a41211bbd9
fix(rebase): rebase follow up corrections
2026-06-22 17:17:47 +02:00
d21682c1a7
docs(mermaid): fixing mermaid diagram
2026-06-22 17:17:46 +02:00
cb94a25e1c
fix(pyav check): fixing PyAV option validation for integer codec options by normalizing
...
numeric values before calling `is_integer()`
Co-authored-by: Wensi (Vince) Ai <59036629+wensi-ai@users.noreply.github.com >
2026-06-22 17:17:46 +02:00
b64f827537
chore(format): formatting code
2026-06-22 17:17:46 +02:00
8ef772820f
test(dataset tools): adding missing tests for new dataset edition tools features
2026-06-22 17:17:46 +02:00
5506d32d38
test(fix): fixing depth tests
2026-06-22 17:17:46 +02:00
15e930e6a3
docs(depth): improving depth maps docs
2026-06-22 17:17:46 +02:00
5a95609e80
chore(format): formatting code
2026-06-22 17:17:46 +02:00
6089e831bb
test(depth encoding): updating and cleaning video/depth encoding tests
2026-06-22 17:17:46 +02:00
952766cdd3
test(depth): cleaning up depth tests
2026-06-22 17:17:46 +02:00
f67b2109ca
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 >
2026-06-22 17:17:46 +02:00
d00b4b5e7e
fix(depth units): fixing depth units output for the realsense cameras
2026-06-22 17:17:46 +02:00
c76bf89cb9
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 >
2026-06-22 17:17:46 +02:00
c2edc5530e
fix(typo): fixing typo
2026-06-22 17:17:46 +02:00
8a5869b093
fix(from_video_info): fixing early validation issue in from_video_info
2026-06-22 17:17:46 +02:00
0109b6f1cd
test(cleaning): cleaning up tests
2026-06-22 17:17:45 +02:00
d3eb18c2ba
test(aggregate): extending aggregation tests to depth frames
2026-06-22 17:17:45 +02:00
bf4a00eb35
feat(tools): adding depth support in LeRobotDataset edition tools
2026-06-22 17:17:45 +02:00
2b8a1e0ce9
feat(batched dequantization): optimizing dequantize_depth for torch based batched dequantization
2026-06-22 17:17:45 +02:00
44453ae966
fix(TIFF): add missing quantization and cleanup for TIFF files
2026-06-22 17:17:45 +02:00
551e861750
fix(typo): fixing typo
2026-06-22 17:17:45 +02:00
67ee4cfbb2
fix(normalization): restricting 255 normalization to non depth/uint8 images only
2026-06-22 17:17:45 +02:00
722eab2d07
fix(realsense): fixing typo in realsense serial number
2026-06-22 17:17:45 +02:00
509622ce41
tests(typos): fixing typos in tests
2026-06-22 17:17:45 +02:00
454f9f7d43
fix(info): fixing info metadata update when is_depth_map was set
2026-06-22 17:17:45 +02:00
f3db25adce
fix(pre-commit): fixing mutable defautl value
2026-06-22 17:17:45 +02:00
765bfabbb9
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.
2026-06-22 17:17:45 +02:00
8f6dd077fa
feat(pix_fmt channels): use PyAv to check get pixel formats number of channels
2026-06-22 17:17:45 +02:00
aaec453190
tests(depth): adding new tests for depth integration validation
2026-06-22 17:17:44 +02:00
04b841dfb5
test(fix): fixing exisiting tests to still work with latest features
2026-06-22 17:17:44 +02:00
eca73edbe2
chore(typos): fixing typos
2026-06-22 17:17:44 +02:00
71b3bce19a
fix(plumbing): fixing missing parts in the depth maps pipeline
2026-06-22 17:17:44 +02:00
aae75346b4
fix(stop_event): fixing stop_event race condition in camera classes
2026-06-22 17:17:38 +02:00
e55a883b0a
feat(is_depth): simplifying is_depth nested name + legacy support
2026-06-22 14:44:51 +02:00
edd2854a2c
feat(depth shape): ensuring depth maps shape is always including the channel
2026-06-22 14:44:51 +02:00
520c19904f
chore(format): format code
2026-06-22 14:44:51 +02:00
4566a8d285
feat(depth maps writer): adding support for raw depth maps recording with image writer
2026-06-22 14:44:51 +02:00
11aa5d7785
feat(viz): render depth observations as rr.DepthImage in Viridis
2026-06-22 14:44:51 +02:00
b05df095f5
feat(record): plumb DepthEncoderConfig through lerobot-record
2026-06-22 14:44:51 +02:00
2ccf794c80
feat(robots/so_follower): emit + populate depth keys when use_depth
2026-06-22 14:44:51 +02:00
52321f7bef
feat(features): route 2D camera shapes to observation.depth.<key>
2026-06-22 14:44:50 +02:00
443a4a7445
feat(cameras/realsense): expose async depth in metric meters
2026-06-22 14:44:50 +02:00
e3afbca893
feat(depth): wire DatasetReader to decode_depth_frames
2026-06-22 14:44:48 +02:00
4374bb4368
feat(depth): wire StreamingVideoEncoder + writer to depth encoder
2026-06-22 14:21:53 +02:00
172cdee0cc
feat(depth): plumb DepthEncoderConfig through LeRobotDataset and DatasetWriter
2026-06-22 14:21:53 +02:00
ee87804cb8
feat(depth): extend quantization tools to better fit the encoding/decoding pipeline
2026-06-22 14:21:53 +02:00
0826676c5e
feat(depth): persist depth metadata
2026-06-22 14:21:52 +02:00
b802ec163d
feat(video): add ffv1 to supported codecs
2026-06-22 14:21:52 +02:00
0509162456
feat(depth): add depth quantization helpers and tests
2026-06-22 14:21:52 +02:00
73782447f2
feat(train): FSDP checkpoint saving ( #3810 )
...
* feat(train): FSDP checkpoint saving
* adding docs for FSDP
* adding a test for the fsdp checkpoint path
* cleanup
* fixing final upload to hub
* refactored initial implementation to use torch fsdp api and adding new tests
2026-06-22 13:51:21 +02:00
CarolinePascal