admin/lerobot
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-07-19 16:02:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(RGB <-> camera): renaming camera_encoder to rgb_encoder for clarity

Browse Source
This commit is contained in:
CarolinePascal
2026-06-23 11:28:13 +02:00
parent 8f939767ca
commit 2167731b2c
23 changed files with 170 additions and 158 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/datasets/test_dataset_tools.py
+8 -8
View File
@@ -24,7 +24,7 @@ import torch
pytest.importorskip("datasets", reason="datasets is required (install lerobot[dataset])")
from lerobot.configs import DepthEncoderConfig, VideoEncoderConfig
from lerobot.configs import DepthEncoderConfig, RGBEncoderConfig
from lerobot.datasets.dataset_tools import (
add_features,
convert_image_to_video_dataset,
@@ -1253,7 +1253,7 @@ def test_convert_image_to_video_dataset(tmp_path):
dataset=source_dataset,
output_dir=output_dir,
repo_id="lerobot/pusht_video",
camera_encoder=VideoEncoderConfig(
rgb_encoder=RGBEncoderConfig(
vcodec="libsvtav1",
pix_fmt="yuv420p",
g=2,
@@ -1396,7 +1396,7 @@ def test_convert_image_to_video_dataset_depth(tmp_path, empty_lerobot_dataset_fa
dataset=source_dataset,
output_dir=output_dir,
repo_id="dummy/depth_video",
camera_encoder=VideoEncoderConfig(vcodec="libsvtav1", pix_fmt="yuv420p", g=2, crf=30),
rgb_encoder=RGBEncoderConfig(vcodec="libsvtav1", pix_fmt="yuv420p", g=2, crf=30),
depth_encoder=depth_encoder,
num_workers=1,
)
@@ -1466,12 +1466,12 @@ def test_reencode_dataset_multi_key_multiprocessing(
):
"""Re-encode a two-camera dataset with num_workers=2 and verify metadata refresh."""
features = features_factory(use_videos=True)
initial_cfg = VideoEncoderConfig(vcodec="libsvtav1", g=2, crf=30, preset=12)
initial_cfg = RGBEncoderConfig(vcodec="libsvtav1", g=2, crf=30, preset=12)
dataset = empty_lerobot_dataset_factory(
root=tmp_path / "ds",
features=features,
use_videos=True,
camera_encoder=initial_cfg,
rgb_encoder=initial_cfg,
)
add_frames(dataset, num_frames=4)
@@ -1482,13 +1482,13 @@ def test_reencode_dataset_multi_key_multiprocessing(
assert len(dataset.meta.video_keys) == 2
target_cfg = VideoEncoderConfig(vcodec="h264", g=6, crf=23, pix_fmt="yuv420p")
target_cfg = RGBEncoderConfig(vcodec="h264", g=6, crf=23, pix_fmt="yuv420p")
result = reencode_dataset(dataset, camera_encoder=target_cfg, num_workers=2)
result = reencode_dataset(dataset, rgb_encoder=target_cfg, num_workers=2)
assert result is dataset
persisted_info = load_info(dataset.root)
for vk in dataset.meta.video_keys:
persisted_encoder = VideoEncoderConfig.from_video_info(persisted_info.features[vk].get("info", {}))
persisted_encoder = RGBEncoderConfig.from_video_info(persisted_info.features[vk].get("info", {}))
assert persisted_encoder == target_cfg
tests/datasets/test_streaming_video_encoder.py
+8 -8
View File
@@ -173,7 +173,7 @@ class TestStreamingVideoEncoder:
video_keys = [f"{OBS_IMAGES}.laptop"]
encoder = StreamingVideoEncoder(
fps=30,
camera_encoder=self._make_encoder_config(
rgb_encoder=self._make_encoder_config(
vcodec="libsvtav1", pix_fmt="yuv420p", g=2, crf=30, preset=13
),
)
@@ -205,7 +205,7 @@ class TestStreamingVideoEncoder:
video_keys = [f"{OBS_IMAGES}.laptop", f"{OBS_IMAGES}.phone"]
encoder = StreamingVideoEncoder(
fps=30,
camera_encoder=self._make_encoder_config(vcodec="libsvtav1", pix_fmt="yuv420p", g=2, crf=30),
rgb_encoder=self._make_encoder_config(vcodec="libsvtav1", pix_fmt="yuv420p", g=2, crf=30),
)
encoder.start_episode(video_keys, tmp_path)
@@ -231,7 +231,7 @@ class TestStreamingVideoEncoder:
video_keys = [f"{OBS_IMAGES}.cam"]
encoder = StreamingVideoEncoder(
fps=30,
camera_encoder=self._make_encoder_config(vcodec="libsvtav1", pix_fmt="yuv420p", g=2, crf=30),
rgb_encoder=self._make_encoder_config(vcodec="libsvtav1", pix_fmt="yuv420p", g=2, crf=30),
)
for ep in range(3):
@@ -257,7 +257,7 @@ class TestStreamingVideoEncoder:
video_keys = [f"{OBS_IMAGES}.cam"]
encoder = StreamingVideoEncoder(
fps=30,
camera_encoder=self._make_encoder_config(vcodec="libsvtav1", pix_fmt="yuv420p", g=2, crf=30),
rgb_encoder=self._make_encoder_config(vcodec="libsvtav1", pix_fmt="yuv420p", g=2, crf=30),
)
encoder.start_episode(video_keys, tmp_path)
@@ -303,7 +303,7 @@ class TestStreamingVideoEncoder:
video_keys = [f"{OBS_IMAGES}.cam"]
encoder = StreamingVideoEncoder(
fps=30,
camera_encoder=self._make_encoder_config(
rgb_encoder=self._make_encoder_config(
vcodec="libsvtav1", pix_fmt="yuv420p", g=2, crf=30, preset=13
),
)
@@ -340,7 +340,7 @@ class TestStreamingVideoEncoder:
video_keys = [f"{OBS_IMAGES}.cam1", f"{OBS_IMAGES}.cam2"]
encoder = StreamingVideoEncoder(
fps=30,
camera_encoder=self._make_encoder_config(vcodec="libsvtav1", pix_fmt="yuv420p", g=2, crf=30),
rgb_encoder=self._make_encoder_config(vcodec="libsvtav1", pix_fmt="yuv420p", g=2, crf=30),
)
encoder.start_episode(video_keys, tmp_path)
@@ -377,7 +377,7 @@ class TestStreamingVideoEncoder:
)
encoder = StreamingVideoEncoder(
fps=30,
camera_encoder=cfg,
rgb_encoder=cfg,
encoder_threads=2,
)
assert encoder._encoder_threads == 2
@@ -417,7 +417,7 @@ class TestStreamingVideoEncoder:
video_keys = [f"{OBS_IMAGES}.cam"]
encoder = StreamingVideoEncoder(
fps=30,
camera_encoder=self._make_encoder_config(
rgb_encoder=self._make_encoder_config(
vcodec="libsvtav1", pix_fmt="yuv420p", g=2, crf=30, preset=13
),
queue_maxsize=1,
tests/datasets/test_video_encoding.py
+2 -2
View File
@@ -595,7 +595,7 @@ class TestEncoderConfigPersistence:
def test_first_episode_save_persists_encoder_config(self, tmp_path, empty_lerobot_dataset_factory):
cfg = VideoEncoderConfig(vcodec="libsvtav1", g=2, crf=30, preset=12)
dataset = empty_lerobot_dataset_factory(
root=tmp_path / "ds", features=DUMMY_VIDEO_FEATURES, use_videos=True, camera_encoder=cfg
root=tmp_path / "ds", features=DUMMY_VIDEO_FEATURES, use_videos=True, rgb_encoder=cfg
)
add_frames(dataset, num_frames=4)
@@ -618,7 +618,7 @@ class TestEncoderConfigPersistence:
def test_second_episode_does_not_overwrite_encoder_fields(self, tmp_path, empty_lerobot_dataset_factory):
cfg = VideoEncoderConfig(vcodec="libsvtav1", g=2, crf=30, preset=12)
dataset = empty_lerobot_dataset_factory(
root=tmp_path / "ds", features=DUMMY_VIDEO_FEATURES, use_videos=True, camera_encoder=cfg
root=tmp_path / "ds", features=DUMMY_VIDEO_FEATURES, use_videos=True, rgb_encoder=cfg
)
add_frames(dataset, num_frames=4)