ydy0615/lerobot-clone
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-05-31 02:41:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into refactor/benchmark-dispatch

Browse Source
This commit is contained in:
Pepijn
2026-04-07 19:36:20 +02:00
committed by GitHub
parent 4a8c7f3354 4eecbad32b
commit f736a36049
13 changed files with 119 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.github/workflows/documentation-upload-pr.yml vendored
View File

@@ -33,7 +33,7 @@ jobs:
github.event.workflow_run.event == 'pull_request' &&
github.event.workflow_run.conclusion == 'success' &&
github.repository == 'huggingface/lerobot'
uses: huggingface/doc-builder/.github/workflows/upload_pr_documentation.yml@main
uses: huggingface/doc-builder/.github/workflows/upload_pr_documentation.yml@90b4ee2c10b81b5c1a6367c4e6fc9e2fb510a7e3 # main
with:
package_name: lerobot
secrets:

4
.github/workflows/documentation.yml vendored
View File

@@ -55,7 +55,7 @@ jobs:
github.repository == 'huggingface/lerobot'
permissions:
contents: read
uses: huggingface/doc-builder/.github/workflows/build_main_documentation.yml@main
uses: huggingface/doc-builder/.github/workflows/build_main_documentation.yml@90b4ee2c10b81b5c1a6367c4e6fc9e2fb510a7e3 # main
with:
commit_sha: ${{ github.sha }}
package: lerobot
@@ -78,7 +78,7 @@ jobs:
permissions:
contents: read
pull-requests: write
uses: huggingface/doc-builder/.github/workflows/build_pr_documentation.yml@main
uses: huggingface/doc-builder/.github/workflows/build_pr_documentation.yml@90b4ee2c10b81b5c1a6367c4e6fc9e2fb510a7e3 # main
with:
commit_sha: ${{ github.event.pull_request.head.sha }}
pr_number: ${{ github.event.number }}

4
.github/workflows/fast_tests.yml vendored
View File

@@ -65,7 +65,7 @@ jobs:
HF_LEROBOT_HOME: /mnt/cache/.cache/huggingface/lerobot
HF_USER_TOKEN: ${{ secrets.LEROBOT_HF_USER }}
steps:
- uses: actions/checkout@v6
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
persist-credentials: false
lfs: true
@@ -83,7 +83,7 @@ jobs:
libusb-1.0-0-dev speech-dispatcher libgeos-dev portaudio19-dev
- name: Setup uv and Python
uses: astral-sh/setup-uv@v6 # zizmor: ignore[unpinned-uses]
uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6
with:
enable-cache: true
version: ${{ env.UV_VERSION }}

12
.github/workflows/full_tests.yml vendored
View File

@@ -63,7 +63,7 @@ jobs:
HF_LEROBOT_HOME: /mnt/cache/.cache/huggingface/lerobot
HF_USER_TOKEN: ${{ secrets.LEROBOT_HF_USER }}
steps:
- uses: actions/checkout@v6
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
lfs: true
persist-credentials: false
@@ -80,7 +80,7 @@ jobs:
speech-dispatcher libgeos-dev portaudio19-dev
- name: Setup uv and Python
uses: astral-sh/setup-uv@v6 # zizmor: ignore[unpinned-uses]
uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6
with:
enable-cache: true
version: ${{ env.UV_VERSION }}
@@ -137,21 +137,21 @@ jobs:
sudo apt-get update
sudo apt-get install git-lfs
git lfs install
- uses: actions/checkout@v6
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
lfs: true
persist-credentials: false
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3 # zizmor: ignore[unpinned-uses]
uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3
with:
cache-binary: false
- name: Login to Docker Hub
uses: docker/login-action@v3 # zizmor: ignore[unpinned-uses]
uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9 # v3
with:
username: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
password: ${{ secrets.DOCKERHUB_LEROBOT_PASSWORD }}
- name: Build and push Docker image
uses: docker/build-push-action@v6 # zizmor: ignore[unpinned-uses]
uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8 # v6
with:
context: .
file: ./docker/Dockerfile.internal

6
.github/workflows/quality.yml vendored
View File

@@ -43,16 +43,16 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: Checkout code
uses: actions/checkout@v6
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
persist-credentials: false
- name: Set up Python
uses: actions/setup-python@v6
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6
with:
python-version: '3.12'
- name: Run pre-commit hooks
uses: pre-commit/action@v3.0.1 # zizmor: ignore[unpinned-uses]
uses: pre-commit/action@2c7b3805fd2a0fd8c1884dcaebf91fc102a13ecd # v3.0.1
with:
extra_args: --all-files --show-diff-on-failure --color=always

12
.github/workflows/release.yml vendored
View File

@@ -38,12 +38,12 @@ jobs:
steps:
- name: Checkout code
uses: actions/checkout@v6
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
persist-credentials: false
- name: Set up Python
uses: actions/setup-python@v6
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6
with:
python-version: '3.12'
@@ -104,7 +104,7 @@ jobs:
- name: Publish to TestPyPI for pre-releases
# True for tags like 'v0.2.0-rc1'
if: startsWith(github.ref, 'refs/tags/v') && contains(github.ref, '-')
uses: pypa/gh-action-pypi-publish@v1.13.0 # zizmor: ignore[unpinned-uses, use-trusted-publishing]
uses: pypa/gh-action-pypi-publish@ed0c53931b1dc9bd32cbe73a98c7f6766f8a527e # v1.13.0
with:
repository-url: https://test.pypi.org/legacy/
verbose: true
@@ -112,7 +112,7 @@ jobs:
- name: Publish to PyPI
if: startsWith(github.ref, 'refs/tags/v') && !contains(github.ref, '-')
uses: pypa/gh-action-pypi-publish@v1.13.0 # zizmor: ignore[unpinned-uses, use-trusted-publishing]
uses: pypa/gh-action-pypi-publish@ed0c53931b1dc9bd32cbe73a98c7f6766f8a527e # v1.13.0
with:
verbose: true
print-hash: true
@@ -127,7 +127,7 @@ jobs:
env:
MUJOCO_GL: egl
steps:
- uses: actions/checkout@v6
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
lfs: true
persist-credentials: false
@@ -137,7 +137,7 @@ jobs:
git curl libglib2.0-0 libegl1-mesa-dev ffmpeg libusb-1.0-0-dev \
speech-dispatcher libgeos-dev portaudio19-dev
- name: Setup uv and Python
uses: astral-sh/setup-uv@v6 # zizmor: ignore[unpinned-uses]
uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6
with:
enable-cache: true # zizmor: ignore[cache-poisoning]
version: ${{ env.UV_VERSION }}

4
.github/workflows/security.yml vendored
View File

@@ -43,12 +43,12 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: Checkout code
uses: actions/checkout@v6 # zizmor: ignore[unpinned-uses]
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
fetch-depth: 0
persist-credentials: false
- name: Secret Scanning
uses: trufflesecurity/trufflehog@v3.90.0 # zizmor: ignore[unpinned-uses]
uses: trufflesecurity/trufflehog@eafb8c5f6a06175141c27f17bcc17941853d0047 # v3.90.0
with:
extra_args: --only-verified

2
pyproject.toml
View File

@@ -25,7 +25,7 @@ discord = "https://discord.gg/s3KuuzsPFb"
[project]
name = "lerobot"
version = "0.5.1"
version = "0.5.2"
description = "🤗 LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch"
dynamic = ["readme"]
license = { text = "Apache-2.0" }

23
src/lerobot/datasets/lerobot_dataset.py
View File

@@ -151,9 +151,11 @@ class LeRobotDataset(torch.utils.data.Dataset):
``$HF_LEROBOT_HOME/hub``.
episodes (list[int] | None, optional): If specified, this will only load episodes specified by
their episode_index in this list. Defaults to None.
image_transforms (Callable | None, optional): You can pass standard v2 image transforms from
torchvision.transforms.v2 here which will be applied to visual modalities (whether they come
from videos or images). Defaults to None.
image_transforms (Callable | None, optional):
Transform applied to visual modalities inside `__getitem__` after image decoding / tensor
conversion. This works for both image-backed and video-backed observations and can later be
updated with `set_image_transforms()` or cleared with `clear_image_transforms()`.
Defaults to None.
delta_timestamps (dict[list[float]] | None, optional): _description_. Defaults to None.
tolerance_s (float, optional): Tolerance in seconds used to ensure data timestamps are actually in
sync with the fps value. It is used at the init of the dataset to make sure that each
@@ -192,7 +194,8 @@ class LeRobotDataset(torch.utils.data.Dataset):
super().__init__()
self.repo_id = repo_id
self._requested_root = Path(root) if root else None
self.image_transforms = image_transforms
self.reader = None
self.set_image_transforms(image_transforms)
self.delta_timestamps = delta_timestamps
self.episodes = episodes
self.tolerance_s = tolerance_s
@@ -475,6 +478,18 @@ class LeRobotDataset(torch.utils.data.Dataset):
f"}})"
)
def set_image_transforms(self, image_transforms: Callable | None) -> None:
"""Replace the transform applied to visual observations."""
if image_transforms is not None and not callable(image_transforms):
raise TypeError("image_transforms must be callable or None.")
self.image_transforms = image_transforms
if self.reader is not None:
self.reader._image_transforms = image_transforms
def clear_image_transforms(self) -> None:
"""Remove the transform applied to visual observations."""
self.set_image_transforms(None)
# ── Hub methods (stay on facade) ──────────────────────────────────
def push_to_hub(

14
src/lerobot/datasets/multi_dataset.py
View File

@@ -89,12 +89,24 @@ class MultiLeRobotDataset(torch.utils.data.Dataset):
)
self.disabled_features.update(extra_keys)
self.image_transforms = image_transforms
self.delta_timestamps = delta_timestamps
# TODO(rcadene, aliberts): We should not perform this aggregation for datasets
# with multiple robots of different ranges. Instead we should have one normalization
# per robot.
self.stats = aggregate_stats([dataset.meta.stats for dataset in self._datasets])
self.set_image_transforms(image_transforms)
def set_image_transforms(self, image_transforms: Callable | None) -> None:
"""Replace the transform for this dataset and its children."""
if image_transforms is not None and not callable(image_transforms):
raise TypeError("image_transforms must be callable or None.")
self.image_transforms = image_transforms
for dataset in getattr(self, "_datasets", []):
dataset.set_image_transforms(self.image_transforms)
def clear_image_transforms(self) -> None:
"""Remove the transform from this dataset and its children."""
self.set_image_transforms(None)
@property
def repo_id_to_index(self):

1
src/lerobot/scripts/lerobot_record.py
View File

@@ -421,6 +421,7 @@ def record_loop(
act_processed_policy: RobotAction = make_robot_action(action_values, dataset.features)
# Applies a pipeline to the action, default is IdentityProcessor
robot_action_to_send = robot_action_processor((act_processed_policy, obs))
action_values = robot_action_to_send
elif policy is None and isinstance(teleop, Teleoperator):
act = teleop.get_action()

58
tests/datasets/test_datasets.py
View File

@@ -24,6 +24,7 @@ import torch
from huggingface_hub import HfApi
from PIL import Image
from safetensors.torch import load_file
from torchvision.transforms import v2
import lerobot
from lerobot.configs.default import DatasetConfig
@@ -34,6 +35,7 @@ from lerobot.datasets.image_writer import image_array_to_pil_image
from lerobot.datasets.io_utils import hf_transform_to_torch
from lerobot.datasets.lerobot_dataset import LeRobotDataset
from lerobot.datasets.multi_dataset import MultiLeRobotDataset
from lerobot.datasets.transforms import ImageTransforms, ImageTransformsConfig
from lerobot.datasets.utils import (
DEFAULT_CHUNK_SIZE,
DEFAULT_DATA_FILE_SIZE_IN_MB,
@@ -355,6 +357,62 @@ def test_add_frame_image_pil(image_dataset):
assert dataset[0]["image"].shape == torch.Size(DUMMY_CHW)
def test_set_image_transforms_applies_transparently(image_dataset):
dataset = image_dataset
dataset.add_frame({"image": np.random.rand(*DUMMY_CHW), "task": "Dummy task"})
dataset.save_episode()
dataset.finalize()
dataset.set_image_transforms(v2.Resize((224, 224)))
assert dataset[0]["image"].shape == torch.Size((3, 224, 224))
dataset.set_image_transforms(v2.Resize((128, 128)))
assert dataset[0]["image"].shape == torch.Size((3, 128, 128))
dataset.clear_image_transforms()
assert dataset[0]["image"].shape == torch.Size(DUMMY_CHW)
def test_set_image_transforms_supports_lerobot_image_transforms(image_dataset):
dataset = image_dataset
dataset.add_frame({"image": np.random.rand(*DUMMY_CHW), "task": "Dummy task"})
dataset.save_episode()
dataset.finalize()
image_transforms = ImageTransforms(ImageTransformsConfig(enable=False))
dataset.set_image_transforms(image_transforms)
assert dataset.image_transforms is image_transforms
assert dataset[0]["image"].shape == torch.Size(DUMMY_CHW)
def test_set_image_transforms_supports_loaded_dataset(tmp_path, lerobot_dataset_factory):
dataset = lerobot_dataset_factory(root=tmp_path / "test", use_videos=False)
dataset.set_image_transforms(v2.Compose([v2.Resize((224, 224)), v2.Resize((112, 112))]))
camera_key = dataset.meta.camera_keys[0]
assert dataset[0][camera_key].shape == torch.Size((3, 112, 112))
def test_multilerobot_dataset_set_image_transforms_propagates(tmp_path, lerobot_dataset_factory):
root = tmp_path / "multi"
repo_ids = ["lerobot/test_multi_a", "lerobot/test_multi_b"]
for repo_id in repo_ids:
lerobot_dataset_factory(root=root / repo_id, repo_id=repo_id, use_videos=False)
dataset = MultiLeRobotDataset(repo_ids, root=root, download_videos=False)
dataset.set_image_transforms(v2.Resize((96, 96)))
camera_key = dataset.camera_keys[0]
assert dataset[0][camera_key].shape == torch.Size((3, 96, 96))
assert all(child.image_transforms is dataset.image_transforms for child in dataset._datasets)
dataset.clear_image_transforms()
assert dataset.image_transforms is None
assert all(child.image_transforms is None for child in dataset._datasets)
def test_image_array_to_pil_image_wrong_range_float_0_255():
image = np.random.rand(*DUMMY_HWC) * 255
with pytest.raises(ValueError):

10
uv.lock generated
View File

@@ -1,5 +1,5 @@
version = 1
revision = 2
revision = 3
requires-python = ">=3.12"
resolution-markers = [
"python_full_version >= '3.14' and platform_machine != 's390x' and sys_platform == 'linux'",
@@ -1828,7 +1828,7 @@ wheels = [
[[package]]
name = "huggingface-hub"
version = "1.9.0"
version = "1.9.1"
source = { registry = "https://pypi.org/simple" }
dependencies = [
{ name = "filelock" },
@@ -1841,9 +1841,9 @@ dependencies = [
{ name = "typer" },
{ name = "typing-extensions" },
]
sdist = { url = "https://files.pythonhosted.org/packages/88/bb/62c7aa86f63a05e2f9b96642fdef9b94526a23979820b09f5455deff4983/huggingface_hub-1.9.0.tar.gz", hash = "sha256:0ea5be7a56135c91797cae6ad726e38eaeb6eb4b77cefff5c9d38ba0ecf874f7", size = 750326, upload-time = "2026-04-03T08:35:55.888Z" }
sdist = { url = "https://files.pythonhosted.org/packages/44/40/68d9b286b125d9318ae95c8f8b206e8672e7244b0eea61ebb4a88037638c/huggingface_hub-1.9.1.tar.gz", hash = "sha256:442af372207cc24dcb089caf507fcd7dbc1217c11d6059a06f6b90afe64e8bd2", size = 750355, upload-time = "2026-04-07T13:47:59.167Z" }
wheels = [
{ url = "https://files.pythonhosted.org/packages/73/37/0d15d16150e1829f3e90962c99f28257f6de9e526a680b4c6f5acdb54fd2/huggingface_hub-1.9.0-py3-none-any.whl", hash = "sha256:2999328c058d39fd19ab748dd09bd4da2fbaa4f4c1ddea823eab103051e14a1f", size = 637355, upload-time = "2026-04-03T08:35:53.897Z" },
{ url = "https://files.pythonhosted.org/packages/3d/af/10a89c54937dccf6c10792770f362d96dd67aedfde108e6e1fd7a0836789/huggingface_hub-1.9.1-py3-none-any.whl", hash = "sha256:8dae771b969b318203727a6c6c5209d25e661f6f0dd010fc09cc4a12cf81c657", size = 637356, upload-time = "2026-04-07T13:47:57.239Z" },
]
[[package]]
@@ -2184,7 +2184,7 @@ wheels = [
[[package]]
name = "lerobot"
version = "0.5.1"
version = "0.5.2"
source = { editable = "." }
dependencies = [
{ name = "accelerate" },