feat(dataset): add streaming video encoding + HW encoder support (#2974)

* feat(dataset): init stream encoding

* feat(dataset): use threads to fix frame pickle latency

* refactor(dataset): remove HW encoded related changes

* add lp (#2977)

* feat(dataset): add Hw encoding + log drop frames (#2978)

* chore(docs): add streaming video encoding guide

* fix(dataset): style docs + testing

* chore(docs): simplify sttreaming video encoding guide

* chore(dataset): add commands + streaming encoding default false + print note if false + queue default is now 30

* chore(docs): add verification note advice

* chore(dataset): adjusting defaults & docs for streaming encoding

* docs(scripts): improve docstrings

* test(dataset): polish streaming encoding tests

* chore(dataset): move FYI log related to streaming

* chore(dataset): add arg vcodec to suggestions

* refactor(dataset): better handling for auto and available vcodec

* chore(dataset): change log level

* docs(dataset): add note related to training performance vcodec

* docs(dataset): add more notes to streaming encoding

---------

Co-authored-by: Caroline Pascal <caroline8.pascal@gmail.com>
Co-authored-by: Pepijn <pepijn@huggingface.co>
This commit is contained in:
Steven Palma
2026-02-23 13:57:43 +01:00
committed by GitHub
parent 5865170d36
commit e96339a3b4
16 changed files with 1532 additions and 55 deletions
+6 -3
View File
@@ -31,7 +31,6 @@ from lerobot.configs.train import TrainPipelineConfig
from lerobot.datasets.factory import make_dataset
from lerobot.datasets.image_writer import image_array_to_pil_image
from lerobot.datasets.lerobot_dataset import (
VALID_VIDEO_CODECS,
LeRobotDataset,
MultiLeRobotDataset,
_encode_video_worker,
@@ -45,6 +44,7 @@ from lerobot.datasets.utils import (
hf_transform_to_torch,
hw_to_dataset_features,
)
from lerobot.datasets.video_utils import VALID_VIDEO_CODECS
from lerobot.envs.factory import make_env_config
from lerobot.policies.factory import make_policy_config
from lerobot.robots import make_robot_from_config
@@ -393,7 +393,7 @@ def test_tmp_mixed_deletion(tmp_path, empty_lerobot_dataset_factory):
vid_key: {"dtype": "video", "shape": DUMMY_HWC, "names": ["height", "width", "channels"]},
}
ds_mixed = empty_lerobot_dataset_factory(
root=tmp_path / "mixed", features=features_mixed, batch_encoding_size=2
root=tmp_path / "mixed", features=features_mixed, batch_encoding_size=2, streaming_encoding=False
)
ds_mixed.add_frame(
{
@@ -1450,7 +1450,10 @@ def test_valid_video_codecs_constant():
assert "h264" in VALID_VIDEO_CODECS
assert "hevc" in VALID_VIDEO_CODECS
assert "libsvtav1" in VALID_VIDEO_CODECS
assert len(VALID_VIDEO_CODECS) == 3
assert "auto" in VALID_VIDEO_CODECS
assert "h264_videotoolbox" in VALID_VIDEO_CODECS
assert "h264_nvenc" in VALID_VIDEO_CODECS
assert len(VALID_VIDEO_CODECS) == 10
def test_delta_timestamps_with_episodes_filter(tmp_path, empty_lerobot_dataset_factory):