-06-15 17:56:28 +02:00
38327fdc84
fix(images/videos): fixing aggregate_pipeline_dataset_features to avoid unwanted images features deletion ( #3783 )
...
* fix(images/videos): fixing aggregate_pipeline_dataset_features to avoid unwanted images features deletion when videos are not used
* fix(docstrings): improving docstrings
Signed-off-by: Caroline Pascal <caroline8.pascal@gmail.com >
---------
Signed-off-by: Caroline Pascal <caroline8.pascal@gmail.com >
2026-06-15 17:55:52 +02:00
9555efc02c
chore(dependencies): update uv.lock ( #3595 )
...
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2026-06-15 16:29:44 +02:00
d576c59afb
refactor(robots): homogenize bi-manual setups implementations ( #3772 )
...
* chore(robots): homogenize bi setups
* feat(robots): split openarm mini into single and bi
* refactor(robots): mixin for bi classes
* docs: update docs
2026-06-15 16:28:54 +02:00
8515d456be
fix(datasets): avoid uint8 overflow in image stats ( #3697 )
...
* fix(datasets): avoid uint8 overflow in image stats
* fix(datasets): promote stats batches dynamically
2026-06-13 12:09:43 +02:00
30790de178
feat(edit-dataset): add concatenate_videos opt-out to merge ( #3663 )
...
* feat(edit-dataset): add `concatenate_videos` opt-out to merge
When merging datasets, source mp4s are concatenated into shards capped at
`video_files_size_in_mb` (default 200 MB). This is great for dataloader
throughput but destroys per-episode (or per-source) video boundaries,
which is undesirable when you want to inspect, ship, or reuse the
individual mp4s.
Add a `concatenate_videos: bool = True` knob plumbed through
`MergeConfig` → `merge_datasets` → `aggregate_datasets` → `aggregate_videos`.
When False, each source mp4 is copied 1:1 to its own destination mp4 with
no re-muxing, so the merge preserves source video boundaries.
Usage:
lerobot-edit-dataset \
--new_repo_id user/merged \
--operation.type=merge \
--operation.repo_ids "['user/a', 'user/b']" \
--operation.concatenate_videos=false
Defaults are unchanged; the dataloader path is unaffected because the
`episodes.parquet` `from_timestamp`/`to_timestamp` index keeps working
regardless of whether each mp4 holds one or many episodes.
* feat(edit-dataset): extend concatenate opt-out to data files
Following review, add a concatenate_data flag mirroring concatenate_videos,
threaded through MergeConfig, merge_datasets, aggregate_datasets, aggregate_data
and append_or_create_parquet_file. Metadata index files still always concatenate.
Also trim the verbose docstrings and comments since the names are
self-explanatory, and extend the existing merge test to cover data files.
2026-06-12 20:05:04 +02:00
CarolinePascal