Files
lerobot-clone/pyproject.toml

516 lines
19 KiB
TOML
Raw Normal View History

# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
[build-system]
requires = ["setuptools"]
build-backend = "setuptools.build_meta"
2025-02-16 14:28:03 +01:00
[project.urls]
homepage = "https://huggingface.co/lerobot"
documentation = "https://huggingface.co/docs/lerobot/index"
source = "https://github.com/huggingface/lerobot"
2025-02-16 14:28:03 +01:00
issues = "https://github.com/huggingface/lerobot/issues"
discord = "https://discord.gg/s3KuuzsPFb"
[project]
2024-02-28 19:11:29 +01:00
name = "lerobot"
version = "0.5.2"
2024-04-16 12:09:56 +02:00
description = "🤗 LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch"
dynamic = ["readme"]
license = { text = "Apache-2.0" }
requires-python = ">=3.12"
2024-02-28 19:11:29 +01:00
authors = [
{ name = "Rémi Cadène", email = "re.cadene@gmail.com" },
{ name = "Simon Alibert", email = "alibert.sim@gmail.com" },
{ name = "Alexander Soare", email = "alexander.soare159@gmail.com" },
{ name = "Quentin Gallouédec", email = "quentin.gallouedec@ec-lyon.fr" },
{ name = "Steven Palma", email = "imstevenpmwork@ieee.org" },
{ name = "Pepijn Kooijmans", email = "pepijnkooijmans@outlook.com"},
{ name = "Michel Aractingi", email = "michel.aractingi@gmail.com"},
{ name = "Adil Zouitine", email = "adilzouitinegm@gmail.com" },
{ name = "Dana Aubakirova", email = "danaaubakirova17@gmail.com"},
{ name = "Caroline Pascal", email = "caroline8.pascal@gmail.com"},
{ name = "Martino Russi", email = "nopyeps@gmail.com"},
{ name = "Thomas Wolf", email = "thomaswolfcontact@gmail.com" },
2024-02-28 19:11:29 +01:00
]
classifiers = [
2024-02-28 19:11:29 +01:00
"Development Status :: 3 - Alpha",
"Intended Audience :: Developers",
2024-04-16 12:09:56 +02:00
"Intended Audience :: Education",
"Intended Audience :: Science/Research",
"License :: OSI Approved :: Apache Software License",
"Programming Language :: Python :: 3.12",
"Programming Language :: Python :: 3.13",
"Topic :: Software Development :: Build Tools",
"Topic :: Scientific/Engineering :: Artificial Intelligence",
2024-02-28 19:11:29 +01:00
]
keywords = ["lerobot", "huggingface", "robotics", "machine learning", "artificial intelligence"]
2025-02-16 14:28:03 +01:00
dependencies = [
# Core ML
"torch>=2.7,<2.12.0",
"torchvision>=0.22.0,<0.27.0",
"numpy>=2.0.0,<2.3.0", # NOTE: Explicitly listing numpy helps the resolver converge faster. Upper bound imposed by opencv-python-headless.
"opencv-python-headless>=4.9.0,<4.14.0",
"Pillow>=10.0.0,<13.0.0",
"einops>=0.8.0,<0.9.0",
# Config & Hub
"draccus==0.10.0", # TODO: Relax version constraint
"huggingface-hub>=1.0.0,<2.0.0",
"requests>=2.32.0,<3.0.0",
# Environments
# NOTE: gymnasium is used in lerobot.envs (lerobot-train, lerobot-eval), policies/factory,
# and robots/unitree. Moving it to an optional extra would require import guards across many
# tightly-coupled modules. Candidate for a future refactor to decouple envs from the core.
"gymnasium>=1.1.1,<2.0.0",
# Serialization & checkpointing
"safetensors>=0.4.3,<1.0.0",
# Lightweight utilities
"packaging>=24.2,<26.0",
"termcolor>=2.4.0,<4.0.0",
"tqdm>=4.66.0,<5.0.0",
# Build tools (required by opencv-python-headless on some platforms)
"cmake>=3.29.0.1,<4.2.0",
"setuptools>=71.0.0,<81.0.0",
2025-02-16 14:28:03 +01:00
]
# Optional dependencies
2025-02-16 14:28:03 +01:00
[project.optional-dependencies]
# ── Feature-scoped extras ──────────────────────────────────
dataset = [
Add extensive language support (#3467) * Add extensive language support * Address review: split persistent/event schemas, drop event timestamps - recipe.py: derive _VALID_ROLES/_VALID_STREAMS from MessageRole/MessageStream Literals - dataset_metadata.py: keep CODEBASE_VERSION at v3.0 - language.py: remove RESERVED_STYLES; split arrow/feature schemas into persistent (with timestamp) and event (without timestamp); add docstrings - language_render.py: events use frame-row timestamp implicitly; no per-event timestamp filtering or sorting - converters.py: drop unused subtask_key passthrough - add docstrings to new public APIs (recipe, render_messages_processor, collate) - update tests for split schemas; revert uv.lock Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * Add docstrings to all new helpers; revert uv.lock Covers private helpers in recipe.py, language.py, language_render.py, and render_messages_processor.py. Also reverts uv.lock to main (it was re-generated by `uv run` during local checks). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(language): add motion (persistent) and trace (event-only) styles Promote the previously-reserved motion/trace styles to first-class core styles. motion routes to language_persistent (it tracks robot state over time); trace routes to language_events (single-moment annotations). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(language): per-camera tagging on view-dependent styles Adds a nullable `camera` field to the language row struct (both persistent and event variants) so view-dependent styles like `vqa` can carry which `observation.images.*` view they were grounded against. Without this, multi-camera datasets ended up with multiple `(vqa, role)` rows at the same timestamp that the resolver could not disambiguate. - `language.py`: add `camera` to PERSISTENT_ROW_FIELDS / EVENT_ROW_FIELDS, to both Arrow struct types and the HF datasets feature mappings; introduce VIEW_DEPENDENT_STYLES = {vqa, motion, trace} plus `is_view_dependent_style` and `validate_camera_field` helpers (camera required iff style is view-dependent). - `language_render.py`: thread an optional `camera=` kwarg through every resolver (`active_at`, `emitted_at`, `nth_prev`, `nth_next`) and through `_matching_rows` / `_select_*`, so recipes can disambiguate per-camera VQA with `emitted_at(t, style=vqa, role=assistant, camera=...)`. Without a `camera` filter, multi-row matches keep raising the existing ambiguity error — which is the desired behaviour on multi-camera data. - `recipes/pi05_hirobot.yaml`: replace the single `ask_vqa` branch with `ask_vqa_top` and `ask_vqa_wrist` per-camera sub-recipes (each carrying the matching image block), keeping the original 0.20 budget and documenting the customization point for datasets with different cameras. - Tests: schema test asserts the new field order; new tests cover `is_view_dependent_style`, `validate_camera_field` (both required and forbidden directions), per-camera `emitted_at` filtering, and the ambiguity error when two cameras emit `(vqa, assistant)` at the same timestamp without a `camera=` filter. RenderMessagesStep + dataset passthrough fixtures updated to include the new field. - `docs/source/language_and_recipes.mdx`: document the `camera` field, the per-camera resolver pattern, and the canonical recipe convention. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(language): drop motion from VIEW_DEPENDENT_STYLES Motion primitives are described in robot-frame (joint / Cartesian) terms, not pixel space, so they are camera-agnostic. Only `vqa` (event) and `trace` (event, pixel-trajectory) are view-dependent. The `camera` field stays on PERSISTENT_ROW_FIELDS for schema symmetry — the validator, resolver, and HF feature mapping behave identically across the two columns regardless of which styles populate `camera` today — but persistent rows now always have `camera=None` in practice. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(language): task_aug style + automatic ${task} rephrasing rotation Adds task-prompt diversity (Xiao 2022 / CAST) without touching ``meta/tasks.parquet`` or forcing recipes to opt in. The plan reserved ``task_aug`` as a future style; this lands it now. - ``language.py``: add ``task_aug`` to ``CORE_STYLES`` and ``PERSISTENT_STYLES``. ``column_for_style("task_aug")`` returns ``language_persistent`` so PR 2 writers route it correctly. - ``language_render.py``: ``_resolve_task`` now consults the persistent slice for rows of ``style="task_aug", role="user"``. When any exist it picks one deterministically by ``sample_idx`` (blake2b-keyed, not Python's randomized hash) so an epoch sees every rephrasing of every episode while the same sample still resolves identically across reruns. Falls back to the canonical ``meta/tasks.parquet`` task when no rephrasings are present, so existing datasets and unannotated runs keep their behaviour. Explicit ``task=`` overrides still win. - Tests: rephrasing coverage across samples, determinism on repeat ``sample_idx``, fallback when persistent has no ``task_aug`` rows, and explicit override priority. Recipes get this for free: any ``${task}`` placeholder rotates through the available rephrasings. Recipes that want the literal canonical task can override the binding. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(language): tool catalog in meta/info.json + LeRobotDatasetMetadata.tools Stores OpenAI-style function schemas at ``meta/info.json["tools"]`` so datasets can declare which tools are available (today: just ``say``; tomorrow: per-dataset extensions). The ``DEFAULT_TOOLS`` constant fills in for unannotated datasets so chat-template consumers don't have to special-case anything. Three pieces: - ``language.py``: ``SAY_TOOL_SCHEMA`` and ``DEFAULT_TOOLS`` constants. Single source of truth — PR 2's writer and PR 3's runtime tool registry will both import from here instead of duplicating the dict. - ``dataset_metadata.py``: ``LeRobotDatasetMetadata.tools`` property reads ``info.json["tools"]`` and falls back to ``DEFAULT_TOOLS``. Returns deep-copied dicts so callers can mutate the result safely. - ``docs/source/tools.mdx``: spec page covering the catalog, per-row invocations, and the three-step "how to add a new tool" workflow (declare schema, implement, register). Linked from the docs toctree under the Datasets section. This lays the groundwork for PR 2's pipeline writing the catalog out during annotation, and PR 3's ``src/lerobot/tools/`` package shipping runnable implementations (one file per tool — first up: ``say.py`` wrapping Kyutai's pocket-tts). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * Apply ruff and prettier formatting after merge Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor(language): unify resolver dispatch and prune redundant test scaffolding * Drop the unused `events` kwarg from `active_at`/`nth_prev`/`nth_next`; only `emitted_at` actually consults events. The dispatcher in `_resolve_spec` now passes events conditionally. * Replace the dual `_persistent_sort_key`/`_event_sort_key` pair with a single `_row_sort_key` and drop the `sort_key` parameter from `_select_one`. Event rows lack `timestamp` (it is implicit in the frame) and now default to `0.0` for sort purposes — the `(style, role)` tiebreaker is unchanged. * Inline `_select_latest` into `active_at` (its only caller). * Collapse `emitted_at`'s dual-branch into one `_select_one` call. * Tighten `_validate_persistent_resolver` to a single `column_for_style(style) != LANGUAGE_PERSISTENT` check. * Parameterize `test_per_camera_blend_renders_both_views` over the two cameras and factor the sub-recipe builder into `_vqa_subrecipe` so the test no longer hand-rolls two near-identical recipe blocks. Net -98 LOC; behavior, public resolver names, and test expectations unchanged. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(language): always raise on ambiguous resolver matches `_select_one` previously skipped its ambiguity check whenever any of `role`/`tool_name`/`camera` was set, on the assumption that the caller had already pinned down a unique row. That left a real ambiguity hole for VQA: with two cameras emitting `(vqa, assistant)` at the same frame, `emitted_at(..., role="assistant")` silently picked the first sorted row instead of telling the recipe to add `camera=...`. The existing `test_emitted_at_raises_on_ambiguous_per_camera_vqa` test already encoded the desired behavior. Tighten the check: any time `len(rows) > 1` we now raise with the selectors echoed back, so users see exactly which fields they passed and that more is needed to disambiguate. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore: fix CI — collapse short ValueError to one line, refresh uv.lock * `ruff format` on CI (newer version) wants the short `camera=None` ValueError on a single line. * `uv.lock` was stale relative to `pyproject.toml`'s `datasets>=4.7.0` pin (and picked up upstream `s390x` marker fixes for cuda packages). CI runs `uv sync --locked` which rejected the divergence. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(language): keep base install green — drop processor re-export, gate dataset-extra tests `lerobot.processor` re-exported `RenderMessagesStep` at the package level, so importing anything from `lerobot.processor` pulled in `lerobot.datasets.language` → `lerobot.datasets/__init__.py` → `require_package("datasets")`, which fails in the Tier 1 base install that intentionally omits the `[dataset]` extra. The chain bricked collection for unrelated suites (`tests/policies/pi0_pi05/...`, `tests/envs/...`, etc.). * Stop re-exporting `RenderMessagesStep` from `lerobot.processor`. The only consumer (the test) already imports from the submodule. Document the deliberate omission in the module docstring. * Add `pytest.importorskip("datasets", ...)` (and `pandas` where needed) at the top of the four PR-added tests that exercise the language stack: - tests/datasets/test_language.py - tests/datasets/test_language_render.py - tests/processor/test_render_messages_processor.py - tests/utils/test_collate.py Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(language): address review — tools accessor, motion docs, conditional collate * **`meta.tools` actually reads `info.json["tools"]`.** `DatasetInfo` had no `tools` field, so `from_dict` silently dropped the key (it warned about unknown fields then discarded them) and the property always returned `DEFAULT_TOOLS`. Added `tools: list[dict] | None` to the dataclass; `to_dict()` drops it when unset so existing datasets keep a clean `info.json`. Fixed the accessor to read `self.info.tools` (the previous `.get(...)` would have raised AttributeError on the dataclass anyway). Added regression tests: fallback when absent, round-trip from disk, and round-trip through `DatasetInfo.from_dict` / `to_dict`. * **`motion` is not view-dependent — fix the docs.** The mdx claimed rows of style `motion` must carry `camera`, but `VIEW_DEPENDENT_STYLES = {"vqa", "trace"}` and the validator agrees: motion primitives are joint/Cartesian-frame, not pixel-space. Updated both call-out paragraphs in `language_and_recipes.mdx`. * **Conditional `collate_fn` swap.** Added `meta.has_language_columns` and gate the `lerobot_collate_fn` swap in `lerobot_train.py` on it, so non-language datasets keep PyTorch's `default_collate`. Also added a pass-through test in `test_collate.py` that asserts on a plain tensor batch the custom collate matches `default_collate` key-for-key, plus a test for the `None`-sample drop path. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * review: dedupe regex, centralize column names, harden collate, more tests * **#2 — dedupe `_PLACEHOLDER_RE`.** The same regex was compiled in `recipe.py` and `language_render.py`. Promote to module-level `PLACEHOLDER_RE` in `recipe.py` (its primary owner — declares template syntax) and import from `language_render.py`. * **#3 — centralize language column names.** `io_utils.py` had hardcoded `{"language_persistent", "language_events"}` literals at two sites. Replace with `LANGUAGE_COLUMNS` import so a future column rename can't silently desync. * **#4 — defensive collate preserved-keys.** `lerobot_collate_fn` silently filtered language fields from samples that didn't have them, which would hand downstream consumers a preserved list shorter than the tensor batch. Now: if any sample carries a key, every sample in the batch must carry it; otherwise raise a `ValueError` so the upstream rendering bug surfaces at the boundary. * **#5 — `_scalar` rejects non-singleton lists.** Previously a zero- or multi-element list fell through and triggered confusing `float([])` errors downstream. Now raises `ValueError` with the actual length. * **#6 — refactor `_extract_complementary_data`.** Replace 11 lines of `key = {... if ... else {}}` plus an 11-line splat dict with a single `_COMPLEMENTARY_KEYS` tuple iterated once. * **#7 — document `EXTENDED_STYLES`.** Was an empty `set()` with no comment. Add a docstring explaining it's an intentional extension point: downstream modules append project-local styles before `column_for_style` is called. * **#9 — `tools.mdx` notes the runtime layer is future work.** The page referenced `src/lerobot/tools/`, `registry.py`, and `get_tools(meta)` — none exist in this PR. Added a callout at the start of "How to add your own tool" plus a note on the implementations paragraph. * **#10 — tests for YAML round-trip, malformed rows, blend validation.** `test_recipe.py` grew from 1 case to 12 covering: blend-or-messages exclusivity, target-turn requirement, blend emptiness, weight presence/positivity, nested-blend rejection, `from_dict` with nested blends, `from_yaml` / `load_recipe` agreement, top-level non-mapping rejection. Added a malformed-row test for `_normalize_rows` that asserts non-dict entries raise `TypeError`. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * review: emitted_at uses 0.1s tolerance; MessageTurn requires stream at construction * **Float tolerance in `emitted_at` for persistent styles.** The ``_timestamp(row) == t`` exact-equality check silently missed any caller that derived ``t`` arithmetically (e.g. ``frame_idx / fps``) even though the parquet timestamp would only differ by ULPs. Added ``EMITTED_AT_TOLERANCE_S = 0.1`` and check ``abs(...) <= tolerance`` instead, with a docstring explaining why exact equality wasn't enough and why 0.1 s is safe at typical 30–100 Hz control rates. Test asserts the new behavior at half-window (matches) and double-window (no match) using the constant so it stays in sync. * **`MessageTurn.stream` is required at construction.** It was typed ``MessageStream | None = None`` so YAML could omit ``stream:`` and pass the dataclass invariant — but ``_validate_rendered`` rejected ``None`` streams later, surfacing the error at the first sample instead of at recipe load. Now ``__post_init__`` raises ``ValueError`` if ``stream`` is ``None``, with the list of valid streams in the message. The redundant late-stage check in ``_validate_rendered`` is replaced with a one-line comment that cites the upstream invariant. Test pins the new construction-time rejection. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs(tools): drop follow-up-PR references Reword the two callouts in `tools.mdx` to describe the runtime layer in present tense ("not part of the catalog layer shipped today", "those modules don't yet exist in the tree") instead of pointing at a specific follow-up PR. Keeps the doc honest about what works now without coupling it to a particular release order. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * review: address CarolinePascal feedback - language timestamps: float64 -> float32 to match LeRobotDataset frame timestamps (Arrow struct + HF feature) - dataset_metadata: hoist `.language` imports to module top — language.py has no lerobot imports, so there is no circular-import risk - dataset_metadata: add a `meta.tools` setter that persists the catalog to info.json and reloads `meta.info` - feature_utils: validate the `language` dtype instead of returning "" — warn (non-fatal) when a non-empty value is written at record time - centralize the scalar-unwrap helper as `lerobot.utils.utils.unwrap_scalar`, shared by render_messages_processor and language_render - docs: move `## Layer 2 — recipe anatomy` ahead of the resolver sections, which describe recipe bindings rather than dataset layout - language_render: note in EMITTED_AT_TOLERANCE_S that persistent rows change on a human-action timescale, not the camera frame rate Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-19 14:46:11 +02:00
"datasets>=4.7.0,<5.0.0",
"pandas>=2.0.0,<3.0.0", # NOTE: Transitive dependency of datasets
"pyarrow>=21.0.0,<30.0.0", # NOTE: Transitive dependency of datasets
"lerobot[av-dep]",
# NOTE: torchcodec wheel availability matrix (PyPI):
# - linux x86_64/amd64 + macOS arm64 : wheels since 0.3.0 (the historic supported set).
# - win32 x86_64 : wheels since 0.7.0 (needs torch>=2.8).
# - linux aarch64/arm64 : wheels since 0.11.0 (needs torch>=2.11).
# - macOS x86_64 (Intel) and linux armv7l: no wheels in any released version -> fall through to the PyAV decoder.
# Each platform gets its own line so the resolver picks the minimum version that has a wheel for it.
# Other torch/torchcodec pairings (informational): 0.8.1 = ffmpeg>=8 support, 0.10 = system-wide ffmpeg support, 0.12 needs torch==2.12.
"torchcodec>=0.3.0,<0.12.0; (sys_platform == 'linux' and (platform_machine == 'x86_64' or platform_machine == 'AMD64')) or (sys_platform == 'darwin' and platform_machine == 'arm64')",
"torchcodec>=0.7.0,<0.12.0; sys_platform == 'win32'",
"torchcodec>=0.11.0,<0.12.0; sys_platform == 'linux' and (platform_machine == 'aarch64' or platform_machine == 'arm64')",
"jsonlines>=4.0.0,<5.0.0",
]
training = [
"lerobot[dataset]",
"accelerate>=1.10.0,<2.0.0",
"wandb>=0.24.0,<0.25.0",
]
hardware = [
"lerobot[pynput-dep]",
"lerobot[pyserial-dep]",
"lerobot[deepdiff-dep]",
]
viz = [
"rerun-sdk>=0.24.0,<0.27.0",
]
# ── User-facing composite extras (map to CLI scripts) ─────
# lerobot-record, lerobot-replay, lerobot-calibrate, lerobot-teleoperate, etc.
core_scripts = ["lerobot[dataset]", "lerobot[hardware]", "lerobot[viz]"]
# lerobot-eval -- base evaluation framework. You also need the policy's extra (e.g., lerobot[pi])
# and the environment's extra (e.g., lerobot[pusht]) if evaluating in simulation.
evaluation = ["lerobot[av-dep]"]
# lerobot-dataset-viz, lerobot-imgtransform-viz
dataset_viz = ["lerobot[dataset]", "lerobot[viz]"]
# Common
av-dep = ["av>=15.0.0,<16.0.0"]
pygame-dep = ["pygame>=2.5.1,<2.7.0"]
fix(deps): cap placo below 0.9.16 and harden kinematics import (#3647) * fix(deps): cap placo below 0.9.16 and harden kinematics import placo 0.9.16 links against liburdfdom_sensor.so.4, which is unavailable on Ubuntu 24.04 (noble ships urdfdom 3.x). Importing placo on that base crashes with: ImportError: liburdfdom_sensor.so.4.0: cannot open shared object file This broke nightly Latest Deps tests (CPU and GPU) when the lockfile upgrade picked placo 0.9.16, since lerobot.model.kinematics unconditionally imports placo when _placo_available is true, and that check (importlib.util.find_spec) cannot detect dlopen failures of transitive shared libraries — so unrelated subsystems (RL actor, gym_manipulator) became unimportable. Two changes: 1. Pin placo to <0.9.16 in pyproject.toml + regenerate uv.lock (0.9.16 → 0.9.15). Short-term unblock for nightly CI until system urdfdom 4.x is broadly available. 2. Harden the import guard in src/lerobot/model/kinematics.py: wrap 'import placo' in try/except ImportError so a missing transitive .so no longer crashes module import. RobotKinematics instantiation now raises an informative ImportError citing the underlying dlopen failure via _raise_if_placo_unusable(). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(kinematics): hoist _placo_runtime_error to module scope for mypy Mypy walks the TYPE_CHECKING branch in which the runtime else-block is not executed, so _placo_runtime_error was only defined at runtime and mypy reported 'Name "_placo_runtime_error" is not defined' on the three references inside _raise_if_placo_unusable. Declare the symbol unconditionally at module scope with a default of None; the runtime import-failure branch still assigns to it. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * style(kinematics): drop verbose comments around placo import guard Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-22 12:03:07 +02:00
# NOTE: 0.9.16 links against liburdfdom_sensor.so.4, which is unavailable on Ubuntu 24.04
# (noble ships urdfdom 3.x). Cap below 0.9.16 until system urdfdom 4.x is broadly available.
placo-dep = ["placo>=0.9.6,<0.9.16"]
transformers-dep = ["transformers>=5.4.0,<5.6.0"]
grpcio-dep = ["grpcio==1.73.1", "protobuf>=6.31.1,<6.32.0"]
can-dep = ["python-can>=4.2.0,<5.0.0"]
chore(dependencies): bump transformers v5 (#2964) * chore(dependencies): upgrade transformers + hggingface-hub + peft + scipy * chore(dependencies): bump pi0 family to transformers v5 * chore(dependencies): bump wall x to transformers v5 * chore(dependencies): bump gr00t to transformers v5 * chore(style): fix pre-commit * fix(policy): xvla forced_bos_token missing * test(rl): skip ci tests for resnet10 * Fix: full pi models support for transformer v5 (#2967) * fix(pi): remove loss truncation * fix(pi): remove state padding before tokenization * fix(pi): fix image padding value * fix from_pretrain * add transformer v5 changes * remove reference * more fixes * make it work * add support for rest of pi family * add pifast work * more changes * more changes * more cleanup * fix torch params * dtype fix * torch compile * embed mismatch fix * revert groot * more nit fixes * remove unused classes * more fixes * revert * nit * torch dtype warning fix * but back dynamic renaming * add tie embedding --------- Co-authored-by: Yufei Sun <skieyfly@gmail.com> * chore: fix XVLA in transformers v5 (#3006) * test(policies): enable wall x CI testing * style(test): pre-commit check * style(test): pre-commit * fix wall x for transformer v5 (#3008) * tv5 fix * various wall x fixes * Delete tests/policies/pi0_pi05/print_pi05_output_logits.py Signed-off-by: Jade Choghari <chogharijade@gmail.com> * sync modeling_florence2.py with chore/bump_transformers_v5 * more * more fixes * more * remove comment * more --------- Signed-off-by: Jade Choghari <chogharijade@gmail.com> * chore(dependencies): adjust dependencies versioning after transformers v5 (#3034) * chore(dependecies): adjust dependecies versioning after transformers v5 * fix(policies): remove deprecated input_embeds * fix(policies): dict _tied_weights_keys * chore(depedencies): common qwen-vl-utils * chore(dependencies): bump transformers to 5.2 * Fix policy testing for tv5 (#3032) * fix ci logger * other fix * fix mypy * change logits to torch2.10 * skip wallx| * remove logging --------- Co-authored-by: Steven Palma <imstevenpmwork@ieee.org> * feat(ci): log into HF to unblock some CI tests (#3007) * feat(ci): log into HF to unblock some CI tests * chore(ci): change hf call + secret name * fix(ci): temp fix for pi0 rtc test * test(policies): require_cuda for unblocked tests * test(policies): require_cuda wall_x * fic(tests): require_cuda outter most for pi0 * fix(test): return instead of yield --------- Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> * style(test): fix pre-commit * chore(deps): upgrade transformers (#3050) * chore(test): use lerobot model * fix(policies): change default action tokenizer for wall x * sample on cpu * Revert "Merge branch 'chore/bump_transformers_v5' of https://github.com/huggingface/lerobot into chore/bump_transformers_v5" This reverts commit d9b76755f7ec640cd6d52d29a7a3c09b815ef28c, reversing changes made to 89359cb0b678a6fe4867457f943d8b0b0de935f6. * Reapply "Merge branch 'chore/bump_transformers_v5' of https://github.com/huggingface/lerobot into chore/bump_transformers_v5" This reverts commit c9914db78b05653e885de15b5992b69fc701a0c2. --------- Signed-off-by: Jade Choghari <chogharijade@gmail.com> Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> Co-authored-by: Jade Choghari <chogharijade@gmail.com> Co-authored-by: Yufei Sun <skieyfly@gmail.com> Co-authored-by: Pepijn <pepijn@huggingface.co>
2026-03-05 09:25:26 +01:00
peft-dep = ["peft>=0.18.0,<1.0.0"]
scipy-dep = ["scipy>=1.14.0,<2.0.0"]
diffusers-dep = ["diffusers>=0.27.2,<0.36.0"]
chore(dependencies): bump transformers v5 (#2964) * chore(dependencies): upgrade transformers + hggingface-hub + peft + scipy * chore(dependencies): bump pi0 family to transformers v5 * chore(dependencies): bump wall x to transformers v5 * chore(dependencies): bump gr00t to transformers v5 * chore(style): fix pre-commit * fix(policy): xvla forced_bos_token missing * test(rl): skip ci tests for resnet10 * Fix: full pi models support for transformer v5 (#2967) * fix(pi): remove loss truncation * fix(pi): remove state padding before tokenization * fix(pi): fix image padding value * fix from_pretrain * add transformer v5 changes * remove reference * more fixes * make it work * add support for rest of pi family * add pifast work * more changes * more changes * more cleanup * fix torch params * dtype fix * torch compile * embed mismatch fix * revert groot * more nit fixes * remove unused classes * more fixes * revert * nit * torch dtype warning fix * but back dynamic renaming * add tie embedding --------- Co-authored-by: Yufei Sun <skieyfly@gmail.com> * chore: fix XVLA in transformers v5 (#3006) * test(policies): enable wall x CI testing * style(test): pre-commit check * style(test): pre-commit * fix wall x for transformer v5 (#3008) * tv5 fix * various wall x fixes * Delete tests/policies/pi0_pi05/print_pi05_output_logits.py Signed-off-by: Jade Choghari <chogharijade@gmail.com> * sync modeling_florence2.py with chore/bump_transformers_v5 * more * more fixes * more * remove comment * more --------- Signed-off-by: Jade Choghari <chogharijade@gmail.com> * chore(dependencies): adjust dependencies versioning after transformers v5 (#3034) * chore(dependecies): adjust dependecies versioning after transformers v5 * fix(policies): remove deprecated input_embeds * fix(policies): dict _tied_weights_keys * chore(depedencies): common qwen-vl-utils * chore(dependencies): bump transformers to 5.2 * Fix policy testing for tv5 (#3032) * fix ci logger * other fix * fix mypy * change logits to torch2.10 * skip wallx| * remove logging --------- Co-authored-by: Steven Palma <imstevenpmwork@ieee.org> * feat(ci): log into HF to unblock some CI tests (#3007) * feat(ci): log into HF to unblock some CI tests * chore(ci): change hf call + secret name * fix(ci): temp fix for pi0 rtc test * test(policies): require_cuda for unblocked tests * test(policies): require_cuda wall_x * fic(tests): require_cuda outter most for pi0 * fix(test): return instead of yield --------- Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> * style(test): fix pre-commit * chore(deps): upgrade transformers (#3050) * chore(test): use lerobot model * fix(policies): change default action tokenizer for wall x * sample on cpu * Revert "Merge branch 'chore/bump_transformers_v5' of https://github.com/huggingface/lerobot into chore/bump_transformers_v5" This reverts commit d9b76755f7ec640cd6d52d29a7a3c09b815ef28c, reversing changes made to 89359cb0b678a6fe4867457f943d8b0b0de935f6. * Reapply "Merge branch 'chore/bump_transformers_v5' of https://github.com/huggingface/lerobot into chore/bump_transformers_v5" This reverts commit c9914db78b05653e885de15b5992b69fc701a0c2. --------- Signed-off-by: Jade Choghari <chogharijade@gmail.com> Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> Co-authored-by: Jade Choghari <chogharijade@gmail.com> Co-authored-by: Yufei Sun <skieyfly@gmail.com> Co-authored-by: Pepijn <pepijn@huggingface.co>
2026-03-05 09:25:26 +01:00
qwen-vl-utils-dep = ["qwen-vl-utils>=0.0.11,<0.1.0"]
matplotlib-dep = ["matplotlib>=3.10.3,<4.0.0", "contourpy>=1.3.0,<2.0.0"] # NOTE: Explicitly listing contourpy helps the resolver converge faster.
pyserial-dep = ["pyserial>=3.5,<4.0"]
deepdiff-dep = ["deepdiff>=7.0.1,<9.0.0"]
pynput-dep = ["pynput>=1.7.8,<1.9.0"]
pyzmq-dep = ["pyzmq>=26.2.1,<28.0.0"]
feat(robots): natively integrate Seeed Studio reBot B601-DM arm (#3624) * feat(robots): natively integrate Seeed Studio reBot B601-DM arm Add first-class LeRobot support for the Seeed Studio reBot arm, replacing the out-of-tree `lerobot-robot-seeed-b601` / `lerobot-teleoperator-rebot-arm-102` plugin packages. New devices: - robot `rebot_b601_follower` — single-arm B601-DM follower (6-DOF + gripper, Damiao CAN motors via `motorbridge`) - robot `bi_rebot_b601_follower` — bimanual follower composing two single arms - teleoperator `rebot_102_leader` — single-arm StarArm102 / reBot Arm 102 leader (FashionStar UART servos via `motorbridge-smart-servo`) - teleoperator `bi_rebot_102_leader` — bimanual leader composing two single arms The bimanual variants reuse the single-arm classes and namespace each arm's observation/action keys with `left_` / `right_` prefixes, so a bimanual StarArm102 leader can teleoperate a bimanual reBot B601 follower. Optional SDK imports are guarded; a `rebot` extra installs `motorbridge` and `motorbridge-smart-servo`. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: add reBot B601-DM calibration & dual-arm teleoperation guide Add docs/source/rebot_b601.mdx covering single-arm and bimanual calibration and teleoperation for the reBot B601-DM follower and reBot Arm 102 leader, with zero-position reference images from the Seeed Studio wiki. Register the page in the docs toctree. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: fix reBot B601 MDX build (move JSON example out of <Tip>) The doc-builder parses `{...}` inside MDX component children as a Svelte expression, so the joint_directions JSON example broke the build. Move it into a top-level fenced code block. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: apply prettier formatting to reBot B601 page Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: remove duplicate colocated reBot B601 page docs/source/rebot_b601.mdx is the canonical, toctree-registered page; the colocated rebot_b601.md was a redundant thinner copy. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: clarify 6-DOF leader fallback comment in reBot B601 follower Explain that holding wrist_yaw at zero is what lets a 6-DOF leader (e.g. so100_leader / so101_leader) teleoperate the 7-DOF follower. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor: address Caroline's PR review on reBot B601 integration - leader: remove _validate_config (no other lerobot device validates its config; a key mismatch now surfaces as a plain KeyError) - leader: simplify _round_to_valid_range to direct modular arithmetic instead of a bidirectional search loop - leader: inline the single-use _clamp helper - follower & leader: write MotorCalibration range_min/range_max from the configured joint_limits / joint_ranges instead of a fixed [-90, 90] - docs: add a "Find the USB ports" section (lerobot-find-port) and move the brltty/permissions tip there; link the OpenArm page for SocketCAN adapter configuration Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-18 19:49:21 +02:00
motorbridge-dep = ["motorbridge>=0.3.2,<0.4.0"]
motorbridge-smart-servo-dep = ["motorbridge-smart-servo>=0.0.4,<0.1.0"]
# Motors
feetech = ["feetech-servo-sdk>=1.0.0,<2.0.0", "lerobot[pyserial-dep]", "lerobot[deepdiff-dep]"]
dynamixel = ["dynamixel-sdk>=3.7.31,<3.9.0", "lerobot[pyserial-dep]", "lerobot[deepdiff-dep]"]
damiao = ["lerobot[can-dep]"]
robstride = ["lerobot[can-dep]"]
# Robots
feat(robots): add OpenArm robot & teleoperator (#2795) * fix(motors): cleanup imports + fix signatures * feat(motors): add damiao canbus + multiple fixes * fix(motors): address comments -> last_state + different gains + sleep * refactor(motors): reduce duplicated code + adressed some comments in the PR * chore(motors): better timeouts * tests(motors): damiao test and imports * chore(deps): fix space * feat(robot): add openarm leader Co-authored-by: Pepijn <pepijn@huggingface.co> * feat(robot): add openarm follower Co-authored-by: Pepijn <pepijn@huggingface.co> * refactor(robot): remove mechanical compensations and double arm assumption + rename * chore(robots): remove left arm references * refactor(teleop): multiple improvements to leader * refactor(teleop): multiple improvements to leader * feat(robots): add open arm to util CLI * chore(robot): add alias openarm * Apply suggestions from code review Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com> Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> * chore(motors): remove normalization tables damiao * fix(motors): imports and signatures * feat(motors): add motor_type_str + recv_id to motor class and _get_motor_recv_id raises if no motor_obj.recv_id * chore(motors): remove normalize from base motor class and damaio * tests(motors): remove bad tests (to be replaced) * chore(motors): updated import check * fix(robots): open arm mirrored config for joint limits * chore(motors): update position_kd gain values * chore(robots): set to 0 if openarm is calibrated at connect time * chore(robots): remove macos in open arm as can doesn't support it * chore(robots): update for motor_type_str in Motor class * chore(robots): no default value for can port in open arms * use constant for kp and kd range and check responses in mit_control_batch() * Add docs on setting up canbus and use damiao otor bus, also add lerobot_setup_can.py and log if there is not response from a write command * precommit format * supress bandit as these are intentional cli commands * fix setup-can * add test * skip test in ci * nit precommit * update doc example * dont import can for tests * remove comment * Add openarms docs * format * update purchase link * can to none if nit availabl;e * add canfd option in bus * make handshake logic similar to lerobot-can * type hint * type check * add temp teleop test * remove script * mock class * ignore linter --------- Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> Co-authored-by: Pepijn <pepijn@huggingface.co> Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com>
2026-01-28 14:28:51 +01:00
openarms = ["lerobot[damiao]"]
gamepad = ["lerobot[pygame-dep]", "hidapi>=0.14.0,<0.15.0"]
hopejr = ["lerobot[feetech]", "lerobot[pygame-dep]"]
lekiwi = ["lerobot[feetech]", "lerobot[pyzmq-dep]"]
Feat/add unitree g1 robot (#2530) * add unitree_g1_robot_class * finish locomotion loading code * precommit * separate groot locomotion logic * remove leftover locomotion variable, unify kp kd * format config * properly comment config, example locomotion and unitree_g1 class * ready to review * download policy from the hub in `examples/unitree_g1/gr00t_locomotion` * fix linter * make precommit happy, add ignore flags * linter pt3 * linter pt4 * [done] make precommit happy * fix linter 5 * add docs * push utils * feat(robots): add Unitree G1 humanoid support with ZMQ bridge (#2539) * feat(robots): add Unitree G1 humanoid support with ZMQ bridge - Use JSON + base64 serialization for secure communication instead of pickle - Add documentation section - Rename robot_server to run_g1_server - Add dependecies to pyproject.toml * nit in docs * remove globals use * cast robot data to int/float * ensure robot is connected before changing mode * temperature can be list, average in such case --------- Co-authored-by: Martino Russi <nopyeps@gmail.com> * style nit * remove transform_imu_data * remove scipy dependency * modify toml, add external unitree_sdk2py dep * return actions from send_action * cleaning * add instructions for local deployment * Update src/lerobot/robots/unitree_g1/unitree_g1.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Signed-off-by: Martino Russi <77496684+nepyope@users.noreply.github.com> * update config and readme * update docs * update docs * remove torch import * fix docs * remove ip from docs * add licence header --------- Signed-off-by: Martino Russi <77496684+nepyope@users.noreply.github.com> Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-12-01 16:10:13 +01:00
unitree_g1 = [
# "unitree-sdk2==1.0.1",
"lerobot[pyzmq-dep]",
"lerobot[pyserial-dep]",
"onnxruntime>=1.16.0,<2.0.0",
"onnx>=1.16.0,<2.0.0",
"meshcat>=0.3.0,<0.4.0",
"lerobot[matplotlib-dep]",
feat(robots): Unitree G1 WBC implementation (#2876) * move locomotion from examples to robot, move controller to teleoperator class * modify teleoperate to send back actions to robot * whole body controller * add holosoma to locomotros * various updates * update joint zeroing etc * ensure safefail with locomotion * add unitree locomotion * launch camera from g1 server * publish at varying framerates * fix async read in camera * attempting to fix camera lag * test camera speedup * training * inference works * remove logging from pi0 * remove logging * push local changes * testing * final changes * revert control_utils * revert utils * revert * revert g1 * revert again: * revert utils * push recents * remove examples * remove junk * remove mjlog * revergt edit_dataset * Update lerobot_edit_dataset.py Signed-off-by: Martino Russi <77496684+nepyope@users.noreply.github.com> * undo teleop changes * revert logging * remove loggings * remove loogs * revert dataset tools * Update dataset_tools.py Signed-off-by: Martino Russi <77496684+nepyope@users.noreply.github.com> * move gravity to utils * revert changes * remove matplotlib viewer (rerun works fine) * factory revert * send policy action directly * recent changes * implement flexible action space * send empty command if arms are missing * rename locomotion to controller * add init * implement feedback * add feedback for teleoperator * fix ruff * fix ruff * use read_latest * fix zmq camera * revert exo_serial * simplify PR * revert exo_changes * revert camera_zmq * Update camera_zmq.py Signed-off-by: Martino Russi <77496684+nepyope@users.noreply.github.com> * remove frame duplication from zmq server * revert channerfactoryinitialize * keep channelfactoryinitialize * remove zeroing out logic * fix typo * refactor teleop class * simplify teleop further * import armindex at the top * fix visualizer again * revert ik helper * push stuff * simplify image_server * update image_server * asd * add threading logic * simplify ik helper stuff * simplify holosoma * fix names * fix docs * revert leg override * clean connect * fix controller * fix ruff * clean teleoperator * set_from_wireless * avoid double initializations * refactor robot class * fix pre-commit * update docs * update docs format * add teleop instructions * unitree_g1 specific exception in record/teleoperate * add thumbnail to docs * add thumbnail to doc * refactor(unitree): multiple improvements (#3103) * refactor(unitree): multiple improvements * test(unitree): added tests + improved installation instructions * refactor(robots): minor changes unitree robot kinematic * chore(robots): rename g1 kinematics file --------- Signed-off-by: Martino Russi <77496684+nepyope@users.noreply.github.com> Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> Co-authored-by: Steven Palma <imstevenpmwork@ieee.org> Co-authored-by: Steven Palma <steven.palma@huggingface.co>
2026-03-08 11:33:24 +01:00
"lerobot[pygame-dep]",
Feat/add unitree g1 robot (#2530) * add unitree_g1_robot_class * finish locomotion loading code * precommit * separate groot locomotion logic * remove leftover locomotion variable, unify kp kd * format config * properly comment config, example locomotion and unitree_g1 class * ready to review * download policy from the hub in `examples/unitree_g1/gr00t_locomotion` * fix linter * make precommit happy, add ignore flags * linter pt3 * linter pt4 * [done] make precommit happy * fix linter 5 * add docs * push utils * feat(robots): add Unitree G1 humanoid support with ZMQ bridge (#2539) * feat(robots): add Unitree G1 humanoid support with ZMQ bridge - Use JSON + base64 serialization for secure communication instead of pickle - Add documentation section - Rename robot_server to run_g1_server - Add dependecies to pyproject.toml * nit in docs * remove globals use * cast robot data to int/float * ensure robot is connected before changing mode * temperature can be list, average in such case --------- Co-authored-by: Martino Russi <nopyeps@gmail.com> * style nit * remove transform_imu_data * remove scipy dependency * modify toml, add external unitree_sdk2py dep * return actions from send_action * cleaning * add instructions for local deployment * Update src/lerobot/robots/unitree_g1/unitree_g1.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Signed-off-by: Martino Russi <77496684+nepyope@users.noreply.github.com> * update config and readme * update docs * update docs * remove torch import * fix docs * remove ip from docs * add licence header --------- Signed-off-by: Martino Russi <77496684+nepyope@users.noreply.github.com> Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-12-01 16:10:13 +01:00
]
reachy2 = ["reachy2_sdk>=1.0.15,<1.1.0"]
feat(robots): natively integrate Seeed Studio reBot B601-DM arm (#3624) * feat(robots): natively integrate Seeed Studio reBot B601-DM arm Add first-class LeRobot support for the Seeed Studio reBot arm, replacing the out-of-tree `lerobot-robot-seeed-b601` / `lerobot-teleoperator-rebot-arm-102` plugin packages. New devices: - robot `rebot_b601_follower` — single-arm B601-DM follower (6-DOF + gripper, Damiao CAN motors via `motorbridge`) - robot `bi_rebot_b601_follower` — bimanual follower composing two single arms - teleoperator `rebot_102_leader` — single-arm StarArm102 / reBot Arm 102 leader (FashionStar UART servos via `motorbridge-smart-servo`) - teleoperator `bi_rebot_102_leader` — bimanual leader composing two single arms The bimanual variants reuse the single-arm classes and namespace each arm's observation/action keys with `left_` / `right_` prefixes, so a bimanual StarArm102 leader can teleoperate a bimanual reBot B601 follower. Optional SDK imports are guarded; a `rebot` extra installs `motorbridge` and `motorbridge-smart-servo`. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: add reBot B601-DM calibration & dual-arm teleoperation guide Add docs/source/rebot_b601.mdx covering single-arm and bimanual calibration and teleoperation for the reBot B601-DM follower and reBot Arm 102 leader, with zero-position reference images from the Seeed Studio wiki. Register the page in the docs toctree. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: fix reBot B601 MDX build (move JSON example out of <Tip>) The doc-builder parses `{...}` inside MDX component children as a Svelte expression, so the joint_directions JSON example broke the build. Move it into a top-level fenced code block. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: apply prettier formatting to reBot B601 page Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: remove duplicate colocated reBot B601 page docs/source/rebot_b601.mdx is the canonical, toctree-registered page; the colocated rebot_b601.md was a redundant thinner copy. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: clarify 6-DOF leader fallback comment in reBot B601 follower Explain that holding wrist_yaw at zero is what lets a 6-DOF leader (e.g. so100_leader / so101_leader) teleoperate the 7-DOF follower. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor: address Caroline's PR review on reBot B601 integration - leader: remove _validate_config (no other lerobot device validates its config; a key mismatch now surfaces as a plain KeyError) - leader: simplify _round_to_valid_range to direct modular arithmetic instead of a bidirectional search loop - leader: inline the single-use _clamp helper - follower & leader: write MotorCalibration range_min/range_max from the configured joint_limits / joint_ranges instead of a fixed [-90, 90] - docs: add a "Find the USB ports" section (lerobot-find-port) and move the brltty/permissions tip there; link the OpenArm page for SocketCAN adapter configuration Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-18 19:49:21 +02:00
# Seeed Studio reBot B601-DM follower (motorbridge / CAN) + StarArm102 / reBot Arm 102
# leader (motorbridge-smart-servo / FashionStar UART servos).
rebot = ["lerobot[motorbridge-dep]", "lerobot[motorbridge-smart-servo-dep]"]
kinematics = ["lerobot[placo-dep]"]
intelrealsense = [
"pyrealsense2>=2.55.1.6486,<2.57.0 ; sys_platform != 'darwin'",
"pyrealsense2-macosx>=2.54,<2.57.0 ; sys_platform == 'darwin'",
]
phone = ["hebi-py>=2.8.0,<2.12.0", "teleop>=0.1.0,<0.2.0", "fastapi<1.0", "lerobot[scipy-dep]"]
# Policies
diffusion = ["lerobot[diffusers-dep]"]
wallx = [
chore(dependencies): bump transformers v5 (#2964) * chore(dependencies): upgrade transformers + hggingface-hub + peft + scipy * chore(dependencies): bump pi0 family to transformers v5 * chore(dependencies): bump wall x to transformers v5 * chore(dependencies): bump gr00t to transformers v5 * chore(style): fix pre-commit * fix(policy): xvla forced_bos_token missing * test(rl): skip ci tests for resnet10 * Fix: full pi models support for transformer v5 (#2967) * fix(pi): remove loss truncation * fix(pi): remove state padding before tokenization * fix(pi): fix image padding value * fix from_pretrain * add transformer v5 changes * remove reference * more fixes * make it work * add support for rest of pi family * add pifast work * more changes * more changes * more cleanup * fix torch params * dtype fix * torch compile * embed mismatch fix * revert groot * more nit fixes * remove unused classes * more fixes * revert * nit * torch dtype warning fix * but back dynamic renaming * add tie embedding --------- Co-authored-by: Yufei Sun <skieyfly@gmail.com> * chore: fix XVLA in transformers v5 (#3006) * test(policies): enable wall x CI testing * style(test): pre-commit check * style(test): pre-commit * fix wall x for transformer v5 (#3008) * tv5 fix * various wall x fixes * Delete tests/policies/pi0_pi05/print_pi05_output_logits.py Signed-off-by: Jade Choghari <chogharijade@gmail.com> * sync modeling_florence2.py with chore/bump_transformers_v5 * more * more fixes * more * remove comment * more --------- Signed-off-by: Jade Choghari <chogharijade@gmail.com> * chore(dependencies): adjust dependencies versioning after transformers v5 (#3034) * chore(dependecies): adjust dependecies versioning after transformers v5 * fix(policies): remove deprecated input_embeds * fix(policies): dict _tied_weights_keys * chore(depedencies): common qwen-vl-utils * chore(dependencies): bump transformers to 5.2 * Fix policy testing for tv5 (#3032) * fix ci logger * other fix * fix mypy * change logits to torch2.10 * skip wallx| * remove logging --------- Co-authored-by: Steven Palma <imstevenpmwork@ieee.org> * feat(ci): log into HF to unblock some CI tests (#3007) * feat(ci): log into HF to unblock some CI tests * chore(ci): change hf call + secret name * fix(ci): temp fix for pi0 rtc test * test(policies): require_cuda for unblocked tests * test(policies): require_cuda wall_x * fic(tests): require_cuda outter most for pi0 * fix(test): return instead of yield --------- Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> * style(test): fix pre-commit * chore(deps): upgrade transformers (#3050) * chore(test): use lerobot model * fix(policies): change default action tokenizer for wall x * sample on cpu * Revert "Merge branch 'chore/bump_transformers_v5' of https://github.com/huggingface/lerobot into chore/bump_transformers_v5" This reverts commit d9b76755f7ec640cd6d52d29a7a3c09b815ef28c, reversing changes made to 89359cb0b678a6fe4867457f943d8b0b0de935f6. * Reapply "Merge branch 'chore/bump_transformers_v5' of https://github.com/huggingface/lerobot into chore/bump_transformers_v5" This reverts commit c9914db78b05653e885de15b5992b69fc701a0c2. --------- Signed-off-by: Jade Choghari <chogharijade@gmail.com> Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> Co-authored-by: Jade Choghari <chogharijade@gmail.com> Co-authored-by: Yufei Sun <skieyfly@gmail.com> Co-authored-by: Pepijn <pepijn@huggingface.co>
2026-03-05 09:25:26 +01:00
"lerobot[transformers-dep]",
"lerobot[peft-dep]",
chore(dependencies): bump transformers v5 (#2964) * chore(dependencies): upgrade transformers + hggingface-hub + peft + scipy * chore(dependencies): bump pi0 family to transformers v5 * chore(dependencies): bump wall x to transformers v5 * chore(dependencies): bump gr00t to transformers v5 * chore(style): fix pre-commit * fix(policy): xvla forced_bos_token missing * test(rl): skip ci tests for resnet10 * Fix: full pi models support for transformer v5 (#2967) * fix(pi): remove loss truncation * fix(pi): remove state padding before tokenization * fix(pi): fix image padding value * fix from_pretrain * add transformer v5 changes * remove reference * more fixes * make it work * add support for rest of pi family * add pifast work * more changes * more changes * more cleanup * fix torch params * dtype fix * torch compile * embed mismatch fix * revert groot * more nit fixes * remove unused classes * more fixes * revert * nit * torch dtype warning fix * but back dynamic renaming * add tie embedding --------- Co-authored-by: Yufei Sun <skieyfly@gmail.com> * chore: fix XVLA in transformers v5 (#3006) * test(policies): enable wall x CI testing * style(test): pre-commit check * style(test): pre-commit * fix wall x for transformer v5 (#3008) * tv5 fix * various wall x fixes * Delete tests/policies/pi0_pi05/print_pi05_output_logits.py Signed-off-by: Jade Choghari <chogharijade@gmail.com> * sync modeling_florence2.py with chore/bump_transformers_v5 * more * more fixes * more * remove comment * more --------- Signed-off-by: Jade Choghari <chogharijade@gmail.com> * chore(dependencies): adjust dependencies versioning after transformers v5 (#3034) * chore(dependecies): adjust dependecies versioning after transformers v5 * fix(policies): remove deprecated input_embeds * fix(policies): dict _tied_weights_keys * chore(depedencies): common qwen-vl-utils * chore(dependencies): bump transformers to 5.2 * Fix policy testing for tv5 (#3032) * fix ci logger * other fix * fix mypy * change logits to torch2.10 * skip wallx| * remove logging --------- Co-authored-by: Steven Palma <imstevenpmwork@ieee.org> * feat(ci): log into HF to unblock some CI tests (#3007) * feat(ci): log into HF to unblock some CI tests * chore(ci): change hf call + secret name * fix(ci): temp fix for pi0 rtc test * test(policies): require_cuda for unblocked tests * test(policies): require_cuda wall_x * fic(tests): require_cuda outter most for pi0 * fix(test): return instead of yield --------- Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> * style(test): fix pre-commit * chore(deps): upgrade transformers (#3050) * chore(test): use lerobot model * fix(policies): change default action tokenizer for wall x * sample on cpu * Revert "Merge branch 'chore/bump_transformers_v5' of https://github.com/huggingface/lerobot into chore/bump_transformers_v5" This reverts commit d9b76755f7ec640cd6d52d29a7a3c09b815ef28c, reversing changes made to 89359cb0b678a6fe4867457f943d8b0b0de935f6. * Reapply "Merge branch 'chore/bump_transformers_v5' of https://github.com/huggingface/lerobot into chore/bump_transformers_v5" This reverts commit c9914db78b05653e885de15b5992b69fc701a0c2. --------- Signed-off-by: Jade Choghari <chogharijade@gmail.com> Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> Co-authored-by: Jade Choghari <chogharijade@gmail.com> Co-authored-by: Yufei Sun <skieyfly@gmail.com> Co-authored-by: Pepijn <pepijn@huggingface.co>
2026-03-05 09:25:26 +01:00
"lerobot[scipy-dep]",
"torchdiffeq>=0.2.4,<0.3.0",
"lerobot[qwen-vl-utils-dep]",
]
chore(dependencies): bump transformers v5 (#2964) * chore(dependencies): upgrade transformers + hggingface-hub + peft + scipy * chore(dependencies): bump pi0 family to transformers v5 * chore(dependencies): bump wall x to transformers v5 * chore(dependencies): bump gr00t to transformers v5 * chore(style): fix pre-commit * fix(policy): xvla forced_bos_token missing * test(rl): skip ci tests for resnet10 * Fix: full pi models support for transformer v5 (#2967) * fix(pi): remove loss truncation * fix(pi): remove state padding before tokenization * fix(pi): fix image padding value * fix from_pretrain * add transformer v5 changes * remove reference * more fixes * make it work * add support for rest of pi family * add pifast work * more changes * more changes * more cleanup * fix torch params * dtype fix * torch compile * embed mismatch fix * revert groot * more nit fixes * remove unused classes * more fixes * revert * nit * torch dtype warning fix * but back dynamic renaming * add tie embedding --------- Co-authored-by: Yufei Sun <skieyfly@gmail.com> * chore: fix XVLA in transformers v5 (#3006) * test(policies): enable wall x CI testing * style(test): pre-commit check * style(test): pre-commit * fix wall x for transformer v5 (#3008) * tv5 fix * various wall x fixes * Delete tests/policies/pi0_pi05/print_pi05_output_logits.py Signed-off-by: Jade Choghari <chogharijade@gmail.com> * sync modeling_florence2.py with chore/bump_transformers_v5 * more * more fixes * more * remove comment * more --------- Signed-off-by: Jade Choghari <chogharijade@gmail.com> * chore(dependencies): adjust dependencies versioning after transformers v5 (#3034) * chore(dependecies): adjust dependecies versioning after transformers v5 * fix(policies): remove deprecated input_embeds * fix(policies): dict _tied_weights_keys * chore(depedencies): common qwen-vl-utils * chore(dependencies): bump transformers to 5.2 * Fix policy testing for tv5 (#3032) * fix ci logger * other fix * fix mypy * change logits to torch2.10 * skip wallx| * remove logging --------- Co-authored-by: Steven Palma <imstevenpmwork@ieee.org> * feat(ci): log into HF to unblock some CI tests (#3007) * feat(ci): log into HF to unblock some CI tests * chore(ci): change hf call + secret name * fix(ci): temp fix for pi0 rtc test * test(policies): require_cuda for unblocked tests * test(policies): require_cuda wall_x * fic(tests): require_cuda outter most for pi0 * fix(test): return instead of yield --------- Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> * style(test): fix pre-commit * chore(deps): upgrade transformers (#3050) * chore(test): use lerobot model * fix(policies): change default action tokenizer for wall x * sample on cpu * Revert "Merge branch 'chore/bump_transformers_v5' of https://github.com/huggingface/lerobot into chore/bump_transformers_v5" This reverts commit d9b76755f7ec640cd6d52d29a7a3c09b815ef28c, reversing changes made to 89359cb0b678a6fe4867457f943d8b0b0de935f6. * Reapply "Merge branch 'chore/bump_transformers_v5' of https://github.com/huggingface/lerobot into chore/bump_transformers_v5" This reverts commit c9914db78b05653e885de15b5992b69fc701a0c2. --------- Signed-off-by: Jade Choghari <chogharijade@gmail.com> Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> Co-authored-by: Jade Choghari <chogharijade@gmail.com> Co-authored-by: Yufei Sun <skieyfly@gmail.com> Co-authored-by: Pepijn <pepijn@huggingface.co>
2026-03-05 09:25:26 +01:00
pi = ["lerobot[transformers-dep]", "lerobot[scipy-dep]"]
smolvla = ["lerobot[transformers-dep]", "num2words>=0.5.14,<0.6.0", "accelerate>=1.7.0,<2.0.0"]
multi_task_dit = ["lerobot[transformers-dep]", "lerobot[diffusers-dep]"]
groot = [
"lerobot[transformers-dep]",
"lerobot[peft-dep]",
"lerobot[diffusers-dep]",
"dm-tree>=0.1.8,<1.0.0",
"timm>=1.0.0,<1.1.0",
"decord>=0.6.0,<1.0.0; (platform_machine == 'AMD64' or platform_machine == 'x86_64')",
"ninja>=1.11.1,<2.0.0",
"flash-attn>=2.5.9,<3.0.0 ; sys_platform != 'darwin'"
]
sarm = ["lerobot[transformers-dep]", "pydantic>=2.0.0,<3.0.0", "faker>=33.0.0,<35.0.0", "lerobot[matplotlib-dep]", "lerobot[qwen-vl-utils-dep]"]
topreward = ["lerobot[transformers-dep]"]
feat(policies): Add X-VLA (#2405) * first commit * more fixes * add franka action * update testing script * add changes * update files * logits matching * add imagenet as a norm type * logits matching atol1e-2 * more eval fixes * more changes * xvla works on libero * remove seed * more refactoring * more fixes * more changes * more changes * more fixes * migrate policy revert * major pre-commit cleanup * renaming * revert to self.transformer * refactor * new changes * clean * update libero * more changes * make it work * more changes: * remove imagenet dependency * style * more * more refactor * remove proprio * add loss * more * more * add freeze/unfreeze options * add testing * upgrade transformers version * update testing * add installation * remove .sh file * fix testing * silent linter in xvlatest * fix failing test * upgrade test, fix failing * fix testing * more fixes to testing * require cuda in tests * temp check * add xvla docs * fix styling * update libero doc * remove timm dep * add different dtype support * remove timm skip * remove white lines * Enhance X-VLA finetuning documentation with optimizer details (#2537) Added detailed instructions for implementing a custom optimizer and modifying parameter retrieval for X-VLA finetuning. Signed-off-by: Jinliang Zheng <54488861+2toinf@users.noreply.github.com> * fix style * iterate on review * iterate on cpilot * revert xvla dep * free up ci * test(xvla): remove main test (#2565) * Add xvla custom optim and dtype (#2567) * add custom optim * add custom optim * add auto mode * more changes * add identity to all * add auto * release * add docs * make image smaller docs * smaller image in doc * evan smaller image doc * finalize doc --------- Signed-off-by: Jinliang Zheng <54488861+2toinf@users.noreply.github.com> Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> Co-authored-by: Jinliang Zheng <54488861+2toinf@users.noreply.github.com> Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co> Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
2025-12-03 15:29:14 +01:00
xvla = ["lerobot[transformers-dep]"]
eo1 = ["lerobot[transformers-dep]", "lerobot[qwen-vl-utils-dep]"]
RL stack refactoring (#3075) * refactor: RL stack refactoring — RLAlgorithm, RLTrainer, DataMixer, and SAC restructuring * chore: clarify torch.compile disabled note in SACAlgorithm * fix(teleop): keyboard EE teleop not registering special keys and losing intervention state Fixes #2345 Co-authored-by: jpizarrom <jpizarrom@gmail.com> * fix: remove leftover normalization calls from reward classifier predict_reward Fixes #2355 * fix: add thread synchronization to ReplayBuffer to prevent race condition between add() and sample() * refactor: update SACAlgorithm to pass action_dim to _init_critics and fix encoder reference * perf: remove redundant CPU→GPU→CPU transition move in learner * Fix: add kwargs in reward classifier __init__() * fix: include IS_INTERVENTION in complementary_info sent to learner for offline replay buffer * fix: add try/finally to control_loop to ensure image writer cleanup on exit * fix: use string key for IS_INTERVENTION in complementary_info to avoid torch.load serialization error * fix: skip tests that require grpc if not available * fix(tests): ensure tensor stats comparison accounts for reshaping in normalization tests * fix(tests): skip tests that require grpc if not available * refactor(rl): expose public API in rl/__init__ and use relative imports in sub-packages * fix(config): update vision encoder model name to lerobot/resnet10 * fix(sac): clarify torch.compile status * refactor(rl): update shutdown_event type hints from 'any' to 'Any' for consistency and clarity * refactor(sac): simplify optimizer return structure * perf(rl): use async iterators in OnlineOfflineMixer.get_iterator * refactor(sac): decouple algorithm hyperparameters from policy config * update losses names in tests * fix docstring * remove unused type alias * fix test for flat dict structure * refactor(policies): rename policies/sac → policies/gaussian_actor * refactor(rl/sac): consolidate hyperparameter ownership and clean up discrete critic * perf(observation_processor): add CUDA support for image processing * fix(rl): correctly wire HIL-SERL gripper penalty through processor pipeline (cherry picked from commit 9c2af818ff4bfef2603348e0609aa249c3ff62b1) * fix(rl): add time limit processor to environment pipeline (cherry picked from commit cd105f65cb213c4a9c9768926cc3304ca52eb5f4) * fix(rl): clarify discrete gripper action mapping in GripperVelocityToJoint for SO100 (cherry picked from commit 494f469a2b9dfb792dde6d9d79d8646ef4fcff54) * fix(rl): update neutral gripper action (cherry picked from commit 9c9064e5befe82e981286c6562194f524e16045e) * fix(rl): merge environment and action-processor info in transition processing (cherry picked from commit 30e1886b6466b8753ec41b3016c09a17dd3e960b) * fix(rl): mirror gym_manipulator in actor (cherry picked from commit d2a046dfc5b6f79df34577aa45f32403d897c0a3) * fix(rl): postprocess action in actor (cherry picked from commit c2556439e550ee3fe5bae6060c57cf227101fcaf) * fix(rl): improve action processing for discrete and continuous actions (cherry picked from commit f887ab3f6ace140c4ea6b6186c26473d785b0727) * fix(rl): enhance intervention handling in actor and learner (cherry picked from commit ef8bfffbd72e9d0951de576553f89c7c281315de) * Revert "perf(observation_processor): add CUDA support for image processing" This reverts commit 38b88c414cdc1f53ebaab3211e688fe87522b732. * refactor(rl): make algorithm a nested config so all SAC hyperparameters are JSON-addressable * refactor(rl): add make_algorithm_config function for RLAlgorithmConfig instantiation * refactor(rl): add type property to RLAlgorithmConfig for better clarity * refactor(rl): make RLAlgorithmConfig an abstract base class for better extensibility * refactor(tests): remove grpc import checks from test files for cleaner code * fix(tests): gate RL tests on the `datasets` extra * refactor: simplify docstrings for clarity and conciseness across multiple files * fix(rl): update gripper position key and handle action absence during reset * fix(rl): record pre-step observation so (obs, action, next.reward) align in gym_manipulator dataset * refactor: clean up import statements * chore: address reviewer comments * chore: improve visual stats reshaping logic and update docstring for clarity * refactor: enforce mandatory config_class and name attributes in RLAlgorithm * refactor: implement NotImplementedError for abstract methods in RLAlgorithm and DataMixer * refactor: replace build_algorithm with make_algorithm for SACAlgorithmConfig and update related tests * refactor: add require_package calls for grpcio and gym-hil in relevant modules * refactor(rl): move grpcio guards to runtime entry points * feat(rl): consolidate HIL-SERL checkpoint into HF-style components Make `RLAlgorithmConfig` and `RLAlgorithm` `HubMixin`s, add abstract `state_dict()` / `load_state_dict()` for critic ensemble, target nets and `log_alpha`, and persist them as a sibling `algorithm/` component next to `pretrained_model/`. Replace the pickled `training_state.pt` with an enriched `training_step.json` carrying `step` and `interaction_step`, so resume restores actor + critics + target nets + temperature + optimizers + RNG + counters from HF-standard files. * refactor(rl): move actor weight-sync wire format from policy to algorithm * refactor(rl): update type hints for learner and actor functions * refactor(rl): hoist grpcio guard to module top in actor/learner * chore(rl): manage import pattern in actor (#3564) * chore(rl): manage import pattern in actor * chore(rl): optional grpc imports in learner; quote grpc ServicerContext types --------- Co-authored-by: Khalil Meftah <khalil.meftah@huggingface.co> * update uv.lock * chore(doc): update doc --------- Co-authored-by: jpizarrom <jpizarrom@gmail.com> Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
2026-05-12 15:49:54 +02:00
hilserl = ["lerobot[transformers-dep]", "lerobot[dataset]", "gym-hil>=0.1.13,<0.2.0", "lerobot[grpcio-dep]", "lerobot[placo-dep]"]
# Features
async = ["lerobot[grpcio-dep]", "lerobot[matplotlib-dep]"]
chore(dependencies): bump transformers v5 (#2964) * chore(dependencies): upgrade transformers + hggingface-hub + peft + scipy * chore(dependencies): bump pi0 family to transformers v5 * chore(dependencies): bump wall x to transformers v5 * chore(dependencies): bump gr00t to transformers v5 * chore(style): fix pre-commit * fix(policy): xvla forced_bos_token missing * test(rl): skip ci tests for resnet10 * Fix: full pi models support for transformer v5 (#2967) * fix(pi): remove loss truncation * fix(pi): remove state padding before tokenization * fix(pi): fix image padding value * fix from_pretrain * add transformer v5 changes * remove reference * more fixes * make it work * add support for rest of pi family * add pifast work * more changes * more changes * more cleanup * fix torch params * dtype fix * torch compile * embed mismatch fix * revert groot * more nit fixes * remove unused classes * more fixes * revert * nit * torch dtype warning fix * but back dynamic renaming * add tie embedding --------- Co-authored-by: Yufei Sun <skieyfly@gmail.com> * chore: fix XVLA in transformers v5 (#3006) * test(policies): enable wall x CI testing * style(test): pre-commit check * style(test): pre-commit * fix wall x for transformer v5 (#3008) * tv5 fix * various wall x fixes * Delete tests/policies/pi0_pi05/print_pi05_output_logits.py Signed-off-by: Jade Choghari <chogharijade@gmail.com> * sync modeling_florence2.py with chore/bump_transformers_v5 * more * more fixes * more * remove comment * more --------- Signed-off-by: Jade Choghari <chogharijade@gmail.com> * chore(dependencies): adjust dependencies versioning after transformers v5 (#3034) * chore(dependecies): adjust dependecies versioning after transformers v5 * fix(policies): remove deprecated input_embeds * fix(policies): dict _tied_weights_keys * chore(depedencies): common qwen-vl-utils * chore(dependencies): bump transformers to 5.2 * Fix policy testing for tv5 (#3032) * fix ci logger * other fix * fix mypy * change logits to torch2.10 * skip wallx| * remove logging --------- Co-authored-by: Steven Palma <imstevenpmwork@ieee.org> * feat(ci): log into HF to unblock some CI tests (#3007) * feat(ci): log into HF to unblock some CI tests * chore(ci): change hf call + secret name * fix(ci): temp fix for pi0 rtc test * test(policies): require_cuda for unblocked tests * test(policies): require_cuda wall_x * fic(tests): require_cuda outter most for pi0 * fix(test): return instead of yield --------- Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> * style(test): fix pre-commit * chore(deps): upgrade transformers (#3050) * chore(test): use lerobot model * fix(policies): change default action tokenizer for wall x * sample on cpu * Revert "Merge branch 'chore/bump_transformers_v5' of https://github.com/huggingface/lerobot into chore/bump_transformers_v5" This reverts commit d9b76755f7ec640cd6d52d29a7a3c09b815ef28c, reversing changes made to 89359cb0b678a6fe4867457f943d8b0b0de935f6. * Reapply "Merge branch 'chore/bump_transformers_v5' of https://github.com/huggingface/lerobot into chore/bump_transformers_v5" This reverts commit c9914db78b05653e885de15b5992b69fc701a0c2. --------- Signed-off-by: Jade Choghari <chogharijade@gmail.com> Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> Co-authored-by: Jade Choghari <chogharijade@gmail.com> Co-authored-by: Yufei Sun <skieyfly@gmail.com> Co-authored-by: Pepijn <pepijn@huggingface.co>
2026-03-05 09:25:26 +01:00
peft = ["lerobot[transformers-dep]", "lerobot[peft-dep]"]
# Development
dev = ["pre-commit>=3.7.0,<5.0.0", "debugpy>=1.8.1,<1.9.0", "lerobot[grpcio-dep]", "grpcio-tools==1.73.1", "mypy>=1.19.1", "ruff>=0.14.1", "lerobot[notebook]"]
notebook = ["jupyter>=1.0.0,<2.0.0", "ipykernel>=6.0.0,<7.0.0"]
test = ["pytest>=8.1.0,<9.0.0", "pytest-timeout>=2.4.0,<3.0.0", "pytest-cov>=5.0.0,<8.0.0", "mock-serial>=0.0.1,<0.1.0 ; sys_platform != 'win32'"]
video_benchmark = ["scikit-image>=0.23.2,<0.26.0", "pandas>=2.2.2,<2.4.0"]
2024-02-28 19:11:29 +01:00
# Simulation
# NOTE: Explicitly listing scipy helps flatten the dependecy tree.
aloha = ["lerobot[dataset]", "gym-aloha>=0.1.2,<0.2.0", "lerobot[scipy-dep]"]
pusht = ["lerobot[dataset]", "gym-pusht>=0.1.5,<0.2.0", "pymunk>=6.6.0,<7.0.0"] # TODO: Fix pymunk version in gym-pusht instead
libero = ["lerobot[dataset]", "lerobot[transformers-dep]", "hf-libero>=0.1.3,<0.2.0; sys_platform == 'linux'", "lerobot[scipy-dep]"]
metaworld = ["lerobot[dataset]", "metaworld==3.0.0", "lerobot[scipy-dep]"]
feat(sim): VLABench benchmark integration (#3396) feat(sim): add VLABench benchmark integration Add VLABench as a new simulation benchmark in LeRobot, following the existing LIBERO and MetaWorld patterns. This PR wires VLABench end-to-end across environment integration, Docker setup, CI smoke evaluation, and documentation. It also fixes a number of upstream packaging and runtime issues required to make VLABench usable and reproducible in CI. What’s included Benchmark integration Add VLABench as a new simulation benchmark. Expose supported VLABench tasks through the LeRobot env interface. Follow the established LIBERO / MetaWorld factory patterns. Preserve lazy async-env metadata so env.unwrapped.metadata["render_fps"] continues to work. CI smoke evaluation Add a VLABench smoke-eval job using lerobot/smolvla_vlabench. Use the correct rename_map for the 3-camera dataset layout. Expand smoke coverage from 1 to 10 primitive tasks. Extract task descriptions after eval so metrics artifacts include per-task labels. Skip Docker Hub login when secrets are unavailable (e.g. fork PRs). Docker / install fixes Install VLABench from GitHub rather than PyPI. Use uv pip, not pip, in the base image. Fail loudly on install errors instead of masking them. Clone VLABench into the non-root user’s home directory. Use shallow editable installs for VLABench and rrt-algorithms to work around missing __init__.py issues. Pin upstream clones to exact commit SHAs for reproducibility. Add undeclared runtime dependencies required by VLABench (open3d, colorlog, scikit-learn, openai). Unpin open3d so Python 3.12 wheels resolve. Assets Support downloading VLABench assets from a Hugging Face Hub mirror via VLABENCH_ASSETS_REPO. Keep Google Drive download support as fallback. Install huggingface_hub[hf_xet] so Xet-backed assets download correctly. Validate required mesh/XML asset subtrees at build time. Patch VLABench constants to tolerate missing asset directories at import time. Runtime / env correctness Import VLABench robots and tasks explicitly so decorator-based registry population happens. Resize and normalize camera observations so they always match the declared (H, W, 3) uint8 observation space. Reinstall LeRobot editably inside the image so the new env code is actually used. Coerce agent_pos / ee_state to the expected shape. Pad actions when needed to match data.ctrl. Replace zero-padding fallback with proper dm_control IK for 7D end-effector actions. Refetch dm_control physics on each step instead of caching weakrefs. Retry unstable resets with reseeding and handle PhysicsError gracefully at step time. Dataset / policy alignment Align VLABench observations and actions with Hugging Face dataset conventions used by lerobot/vlabench_unified: convert EE position between world frame and robot-base frame at the env boundary, expose / consume Euler XYZ instead of raw quaternion layout, align gripper semantics with dataset convention (1 = open, 0 = closed). This fixes policy/env mismatches that previously caused incorrect IK targets and unstable behavior at evaluation time. Docs Add a full docs/source/vlabench.mdx page aligned with the standard benchmark template. Document task selection forms (single task, comma list, suite shortcut). Document installation, evaluation, training, and result reproduction. Point examples at lerobot/smolvla_vlabench. Add a benchmark banner image. Remove outdated / misleading references to upstream evaluation tracks. Document manual install flow instead of a broken vlabench extra. Packaging cleanup Remove the unresolvable vlabench extra from pyproject.toml. Remove the no-op VLABench processor step. Remove the obsolete env unit test that only covered the dropped gripper remap helper. Apply formatting / logging / style cleanup from review feedback. Why this is needed VLABench is not currently consumable as a normal Python dependency and requires several upstream workarounds: no PyPI release, missing package declarations, undeclared runtime deps, SSH-only submodule references, asset downloads outside normal package install flow, registry population that depends on import side effects, env outputs that do not always match declared observation shapes, task resets that can diverge under some random layouts. This PR makes the benchmark usable in LeRobot despite those constraints, and ensures CI runs are reproducible and informative. If you want a much shorter squash commit message, I’d use this: feat(sim): integrate VLABench benchmark with CI, Docker, and docs Add VLABench as a new LeRobot simulation benchmark, following the existing LIBERO / MetaWorld patterns. This includes: LeRobot env integration and task exposure, CI smoke eval with lerobot/smolvla_vlabench, Docker install and asset-download fixes, runtime fixes for registry loading, assets, camera obs, action handling, dm_control IK, and PhysicsError recovery, alignment of obs/action semantics with HF VLABench datasets, docs and packaging cleanup. The PR also incorporates review feedback, improves reproducibility by pinning upstream commits, and makes VLABench usable in CI despite upstream packaging and asset-management issues.
2026-04-21 17:54:11 +02:00
# NOTE: vlabench is NOT exposed as a `lerobot` extra. Its only distribution
# is the OpenMOSS/VLABench GitHub repo (package name `VLABench`, no PyPI
# release), so any `vlabench>=X` pip spec is unresolvable. Install it
# manually alongside MuJoCo / dm-control — see docs/source/vlabench.mdx
# for the recipe.
feat(envs): add RoboMME benchmark (#3311) * feat(envs): add RoboMME benchmark integration - RoboMME env wrapper with image/wrist_image/state observations - Docker image with Vulkan, SAPIEN, mani-skill deps - CI workflow: 1-episode smoke eval with pepijn223/smolvla_robomme - preprocess_observation: handle image/wrist_image/state keys - pyproject.toml: robomme extra Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * refactor(docker): rebase RoboMME image on huggingface/lerobot-gpu Mirror the libero/metaworld pattern: start from the nightly GPU image (which already has apt deps, uv, venv, and lerobot[all] preinstalled) and only layer on what RoboMME uniquely needs — the Vulkan libs ManiSkill/SAPIEN requires, plus the robomme extra with the gymnasium/numpy overrides. Drops 48 lines of duplicated base setup (CUDA FROM, python install, user creation, venv init, base apt deps) that the nightly image already provides. Net: 102 → 54 lines. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * docs(robomme): drop prototype-branch note and move dataset to lerobot/robomme - Remove the "Related work" block referencing the prototype branch feat/robomme-integration; the PR stands on its own. - Point all dataset references at lerobot/robomme (docs, env module docstring, RoboMMEEnvConfig docstring) — this is the canonical HF location once the dataset is mirrored. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(robomme): make docs build + fast tests green 1. Docs: add robomme to _toctree.yml under Benchmarks so doc-builder's TOC integrity check stops rejecting the new page. 2. Fast tests: robomme's mani-skill transitively pins numpy<2 which is unsatisfiable against the project's numpy>=2 base pin, so `uv sync` couldn't resolve a universal lockfile. Drop robomme as a pyproject extra entirely — it truly cannot coexist with the rest of the dep tree. The Dockerfile installs robomme directly from its git URL via `uv pip install --override`, which was already the runtime path. pyproject, docs, env docstrings, and the CI job comment all now point to the docker-only install. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * test(robomme): realign unit tests with current env API The tests were written against an earlier env layout and never updated when the wrapper was refactored, so CI's fast-test job was failing with: - KeyError: 'front_rgb' / 'wrist_rgb' — these were renamed to the lerobot-canonical 'image' / 'wrist_image' keys (matching the dataset columns and preprocess_observation's built-in fallbacks). - AssertionError: 'robomme' not in result — create_robomme_envs now returns {task_name: {task_id: env}}, not {'robomme': {...}}, so comma-separated task lists work. - ModuleNotFoundError: lerobot.envs.lazy_vec_env — LazyVectorEnv was removed; create_robomme_envs is straightforward synchronous now. Rewrite the 7 failing cases against the current API, drop the three LazyVectorEnv tests, and add a multi-task test so the new comma-separated task parsing is covered. Stub install/teardown is moved into helpers (`_install_robomme_stub` / `_uninstall_robomme_stub`) so individual tests stop repeating six boilerplate lines. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * ci: point benchmark eval checkpoints at the lerobot/ org mirrors pepijn223/smolvla_* → lerobot/smolvla_* across every benchmark job in this branch (libero, metaworld, and the per-branch benchmark). The checkpoints were mirrored into the lerobot/ org and that's the canonical location going forward. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix: integrate PR #3311 review feedback - envs: rename obs keys to pixels/image, pixels/wrist_image, agent_pos - envs: add __post_init__ for dynamic action_dim in RoboMMEEnv config - envs: remove special-case obs conversion in utils.py (no longer needed) - ci: add Docker Hub login, HF_USER_TOKEN guard, --env.task_ids=[0] - scripts: extract_task_descriptions supports multiple task_ids - docs: title to # RoboMME, add image, restructure eval section - tests: update all key assertions to match new obs naming Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * fix(docs): use correct RoboMME teaser image URL Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * ci(robomme): smoke-eval 10 tasks instead of 5 Broader coverage on the RoboMME benchmark CI job: bump the smoke eval from 5 tasks to 10 (one episode each), all drawn from ROBOMME_TASKS. Tasks now run: PickXtimes, BinFill, StopCube, MoveCube, InsertPeg, SwingXtimes, VideoUnmask, ButtonUnmask, PickHighlight, PatternLock. Updated the parse_eval_metrics.py `--task` label from the single `PickXtimes` stub to the full comma list so the metrics artifact reflects what was actually run. `parse_eval_metrics.py` already reads `overall` for multi-task runs, so no parser change is needed. Made-with: Cursor * fix(robomme): nest `pixels` as a dict so preprocess_observation picks it up `_convert_obs` was returning flat keys (`pixels/image`, `pixels/wrist_image`). `preprocess_observation()` in envs/utils.py keys off the top-level `"pixels"` entry and, not finding it, silently dropped every image from the batch. The policy then saw zero image features and raised ValueError: All image features are missing from the batch. Match the LIBERO layout: return `{"pixels": {"image": ..., "wrist_image": ...}, "agent_pos": ...}` and declare the same shape in `observation_space`. Made-with: Cursor * fix(robomme): align docs and tests with nested pixels obs layout Addresses PR #3311 review feedback: - Docs: correct observation keys to `pixels/image` / `pixels/wrist_image` (mapped to `observation.images.image` / `observation.images.wrist_image`) and drop the now-obsolete column-rename snippet. - Tests: assert `result["pixels"]["image"]` instead of flat `pixels/image`, matching the nested layout required by `preprocess_observation()`. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(envs): preserve AsyncVectorEnv metadata/unwrapped in lazy eval envs Port of #3416 onto this branch. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * ci: gate Docker Hub login on secret availability Fork PRs cannot access `secrets.DOCKERHUB_LEROBOT_{USERNAME,PASSWORD}`, which made every benchmark job fail at the login step. Gate the login on the env-var expansion of the username so the step is skipped (not failed) when secrets are absent. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(robomme): address review feedback --------- Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-20 20:21:27 +02:00
# NOTE: robomme is NOT a pyproject extra — mani-skill hard-pins numpy<2
# which conflicts with lerobot's numpy>=2 base pin, so the two trees can't
# resolve into a single env. Install it only in the RoboMME Docker image
# via `uv pip install --override` (see docker/Dockerfile.benchmark.robomme).
feat(envs): add RoboCasa365 benchmark integration (#3375) * feat(envs): add RoboCasa365 benchmark integration Add RoboCasa365 (arXiv:2603.04356) as a new simulation benchmark with 365 everyday kitchen manipulation tasks across 2,500 diverse environments. New files: - src/lerobot/envs/robocasa.py: gym.Env wrapper with deferred env creation, flat 12D action / 16D state vectors, 3-camera support - docs/source/robocasa.mdx: user-facing documentation - docker/Dockerfile.benchmark.robocasa: CI benchmark image Modified files: - src/lerobot/envs/configs.py: RoboCasaEnv config (--env.type=robocasa) - pyproject.toml: robocasa optional dependency group - docs/source/_toctree.yml: sidebar entry - .github/workflows/benchmark_tests.yml: integration test job Refs: https://arxiv.org/abs/2603.04356, https://robocasa.ai Related: huggingface/lerobot#321 * fix(docker): use uv pip to install robocasa in benchmark image The huggingface/lerobot-gpu base image uses `uv` with a venv at /lerobot/.venv — `pip` is not on PATH, so `pip install` fails with "pip: not found". Switch to `uv pip install` which installs into the existing venv. Also drop the @v1.0.0 tag pin from the robocasa git URL since the upstream repo may not have that tag; use default branch instead. * fix(robocasa): editable install + switch to lerobot/smolvla_robocasa - pip install from git omits data files like box_links_assets.json (not declared in package_data). Clone and install editable so the source tree is used at runtime. - Download only tex + fixtures_lw asset types (smoke test doesn't need objaverse/aigen objects). Pipe 'y' to auto-accept download prompt. - Switch CI policy from pepijn223/smolvla_robocasa to lerobot/smolvla_robocasa. * fix(docker): re-install lerobot editably after COPY The nightly huggingface/lerobot-gpu image predates the RoboCasaEnv registration — so `lerobot-eval --env.type=robocasa` fails at argparse with "invalid choice" even after COPY . . overlays the new source. Force an editable reinstall so the venv picks up the current configs.py. * fix(ci): add rename_map for robocasa eval (image* -> camera*) Policy lerobot/smolvla_robocasa expects observation.images.camera1/2/3, but RoboCasaEnv produces observation.images.image/image2/image3. * fix(robocasa): override RoboCasaGymEnv default split (test -> all) RoboCasaGymEnv defaults split="test", but create_env only accepts {None, "all", "pretrain", "target"}, so the out-of-the-box default crashes with ValueError. Always pass "all" when split is None. * fix(docker): also download objs_lw (lightwheel objects) for robocasa Kitchen tasks (e.g. CloseFridge) reference lightwheel object meshes like Stool022/model.xml. fixtures_lw alone isn't enough — we also need objs_lw. Still skipping objaverse/aigen to keep image size down. Made-with: Cursor * feat(robocasa): raw camera names + benchmark-group task shortcuts Align the LeRobot env with RoboCasa's native conventions so policies trained on the upstream datasets don't need a --rename_map at eval time, and expose the standard task groups as first-class --env.task values. - Preserve raw RoboCasa camera names (e.g. robot0_agentview_left) as observation.images.<name> end-to-end. Drops camera_name_mapping and DEFAULT_CAMERA_NAME_MAPPING; features/features_map are now built dynamically from the parsed camera list. - Accept benchmark-group names as --env.task: atomic_seen, composite_seen, composite_unseen, pretrain50/100/200/300. Expanded lazily via robocasa.utils.dataset_registry and auto-sets the split ("target" | "pretrain"). - Update CI smoke-eval rename_map to map raw cam names to the camera1/2/3 keys expected by lerobot/smolvla_robocasa. * docs(robocasa): single-task smolvla train+eval recipe on pepijn223/robocasa_CloseFridge - Rewrite observation section to use raw RoboCasa camera keys (observation.images.robot0_agentview_{left,right}, observation.images.robot0_eye_in_hand). - Add a "Training on a single task" section with a full smolvla training command on pepijn223/robocasa_CloseFridge, plus matching single-task eval command. - Document benchmark-group task shortcuts (atomic_seen, composite_seen, composite_unseen, pretrain50/100/200/300) as valid --env.task values. * fix(robocasa): restrict obj_registries to lightwheel by default CloseFridge (and most kitchen tasks) crashed at reset with `ValueError: Probabilities contain NaN` coming out of `sample_kitchen_object_helper`. RoboCasa's upstream default `obj_registries=("objaverse", "lightwheel")` normalizes per-registry candidate counts as probabilities; when a sampled category has zero mjcf paths in every configured registry (because the objaverse asset pack isn't on disk — ~30GB, skipped by our Docker build), the 0/0 divide yields NaNs and `rng.choice` raises. - Add `obj_registries: list[str] = ["lightwheel"]` to `RoboCasaEnv` config; thread it through `create_robocasa_envs`, `_make_env_fns`, and the gym.Env wrapper to the underlying `RoboCasaGymEnv` (which forwards to `create_env` → `robosuite.make` → kitchen env). - Default matches what `download_kitchen_assets --type objs_lw` actually ships, so the env works out of the box without a 30GB objaverse download. - Document the override (`--env.obj_registries='[objaverse,lightwheel]'`) for users who have downloaded the full asset set. * fix(docker): also download tex_generative for robocasa benchmark RoboCasa's lightwheel kitchen fixtures embed references to `generative_textures/wall/tex*.png` directly in their MuJoCo XML, so `MjModel.from_xml_string` errors out at reset time with "No such file or directory" even when the env is constructed with `generative_textures=None`. The generative textures live under a separate asset registry key (`tex_generative`) in `download_kitchen_assets`, distinct from the base `tex` pack we were already fetching. - Add `tex_generative` to the download list so the fixture XMLs resolve. - Document the remaining omissions (objaverse/aigen, ~30GB) and how the runtime side pairs this with obj_registries=["lightwheel"] to avoid sampling from categories whose assets aren't on disk. * ci(robocasa): smoke-eval 10 atomic tasks instead of 1 Broader coverage in the benchmark CI job: evaluate SmolVLA on ten fixture-centric atomic RoboCasa tasks (one episode each) instead of just CloseFridge. The tasks are all drawn from TARGET_TASKS.atomic_seen and selected to avoid object-manipulation categories that would require the objaverse/aigen asset packs (we only ship objs_lw in the Docker image, paired with obj_registries=["lightwheel"] on the runtime side). Tasks: CloseFridge, OpenCabinet, OpenDrawer, TurnOnMicrowave, TurnOffStove, CloseToasterOvenDoor, SlideDishwasherRack, TurnOnSinkFaucet, NavigateKitchen, TurnOnElectricKettle. `scripts/ci/parse_eval_metrics.py` already handles multi-task output via the `overall` key, so no parser changes needed. Bumped the metrics artifact's task label to `atomic_smoke_10` to reflect the grouping. * fix(pyproject): drop unresolvable robocasa extra robocasa's upstream setup.py hardcodes `lerobot==0.3.3` in install_requires. Exposing it as the `lerobot[robocasa]` extra made uv's dep resolver cycle: `lerobot[robocasa]` -> robocasa -> lerobot (a different version) -> unsolvable. This broke every `uv sync` — even invocations with an unrelated extra like `--extra test` — because uv validates the whole lockfile graph. - Remove the `robocasa` extra from pyproject.toml. Installation instructions in docs/source/robocasa.mdx now walk users through the manual `git clone` + `pip install --no-deps` flow, which matches what the Docker image already does and sidesteps the cyclic dep entirely. - Dockerfile: `uv pip install -e ~/robocasa --no-deps` so the shadowed lerobot==0.3.3 never lands in the image; install robocasa's actual runtime deps (numpy, numba, scipy, mujoco, tianshou, etc.) explicitly. * docs(robocasa): align page with adding_benchmarks template Rework docs/source/robocasa.mdx to follow the standard benchmark doc structure: intro + links + available tasks (with family breakdown and first-class benchmark-group shortcuts) + installation + eval + recommended episodes + policy I/O + training + reproducing results. - Fix the paper link (was pointing at a non-existent arxiv ID). - Surface lerobot/smolvla_robocasa and pepijn223/robocasa_CloseFridge in the top-of-page links so they're findable without reading the training section. - Add an explicit "Object registries" subsection explaining the `--env.obj_registries=[objaverse,lightwheel]` override path. - Add an explicit "Reproducing published results" section pointing at the CI smoke eval. * fix: integrate PR #3375 review feedback - envs(robocasa): hoist the duplicated `_parse_camera_names` helper out of `libero.py` and `robocasa.py` into `envs/utils.py` as the public `parse_camera_names`; call sites updated. - envs(robocasa): give each factory a distinct `episode_index` (`0..n_envs-1`) and derive a per-worker seed series in `reset()` so n_envs workers don't all roll the same scene under a shared outer seed. - envs(robocasa): drop the unused `**kwargs` on `_make_env`; declare `visualization_height` / `visualization_width` on both the wrapper and the `RoboCasaEnv` config + propagate via `gym_kwargs`. - envs(robocasa): emit `info["final_info"]` on termination (matching MetaWorld) so downstream vector-env auto-reset keeps the terminal task/success flags. - docs(robocasa): add `--rename_map` (robot0_agentview_left/ eye_in_hand/agentview_right → camera1/2/3) plus CI-parity flags to all three eval snippets. - docker(robocasa): pin robocasa + robosuite git SHAs and the pip dep versions (pygame, Pillow, opencv-python, pyyaml, pynput, tqdm, termcolor, imageio, h5py, lxml, hidapi, gymnasium) for reproducible benchmark images. - ci(robocasa): update the workflow comment — there is no `lerobot[robocasa]` extra; robocasa/robosuite are installed manually because upstream's `lerobot==0.3.3` pin shadows ours. * docs(robocasa): add benchmark banner image * fix(envs): preserve AsyncVectorEnv metadata/unwrapped in lazy eval envs Port of #3416 onto this branch. Also threads the cached metadata through the RoboCasa factory so async eval on `--env.type=robocasa` keeps the same improvement. * fix: integrate PR #3375 review feedback (round 2) - envs(robocasa): when the caller passes `seed=None` to `reset()`, fall back to `self.episode_index` for the inner env seed so each worker still samples a distinct trajectory instead of all workers inheriting the same global RNG state. - envs(robocasa): replace the two module-level `print()` calls in `create_robocasa_envs` with `logger.info(...)` via a module-level `logger = logging.getLogger(__name__)`. - ci(robocasa): run `scripts/ci/extract_task_descriptions.py` after the eval so `metrics.json` carries per-task natural-language labels, matching LIBERO / MetaWorld / VLABench jobs. Added a `_robocasa_descriptions()` extractor that splits CamelCase task names into word-level labels keyed by `<task>_0`.
2026-04-20 17:10:53 +02:00
# NOTE: robocasa is NOT exposed as a `lerobot` extra. Its setup.py pins
# `lerobot==0.3.3` in install_requires, which cyclically shadows our own
# workspace `lerobot` and makes the graph unsolvable under any resolver
# (uv, pip). Install it manually alongside robosuite — see
# docs/source/robocasa.mdx for the recipe.
# All
all = [
# Feature-scoped extras
"lerobot[dataset]",
"lerobot[training]",
"lerobot[hardware]",
"lerobot[viz]",
# NOTE(resolver hint): scipy is pulled in transitively via lerobot[scipy-dep] through
# multiple extras (aloha, metaworld, pi, wallx, phone). Listing it explicitly
# helps pip's resolver converge by constraining scipy early, before it encounters
# the loose scipy requirements from transitive deps like dm-control and metaworld.
"scipy>=1.14.0,<2.0.0",
"lerobot[dynamixel]",
"lerobot[feetech]",
"lerobot[damiao]",
"lerobot[robstride]",
"lerobot[gamepad]",
"lerobot[hopejr]",
"lerobot[lekiwi]",
"lerobot[openarms]",
2 add reachy 2 to updated lerobot (#1767) * Start adding Reachy 2 (no camera) * Fix joint shape * Remove print * Modify observation_features * Fix observation state * Try adding a fake Reachy teleoperator * Saving test scripts * Add reachy2camera to cameras * Add teleop_left camera to observation * Create test_reachy2_camera.py * Update utils.py * Add all rgb cameras * Future depth work * Try adding mobile_base velocity * Update tests * Update data_acquisition_server.py * Update with use_external_commands * Replay * Usable with or without mobile base * No need for new isntance * Use same ip for cameras * Remove useless imports * Add resume * Divide joints in multiple dicts * Divide joinits into several dicts in teleoperator * Fix forgotten method call * Create test_robot_client.py * Open gripper on start * Add arguments for cameras * Modify get_frame() requested size * Call generate_joints_dict on _init_ * black + isort * Add reachy2 in imports * Add reachy2 dependencies * Add documentation * Update reachy2.mdx * Update reachy2.mdx * Clean files and add types * Fix type in send_action * Remove print * Delete test files * Clean code * Update cameras * Disconnect from camera * Run pre-commit hooks * Update pyproject.toml * Create test_reachy2.py * Fix generate_joints * Update test_reachy2.py * Update send_action test * Update reachy2_cameras depth + CameraManager * Update reachy2_camera tests * Remove useless import and args * Rename reachy2_teleoperator * Create test_reachy2_teleoperator.py * Fix remainging fake_teleoperator * Remove useless elements * Mock cameras in test_reachy2 * Delete commented lines * Add use_present_position to teleoperator * Add cameras tests * Add check no part + test * Use disable_torque_on_disconnect * Use odometry for vel with present_position * Update documentation * Fix vel value type * Use ensure_safe_goal_position * Import joints dict from classes * Update reachy2.mdx * Update reachy2.mdx * Update minimal version * Update minimal version * fix(tests) fixes for reachy2 tests; removing reachy2 references from the script * Add reachy2_sdk fake as plugins --------- Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co>
2025-09-05 11:03:14 +02:00
"lerobot[reachy2]",
feat(robots): natively integrate Seeed Studio reBot B601-DM arm (#3624) * feat(robots): natively integrate Seeed Studio reBot B601-DM arm Add first-class LeRobot support for the Seeed Studio reBot arm, replacing the out-of-tree `lerobot-robot-seeed-b601` / `lerobot-teleoperator-rebot-arm-102` plugin packages. New devices: - robot `rebot_b601_follower` — single-arm B601-DM follower (6-DOF + gripper, Damiao CAN motors via `motorbridge`) - robot `bi_rebot_b601_follower` — bimanual follower composing two single arms - teleoperator `rebot_102_leader` — single-arm StarArm102 / reBot Arm 102 leader (FashionStar UART servos via `motorbridge-smart-servo`) - teleoperator `bi_rebot_102_leader` — bimanual leader composing two single arms The bimanual variants reuse the single-arm classes and namespace each arm's observation/action keys with `left_` / `right_` prefixes, so a bimanual StarArm102 leader can teleoperate a bimanual reBot B601 follower. Optional SDK imports are guarded; a `rebot` extra installs `motorbridge` and `motorbridge-smart-servo`. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: add reBot B601-DM calibration & dual-arm teleoperation guide Add docs/source/rebot_b601.mdx covering single-arm and bimanual calibration and teleoperation for the reBot B601-DM follower and reBot Arm 102 leader, with zero-position reference images from the Seeed Studio wiki. Register the page in the docs toctree. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: fix reBot B601 MDX build (move JSON example out of <Tip>) The doc-builder parses `{...}` inside MDX component children as a Svelte expression, so the joint_directions JSON example broke the build. Move it into a top-level fenced code block. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: apply prettier formatting to reBot B601 page Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: remove duplicate colocated reBot B601 page docs/source/rebot_b601.mdx is the canonical, toctree-registered page; the colocated rebot_b601.md was a redundant thinner copy. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs: clarify 6-DOF leader fallback comment in reBot B601 follower Explain that holding wrist_yaw at zero is what lets a 6-DOF leader (e.g. so100_leader / so101_leader) teleoperate the 7-DOF follower. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * refactor: address Caroline's PR review on reBot B601 integration - leader: remove _validate_config (no other lerobot device validates its config; a key mismatch now surfaces as a plain KeyError) - leader: simplify _round_to_valid_range to direct modular arithmetic instead of a bidirectional search loop - leader: inline the single-use _clamp helper - follower & leader: write MotorCalibration range_min/range_max from the configured joint_limits / joint_ranges instead of a fixed [-90, 90] - docs: add a "Find the USB ports" section (lerobot-find-port) and move the brltty/permissions tip there; link the OpenArm page for SocketCAN adapter configuration Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-18 19:49:21 +02:00
"lerobot[rebot]",
"lerobot[kinematics]",
"lerobot[intelrealsense]",
"lerobot[diffusion]",
"lerobot[multi_task_dit]",
chore(dependencies): bump transformers v5 (#2964) * chore(dependencies): upgrade transformers + hggingface-hub + peft + scipy * chore(dependencies): bump pi0 family to transformers v5 * chore(dependencies): bump wall x to transformers v5 * chore(dependencies): bump gr00t to transformers v5 * chore(style): fix pre-commit * fix(policy): xvla forced_bos_token missing * test(rl): skip ci tests for resnet10 * Fix: full pi models support for transformer v5 (#2967) * fix(pi): remove loss truncation * fix(pi): remove state padding before tokenization * fix(pi): fix image padding value * fix from_pretrain * add transformer v5 changes * remove reference * more fixes * make it work * add support for rest of pi family * add pifast work * more changes * more changes * more cleanup * fix torch params * dtype fix * torch compile * embed mismatch fix * revert groot * more nit fixes * remove unused classes * more fixes * revert * nit * torch dtype warning fix * but back dynamic renaming * add tie embedding --------- Co-authored-by: Yufei Sun <skieyfly@gmail.com> * chore: fix XVLA in transformers v5 (#3006) * test(policies): enable wall x CI testing * style(test): pre-commit check * style(test): pre-commit * fix wall x for transformer v5 (#3008) * tv5 fix * various wall x fixes * Delete tests/policies/pi0_pi05/print_pi05_output_logits.py Signed-off-by: Jade Choghari <chogharijade@gmail.com> * sync modeling_florence2.py with chore/bump_transformers_v5 * more * more fixes * more * remove comment * more --------- Signed-off-by: Jade Choghari <chogharijade@gmail.com> * chore(dependencies): adjust dependencies versioning after transformers v5 (#3034) * chore(dependecies): adjust dependecies versioning after transformers v5 * fix(policies): remove deprecated input_embeds * fix(policies): dict _tied_weights_keys * chore(depedencies): common qwen-vl-utils * chore(dependencies): bump transformers to 5.2 * Fix policy testing for tv5 (#3032) * fix ci logger * other fix * fix mypy * change logits to torch2.10 * skip wallx| * remove logging --------- Co-authored-by: Steven Palma <imstevenpmwork@ieee.org> * feat(ci): log into HF to unblock some CI tests (#3007) * feat(ci): log into HF to unblock some CI tests * chore(ci): change hf call + secret name * fix(ci): temp fix for pi0 rtc test * test(policies): require_cuda for unblocked tests * test(policies): require_cuda wall_x * fic(tests): require_cuda outter most for pi0 * fix(test): return instead of yield --------- Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> * style(test): fix pre-commit * chore(deps): upgrade transformers (#3050) * chore(test): use lerobot model * fix(policies): change default action tokenizer for wall x * sample on cpu * Revert "Merge branch 'chore/bump_transformers_v5' of https://github.com/huggingface/lerobot into chore/bump_transformers_v5" This reverts commit d9b76755f7ec640cd6d52d29a7a3c09b815ef28c, reversing changes made to 89359cb0b678a6fe4867457f943d8b0b0de935f6. * Reapply "Merge branch 'chore/bump_transformers_v5' of https://github.com/huggingface/lerobot into chore/bump_transformers_v5" This reverts commit c9914db78b05653e885de15b5992b69fc701a0c2. --------- Signed-off-by: Jade Choghari <chogharijade@gmail.com> Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> Co-authored-by: Jade Choghari <chogharijade@gmail.com> Co-authored-by: Yufei Sun <skieyfly@gmail.com> Co-authored-by: Pepijn <pepijn@huggingface.co>
2026-03-05 09:25:26 +01:00
"lerobot[wallx]",
"lerobot[pi]",
"lerobot[smolvla]",
# "lerobot[groot]", TODO(Steven): Gr00t requires specific installation instructions for flash-attn
feat(policies): Add X-VLA (#2405) * first commit * more fixes * add franka action * update testing script * add changes * update files * logits matching * add imagenet as a norm type * logits matching atol1e-2 * more eval fixes * more changes * xvla works on libero * remove seed * more refactoring * more fixes * more changes * more changes * more fixes * migrate policy revert * major pre-commit cleanup * renaming * revert to self.transformer * refactor * new changes * clean * update libero * more changes * make it work * more changes: * remove imagenet dependency * style * more * more refactor * remove proprio * add loss * more * more * add freeze/unfreeze options * add testing * upgrade transformers version * update testing * add installation * remove .sh file * fix testing * silent linter in xvlatest * fix failing test * upgrade test, fix failing * fix testing * more fixes to testing * require cuda in tests * temp check * add xvla docs * fix styling * update libero doc * remove timm dep * add different dtype support * remove timm skip * remove white lines * Enhance X-VLA finetuning documentation with optimizer details (#2537) Added detailed instructions for implementing a custom optimizer and modifying parameter retrieval for X-VLA finetuning. Signed-off-by: Jinliang Zheng <54488861+2toinf@users.noreply.github.com> * fix style * iterate on review * iterate on cpilot * revert xvla dep * free up ci * test(xvla): remove main test (#2565) * Add xvla custom optim and dtype (#2567) * add custom optim * add custom optim * add auto mode * more changes * add identity to all * add auto * release * add docs * make image smaller docs * smaller image in doc * evan smaller image doc * finalize doc --------- Signed-off-by: Jinliang Zheng <54488861+2toinf@users.noreply.github.com> Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> Co-authored-by: Jinliang Zheng <54488861+2toinf@users.noreply.github.com> Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co> Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
2025-12-03 15:29:14 +01:00
"lerobot[xvla]",
"lerobot[hilserl]",
"lerobot[async]",
"lerobot[dev]",
"lerobot[test]",
"lerobot[video_benchmark]",
"lerobot[aloha]",
"lerobot[pusht]",
feat(processors): use pipelines across the codebase (#1452) * Refactor observation preprocessing to use a modular pipeline system - Introduced `RobotPipeline` and `ObservationProcessor` for handling observation transformations. - Updated `preprocess_observation` to maintain backward compatibility while leveraging the new pipeline. - Added tests for the new processing components and ensured they match the original functionality. - Removed hardcoded logic in favor of a more flexible, composable architecture. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Refactor observation processing and improve modularity - Updated `ObservationProcessor` to enhance the modular design for processing observations. - Cleaned up imports and improved code readability by removing unnecessary lines and comments. - Ensured backward compatibility while integrating new processing components. - Added tests to validate the functionality of the updated processing architecture. * Remove redundant tests for None observation and serialization methods in `test_observation_processor.py` to streamline the test suite and improve maintainability. * Refactor processing architecture to use RobotProcessor - Replaced instances of RobotPipeline with RobotProcessor across the codebase for improved modularity and clarity. - Introduced ProcessorStepRegistry for better management of processing steps. - Updated relevant documentation and tests to reflect the new processing structure. - Enhanced the save/load functionality to support the new processor design. - Added a model card template for RobotProcessor to facilitate sharing and documentation. * Add RobotProcessor tutorial to documentation - Introduced a new tutorial on using RobotProcessor for preprocessing robot data. - Added a section in the table of contents for easy navigation to the new tutorial. - The tutorial covers key concepts, real-world scenarios, and practical examples for effective use of the RobotProcessor pipeline. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Add normalization processor and related components - Introduced `NormalizationProcessor` to handle both observation normalization and action unnormalization. - Added `ObservationNormalizer` and `ActionUnnormalizer` classes for specific normalization tasks. - Updated `__init__.py` to include the new `NormalizationProcessor` in the module exports. - Enhanced `ObservationProcessor` with registration in the `ProcessorStepRegistry` for better modularity. - Created `RenameProcessor` for renaming keys in observations, improving flexibility in data processing. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Enhance processing architecture with new components - Added `RenameProcessor` to facilitate key renaming in observations, improving data handling flexibility. - Updated `__init__.py` to include `RenameProcessor` in module exports. - Refactored `NormalizationProcessor` and `ObservationNormalizer` to use `rsplit` for better key handling. - Introduced comprehensive tests for `NormalizationProcessor` and `RenameProcessor` to ensure functionality and robustness. * chore (docs): add docstring for processor * fix (test): test factory * fix(test): policies * Update tests/processor/test_observation_processor.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Signed-off-by: Adil Zouitine <adilzouitinegm@gmail.com> * chore(test): add suggestion made by copilot regarding numpy test * fix(test): import issue * Refactor normalization components and update tests - Renamed `ObservationNormalizer` to `NormalizerProcessor` and `ActionUnnormalizer` to `UnnormalizerProcessor` for clarity. - Consolidated normalization logic for both observations and actions into `NormalizerProcessor` and `UnnormalizerProcessor`. - Updated tests to reflect the new class names and ensure proper functionality of normalization and unnormalization processes. - Enhanced handling of missing statistics in normalization processes. * chore (docstrin):Improve docstring for NormalizerProcessor * feat (device processor): Implement device processor * chore (batch handling): Enhance processing components with batch conversion utilities * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix(test): linting issue * chore (output format): improves output format * chore (type): add typing for multiprocess envs * feat (overrides): Implement support for loading processors with parameter overrides - Added the ability to provide non-serializable objects when loading processors from saved configurations using the `overrides` parameter. - Enhanced error handling for invalid override keys and instantiation errors. - Updated documentation and examples to illustrate the usage of overrides for both registered and unregistered steps. - Added comprehensive tests to validate the new functionality and ensure backward compatibility. * chore(normalization): addressing comments from copilot * chore(learner): nit comment from copilot * feat(pipeline): Enhance step_through method to support both tuple and dict inputs * refactor(pipeline): Simplify observation and padding data handling in batch transitions * Apply suggestions from code review Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com> Signed-off-by: Adil Zouitine <adilzouitinegm@gmail.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * refactor(pipeline): Introduce ComplementaryDataProcessor for handling complementary data in transitions * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * refactor(pipeline): Transition from tuple to dictionary format for EnvTransition - Updated the EnvTransition structure to use a dictionary format instead of a tuple, enhancing readability and maintainability. - Replaced instances of TransitionIndex with TransitionKey for accessing transition components. - Adjusted related processing functions and tests to accommodate the new dictionary format, ensuring consistent handling of transitions across the codebase. * refactor(observation_processor): Improve observation processing by using constants and simplifying pixel handling - Introduced constants for observation keys to enhance readability. - Streamlined the handling of the "pixels" key by copying observations first and processing images more clearly. - Updated the environment state and agent position assignments to use the new constants, improving maintainability. * feat(pipeline): Add hook unregistration functionality and enhance documentation - Implemented methods to unregister before, after, and reset hooks in the RobotProcessor class, allowing for more flexible hook management. - Enhanced documentation to clarify hook execution semantics and the implications of modifying transitions within hooks. - Added comprehensive tests to verify the correct behavior of hook registration and unregistration, including error handling for non-existent hooks. * refactor(pipeline): Clarify hook behavior and improve documentation - Updated the RobotProcessor class to ensure hooks are strictly for observation and do not modify transitions, enhancing clarity and maintainability. - Refactored hook registration methods to reflect the new behavior, ensuring they accept only functions that do not return modified transitions. - Enhanced documentation to clearly outline the purpose of hooks and their execution semantics. - Added tests to verify that hooks are not executed during the step_through method while ensuring they function correctly during the __call__ method. * feat(pipeline): Add __repr__ method to RobotProcessor for improved readability - Implemented a __repr__ method in the RobotProcessor class to provide a clear string representation of the processor, including step names and optional parameters like name and seed. - Added comprehensive tests to validate the __repr__ output for various scenarios, including empty processors, single and multiple steps, custom names, and seed values. - Ensured that the representation handles long lists of steps with truncation for better readability. * chore(pipeline): Move _CFG_NAME along other class member * refactor(pipeline): Utilize get_safe_torch_device for device assignment - Replaced direct torch.device instantiation with get_safe_torch_device to ensure safe device handling. - This change enhances code readability and maintains consistency in device management across the RobotProcessor class. * refactor(pipeline): Enhance state filename generation and profiling method - Updated state filename generation to use the registry name when available, improving clarity in saved files. - Modified the profile_steps method to include a warmup_runs parameter, allowing for more controlled performance profiling. - Ensured consistent conditions during profiling by deep copying transitions for each run, enhancing accuracy in timing results. * chore(doc): address pip install commant lerobot that not exist yet * feat(pipeline): Enhance configuration filename handling and state file naming - Introduced support for custom configuration filenames in the `save_pretrained` method, allowing users to specify a filename instead of the default. - Improved state file naming to include step indices, preventing conflicts when multiple processors of the same type are saved. - Added automatic detection for configuration files when loading from a directory, with error handling for multiple files. - Updated tests to validate new features, including custom filenames and automatic config detection. * refactor(pipeline): Improve state file naming conventions for clarity and uniqueness - Enhanced state file naming to include the processor's sanitized name, ensuring uniqueness when multiple processors are saved in the same directory. - Updated tests to reflect changes in state file naming, verifying that filenames now include the processor name and step indices to prevent conflicts. - Added a new test to validate state file naming when using multiple processors, ensuring distinct filenames for each processor's state files. * docs(pipeline): Add clarification for repo name sanitization process * Feat/pipeline add feature contract (#1637) * Add feature contract to pipelinestep and pipeline * Add tests * Add processor tests * PR feedback * encorperate pr feedback * type in doc * oops * docs(pipeline): Clarify transition handling and hook behavior - Updated documentation to specify that hooks always receive transitions in EnvTransition format, ensuring consistent behavior across input formats. - Refactored the step_through method to yield only EnvTransition objects, regardless of the input format, and updated related tests to reflect this change. - Enhanced test assertions to verify the structure of results and the correctness of processing steps. * refactor(pipeline): Remove to() method for device management - Eliminated the to() method from RobotProcessor, which was responsible for moving tensor states to specified devices. - Removed associated unit tests that validated the functionality of the to() method across various scenarios. - Streamlined the pipeline code by focusing on other device management strategies. * refactor(pipeline): Remove model card generation and streamline processor methods - Eliminated the _generate_model_card method from RobotProcessor, which was responsible for generating README.md files from a template. - Updated save_pretrained method to remove model card generation, focusing on serialization of processor definitions and parameters. - Added default implementations for get_config, state_dict, load_state_dict, reset, and feature_contract methods in various processor classes to enhance consistency and usability. * refactor(observation): Streamline observation preprocessing and remove unused processor methods - Updated the `preprocess_observation` function to enhance image handling and ensure proper tensor formatting. - Removed the `RobotProcessor` and associated transition handling from the `rollout` function, simplifying the observation processing flow. - Integrated direct calls to `preprocess_observation` for improved clarity and efficiency in the evaluation script. * refactor(pipeline): Rename parameters for clarity and enhance save/load functionality - Updated parameter names in the save_pretrained and from_pretrained methods for improved readability, changing destination_path to save_directory and source to pretrained_model_name_or_path. - Enhanced the save_pretrained method to ensure directory creation and file handling is consistent with the new parameter names. - Streamlined the loading process in from_pretrained to utilize loaded_config for better clarity and maintainability. * refactor(pipeline): minor improvements (#1684) * chore(pipeline): remove unused features + device torch + envtransition keys * refactor(pipeline): ImageProcessor & StateProcessor are both implemented directly in VanillaObservationPRocessor * refactor(pipeline): RenameProcessor now inherits from ObservationProcessor + remove unused code * test(pipeline): fix broken test after refactors * docs(pipeline): update docstrings VanillaObservationProcessor * chore(pipeline): move None check to base pipeline classes * feat(processors): Introduce processors for various policy types - Added `make_processor` function to create processor instances for different policy types, including `tdmpc`, `diffusion`, `act`, `vqbet`, `pi0`, `pi0fast`, `sac`, and `reward_classifier`. - Implemented corresponding processor files for each policy type, encapsulating normalization and unnormalization steps. - Updated existing policies to remove direct normalization dependencies, enhancing modularity and clarity. - Enhanced test coverage to validate the integration of new processors with existing policy configurations. * refactor(learner): Remove normalization from cached image features retrieval - Simplified the retrieval of observation features by removing the normalization step from the `get_cached_image_features` method calls. - This change enhances clarity and aligns with the recent updates to policy processors. * refactor(policies): Remove unnormalization step from action predictions - Eliminated the unnormalization of actions in both `TDMPCPolicy` and `VQBeTPolicy` classes to streamline action prediction. - This change improves code clarity and aligns with recent updates to policy processors. * feat(train): Integrate preprocessor into training pipeline * refactor(train): Update preprocessor initialization to include dataset statistics * refactor(policies): Enhance processor creation and add NaN detection hook * feat(record): Integrate RobotProcessor into recording loop and update policy handling - Added support for RobotProcessor in the record_loop function to enhance data processing capabilities. - Updated the logic to reset both policy and processor when provided, ensuring proper state management. - Modified action prediction to utilize the processor, improving the overall functionality of the recording process. - Adjusted the save_checkpoint function to include preprocessor state saving, enhancing checkpointing capabilities. * feat(migration): Add script for migrating policy models with normalization layers * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * feat(migrate): Enhance migration script to create preprocessor and postprocessor for policy models - Updated the migration script to generate both a preprocessor and a postprocessor, improving the handling of normalization for training and inference. - Added functionality to convert features to PolicyFeature objects, ensuring compatibility with the new processor architecture. - Refined the extraction and removal of normalization statistics and layers, streamlining the migration process. - Improved error handling for missing mandatory configuration fields during model instantiation. * feat(migrate): Add model card generation and saving to migration script - Implemented functionality to generate and save a model card for the migrated model, including metadata such as dataset repository ID, license, and tags. - Enhanced the script to push the model card to the hub if requested, improving model documentation and accessibility. - Refactored the saving process to ensure the model card is saved locally and uploaded correctly when pushing to the hub. * feat(processor): Introduce ToBatchProcessor for handling observation batching - Added ToBatchProcessor to ensure observations have proper batch dimensions for model processing. - Implemented functionality to add batch dimensions to state and image observations as needed. - Created comprehensive unit tests to validate the processor's behavior with various tensor dimensions and types. - Ensured compatibility with existing transition keys and maintained the integrity of non-observation data. * feat(processors): Add ToBatchProcessor to multiple policy processors - Integrated ToBatchProcessor into various policy processors to handle observation batching. - Updated make functions for act, diffusion, pi0, pi0fast, sac, smolvla, tdmpc, and vqbet processors to include the new batching functionality. - Ensured consistency across all processor implementations for improved data handling. * refactor(factory): Remove unused imports and NaN detection hook from processor creation * feat(batch_processor): Enhance ToBatchProcessor to handle action batching - Updated ToBatchProcessor to add batch dimensions to actions in addition to observations. - Implemented separate methods for processing observations and actions, improving code readability. - Added comprehensive unit tests to validate action batching functionality across various tensor dimensions and types. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * feat(factory): Enhance make_processor to support preprocessor and postprocessor configuration - Introduced ProcessorConfigKwargs TypedDict for better type safety in processor configuration. - Updated make_processor to accept preprocessor and postprocessor configuration filenames, improving flexibility in processor instantiation. - Refactored the loading of pretrained processors to utilize the new configuration options. * refactor(factory): Clean up imports in factory.py - Removed unused import of IdentityProcessor to streamline the code. * feat(migrate): Extend load_model_from_hub to include train configuration - Updated load_model_from_hub to return the train configuration alongside the model state_dict and config. - Modified main function to handle the additional train configuration when loading models from both the hub and local paths. - Adjusted dataset_repo_id extraction to utilize the train configuration for improved accuracy. * refactor(record): Rename processor parameters and update processing logic - Renamed `processor` to `preprocessor` and added `postprocessor` parameter for clarity. - Updated the `record_loop` and `predict_action` functions to utilize the new preprocessor and postprocessor, enhancing the processing flow. - Ensured compatibility with existing functionality while improving code readability. * feat(batch_processor): Add task field processing to ToBatchProcessor - Enhanced ToBatchProcessor to wrap string tasks in a list, adding batch dimensions for compatibility with model inference. - Implemented a new method for processing complementary data, ensuring that task values are correctly handled as either strings or lists of strings. - Added comprehensive unit tests to validate task processing, including edge cases and in-place mutation of complementary data. * feat(normalization): Implement IDENTITY mode for normalization and unnormalization - Enhanced NormalizerProcessor and UnnormalizerProcessor to support IDENTITY mode, allowing features to bypass normalization when specified. - Updated processing logic to check normalization modes and handle missing statistics gracefully. - Added comprehensive unit tests to validate IDENTITY mode functionality for both observations and actions, ensuring correct behavior across various scenarios. - Improved error handling for unsupported normalization modes. * fix(rebase): remove residual normalization layer: * refactor(diffusion): remove normalization layer from input processing * refactor(normalization): Remove unused state dict transformation methods and streamline imports - Eliminated the _transform_state_dict_keys and _load_as_safetensor methods from PI0Policy, simplifying the model loading process. - Cleaned up imports in modeling_pi0.py by removing log_model_loading_keys and init_logging. - Updated TDMPCPolicy and VQBeTPolicy to handle action removal from batches during offline evaluation. - Introduced hotswap_stats function in normalize_processor.py to update normalization statistics dynamically, with corresponding tests to ensure functionality. * refactor(normalization): Clean up imports in normalize_processor.py * feat(batch_processor): Add feature_contract method to ToBatchProcessor - Introduced feature_contract method that returns features without modification, maintaining the no-op behavior of the processor. - This addition enhances the flexibility of the ToBatchProcessor for future feature processing needs. * fix(dependencies): Update transformers dependency constraint to allow only versions up to 4.52.0 * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * feature(pipeline): port tokenizer pipeline for VLA (#1645) * feat(tokenizer): Introduce TokenizerProcessor for text tokenization - Added TokenizerProcessor class to handle tokenization of task strings using Hugging Face's AutoTokenizer. - Supports both string and list inputs, with customizable parameters for task key, output key, and tokenization settings. - Implemented comprehensive unit tests to validate functionality, including handling of various input scenarios and integration with RobotProcessor. - Updated types.py to include LANGUAGE feature type and modified __init__.py to register the new processor. * feat(language): Enhance language processing in TokenizerProcessor - Added OBS_LANGUAGE constant to define the observation language key. - Updated TokenizerProcessor to store tokenized task data in the observation dictionary, ensuring compatibility with the new language feature. - Introduced Pi0NewLineProcessor to append newlines to tasks for proper tokenization. - Modified tests to validate the integration of language tokens and attention masks in the observation structure. * feat(tokenizer): Add padding configuration to TokenizerProcessor - Introduced `padding_side` parameter to the TokenizerProcessor for customizable padding direction. - Updated the `make_pi0_processor` function to include the new padding configuration. - Enhanced unit tests to validate the functionality of the `padding_side` parameter in various scenarios. * feat(processor): Add state management methods to Pi0NewLineProcessor * feat(normalization): Track normalization and unnormalization info in complementary data - Updated NormalizerProcessor and UnnormalizerProcessor to accept additional parameters for tracking normalization modes. - Enhanced the __call__ methods to store normalization and unnormalization information in the complementary data of transitions. - Added unit tests to verify the correct tracking of normalization info, including scenarios with missing stats and selective normalization keys. * feat(factory): Add preprocessor and postprocessor overrides to ProcessorConfigKwargs - Updated ProcessorConfigKwargs to include optional overrides for preprocessor and postprocessor configurations. - Enhanced the make_processor function to utilize the new overrides, allowing for more flexible processor initialization. * feat(processors): Integrate RenameProcessor into various processor configurations - Added RenameProcessor to the input steps of multiple processor functions, including make_act_processor, make_diffusion_processor, make_pi0_processor, make_sac_processor, make_tdmpc_processor, make_vqbet_processor, and make_smolvla_processor. - Consolidated normalization features from input and output into a single NormalizerProcessor for improved efficiency. - Updated the input steps to ensure compatibility with the new RenameProcessor integration. * feat(smolvla): Refactor language processing and introduce new line processor (#1658) - Removed the prepare_language method and directly accessed language tokens and masks from the batch using the OBS_LANGUAGE constant. - Added SmolVLANewLineProcessor to ensure tasks end with a newline, enhancing tokenization compatibility. - Updated the make_smolvla_processor function to include the new line processor and tokenizer processor for improved input handling. * feture(policies): add device processor (#1659) * feat(processors): Integrate DeviceProcessor into multiple processor configurations - Added DeviceProcessor to the input and output steps of various processor functions, including make_act_processor, make_diffusion_processor, make_pi0_processor, make_pi0fast_processor, make_sac_processor, make_tdmpc_processor, make_vqbet_processor, and make_smolvla_processor. - Enhanced the DeviceProcessor class with state management methods and ensured compatibility with existing processor pipelines. - Introduced unit tests for DeviceProcessor to validate functionality across different scenarios, including CPU and CUDA operations. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * refactor(pipeline): Remove to() method for device management - Eliminated the to() method from RobotProcessor, which was responsible for moving tensor states to specified devices. - Removed associated unit tests that validated the functionality of the to() method across various scenarios. - Streamlined the pipeline code by focusing on other device management strategies. * feat(processor): Enhance DeviceProcessor with float dtype conversion - Added support for optional float dtype conversion in DeviceProcessor, allowing tensors to be converted to specified floating-point types while preserving non-float types. - Implemented validation for float dtype input and updated the processor's configuration methods to include float dtype. - Refactored tensor processing logic to streamline device movement and dtype conversion. - Introduced comprehensive unit tests to validate the new float dtype functionality across various scenarios. * feat(policies): Add new line processors and update module exports * feat(processor): Enhance batch and device processors to handle index and task_index fields - Added logic to ToBatchProcessor for unsqueezing 0D tensors for index and task_index fields, ensuring they are processed as 1D tensors. - Updated DeviceProcessor to process index and task_index fields in complementary data, preserving their tensor types and ensuring non-tensor fields remain unchanged. - Enhanced unit tests to validate the correct handling of index and task_index fields across various scenarios, including device compatibility and dtype preservation. * refactor(processors): Standardize processor naming conventions - Updated processor names across various files to use a consistent "robot_preprocessor" and "robot_postprocessor" format. - Modified the make_processor functions in factory, act, diffusion, pi0, pi0fast, sac, smolvla, tdmpc, and vqbet to reflect the new naming scheme. - Enhanced the pipeline configuration to align with the updated processor names, improving clarity and maintainability. * refactor(factory): Update processor configuration and type hints - Changed return type of get_policy_class to type[PreTrainedPolicy] for improved type safety. - Enhanced make_processor function to utilize dataset_stats in processor creation for better flexibility. - Updated ProcessorConfigKwargs to include dataset_stats, allowing for more comprehensive processor configurations. - Streamlined processor initialization by removing unnecessary kwargs and ensuring clarity in processor type handling. * refactor(factory, pi0fast): Update processor function names and parameters - Renamed make_pi0_processor to make_pi0fast_processor for clarity and consistency. - Updated parameter names in the factory's make_processor function to use pretrained_model_name_or_path instead of source, enhancing readability and alignment with naming conventions. * fix(train.py) push postprocessor with preprocessor - Add preprocesser policy overrides for device and rename_map - Add rename_map to DatasetRecordConfig (record.py) * refactor(device_processor): Update device handling and improve type hints - Changed device attribute type from torch.device to str for better clarity. - Introduced a private _device attribute to store the actual torch.device instance. - Updated tests to conditionally check for CUDA availability, ensuring compatibility across different environments. - Refactored device-related assertions in tests to use a consistent approach for device type verification. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * test(tokenizer_processor): Add require_package decorator for transformers - Introduced @require_package("transformers") decorator in multiple test functions to ensure the transformers package is available before running tests. - This change enhances test reliability by preventing failures due to missing dependencies. * refactor(migrate_policy_normalization): Enhance preprocessor and postprocessor structure - Introduced RenameProcessor in the preprocessor to handle renaming features. - Combined input and output features in a single NormalizerProcessor for improved efficiency. - Updated RobotProcessor initialization to clarify step naming for preprocessor and postprocessor. - Added DeviceProcessor to both preprocessor and postprocessor for better device management. * Integrate pipeline and add phone teleop (#1681) * Add normalization processor and related components - Introduced `NormalizationProcessor` to handle both observation normalization and action unnormalization. - Added `ObservationNormalizer` and `ActionUnnormalizer` classes for specific normalization tasks. - Updated `__init__.py` to include the new `NormalizationProcessor` in the module exports. - Enhanced `ObservationProcessor` with registration in the `ProcessorStepRegistry` for better modularity. - Created `RenameProcessor` for renaming keys in observations, improving flexibility in data processing. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Enhance processing architecture with new components - Added `RenameProcessor` to facilitate key renaming in observations, improving data handling flexibility. - Updated `__init__.py` to include `RenameProcessor` in module exports. - Refactored `NormalizationProcessor` and `ObservationNormalizer` to use `rsplit` for better key handling. - Introduced comprehensive tests for `NormalizationProcessor` and `RenameProcessor` to ensure functionality and robustness. * chore (docs): add docstring for processor * fix (test): test factory * fix(test): policies * Update tests/processor/test_observation_processor.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Signed-off-by: Adil Zouitine <adilzouitinegm@gmail.com> * chore(test): add suggestion made by copilot regarding numpy test * fix(test): import issue * Refactor normalization components and update tests - Renamed `ObservationNormalizer` to `NormalizerProcessor` and `ActionUnnormalizer` to `UnnormalizerProcessor` for clarity. - Consolidated normalization logic for both observations and actions into `NormalizerProcessor` and `UnnormalizerProcessor`. - Updated tests to reflect the new class names and ensure proper functionality of normalization and unnormalization processes. - Enhanced handling of missing statistics in normalization processes. * chore (docstrin):Improve docstring for NormalizerProcessor * feat (device processor): Implement device processor * chore (batch handling): Enhance processing components with batch conversion utilities * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix(test): linting issue * chore (output format): improves output format * chore (type): add typing for multiprocess envs * feat (overrides): Implement support for loading processors with parameter overrides - Added the ability to provide non-serializable objects when loading processors from saved configurations using the `overrides` parameter. - Enhanced error handling for invalid override keys and instantiation errors. - Updated documentation and examples to illustrate the usage of overrides for both registered and unregistered steps. - Added comprehensive tests to validate the new functionality and ensure backward compatibility. * chore(normalization): addressing comments from copilot * chore(learner): nit comment from copilot * feat(pipeline): Enhance step_through method to support both tuple and dict inputs * refactor(pipeline): Simplify observation and padding data handling in batch transitions * Apply suggestions from code review Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com> Signed-off-by: Adil Zouitine <adilzouitinegm@gmail.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * refactor(pipeline): Introduce ComplementaryDataProcessor for handling complementary data in transitions * fix(ci): temporary fix on dataset deps version * feat(processors): Introduce processors for various policy types - Added `make_processor` function to create processor instances for different policy types, including `tdmpc`, `diffusion`, `act`, `vqbet`, `pi0`, `pi0fast`, `sac`, and `reward_classifier`. - Implemented corresponding processor files for each policy type, encapsulating normalization and unnormalization steps. - Updated existing policies to remove direct normalization dependencies, enhancing modularity and clarity. - Enhanced test coverage to validate the integration of new processors with existing policy configurations. * refactor(learner): Remove normalization from cached image features retrieval - Simplified the retrieval of observation features by removing the normalization step from the `get_cached_image_features` method calls. - This change enhances clarity and aligns with the recent updates to policy processors. * refactor(policies): Remove unnormalization step from action predictions - Eliminated the unnormalization of actions in both `TDMPCPolicy` and `VQBeTPolicy` classes to streamline action prediction. - This change improves code clarity and aligns with recent updates to policy processors. * feat(train): Integrate preprocessor into training pipeline * refactor(train): Update preprocessor initialization to include dataset statistics * refactor(policies): Enhance processor creation and add NaN detection hook * refactor(train): Update memory pinning logic for mps compatibility * feat: initial commit phone teleop * ugly delta control * use quaternion * Refactor observation preprocessing to use a modular pipeline system - Introduced `RobotPipeline` and `ObservationProcessor` for handling observation transformations. - Updated `preprocess_observation` to maintain backward compatibility while leveraging the new pipeline. - Added tests for the new processing components and ensured they match the original functionality. - Removed hardcoded logic in favor of a more flexible, composable architecture. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Refactor observation processing and improve modularity - Updated `ObservationProcessor` to enhance the modular design for processing observations. - Cleaned up imports and improved code readability by removing unnecessary lines and comments. - Ensured backward compatibility while integrating new processing components. - Added tests to validate the functionality of the updated processing architecture. * Remove redundant tests for None observation and serialization methods in `test_observation_processor.py` to streamline the test suite and improve maintainability. * Refactor processing architecture to use RobotProcessor - Replaced instances of RobotPipeline with RobotProcessor across the codebase for improved modularity and clarity. - Introduced ProcessorStepRegistry for better management of processing steps. - Updated relevant documentation and tests to reflect the new processing structure. - Enhanced the save/load functionality to support the new processor design. - Added a model card template for RobotProcessor to facilitate sharing and documentation. * Add RobotProcessor tutorial to documentation - Introduced a new tutorial on using RobotProcessor for preprocessing robot data. - Added a section in the table of contents for easy navigation to the new tutorial. - The tutorial covers key concepts, real-world scenarios, and practical examples for effective use of the RobotProcessor pipeline. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Add normalization processor and related components - Introduced `NormalizationProcessor` to handle both observation normalization and action unnormalization. - Added `ObservationNormalizer` and `ActionUnnormalizer` classes for specific normalization tasks. - Updated `__init__.py` to include the new `NormalizationProcessor` in the module exports. - Enhanced `ObservationProcessor` with registration in the `ProcessorStepRegistry` for better modularity. - Created `RenameProcessor` for renaming keys in observations, improving flexibility in data processing. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Enhance processing architecture with new components - Added `RenameProcessor` to facilitate key renaming in observations, improving data handling flexibility. - Updated `__init__.py` to include `RenameProcessor` in module exports. - Refactored `NormalizationProcessor` and `ObservationNormalizer` to use `rsplit` for better key handling. - Introduced comprehensive tests for `NormalizationProcessor` and `RenameProcessor` to ensure functionality and robustness. * chore (docs): add docstring for processor * fix (test): test factory * fix(test): policies * Update tests/processor/test_observation_processor.py Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Signed-off-by: Adil Zouitine <adilzouitinegm@gmail.com> * chore(test): add suggestion made by copilot regarding numpy test * fix(test): import issue * Refactor normalization components and update tests - Renamed `ObservationNormalizer` to `NormalizerProcessor` and `ActionUnnormalizer` to `UnnormalizerProcessor` for clarity. - Consolidated normalization logic for both observations and actions into `NormalizerProcessor` and `UnnormalizerProcessor`. - Updated tests to reflect the new class names and ensure proper functionality of normalization and unnormalization processes. - Enhanced handling of missing statistics in normalization processes. * chore (docstrin):Improve docstring for NormalizerProcessor * feat (device processor): Implement device processor * chore (batch handling): Enhance processing components with batch conversion utilities * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix(test): linting issue * chore (output format): improves output format * chore (type): add typing for multiprocess envs * feat (overrides): Implement support for loading processors with parameter overrides - Added the ability to provide non-serializable objects when loading processors from saved configurations using the `overrides` parameter. - Enhanced error handling for invalid override keys and instantiation errors. - Updated documentation and examples to illustrate the usage of overrides for both registered and unregistered steps. - Added comprehensive tests to validate the new functionality and ensure backward compatibility. * chore(normalization): addressing comments from copilot * chore(learner): nit comment from copilot * feat(pipeline): Enhance step_through method to support both tuple and dict inputs * refactor(pipeline): Simplify observation and padding data handling in batch transitions * Apply suggestions from code review Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com> Signed-off-by: Adil Zouitine <adilzouitinegm@gmail.com> * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * refactor(pipeline): Introduce ComplementaryDataProcessor for handling complementary data in transitions * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * refactor(pipeline): Transition from tuple to dictionary format for EnvTransition - Updated the EnvTransition structure to use a dictionary format instead of a tuple, enhancing readability and maintainability. - Replaced instances of TransitionIndex with TransitionKey for accessing transition components. - Adjusted related processing functions and tests to accommodate the new dictionary format, ensuring consistent handling of transitions across the codebase. * refactor(observation_processor): Improve observation processing by using constants and simplifying pixel handling - Introduced constants for observation keys to enhance readability. - Streamlined the handling of the "pixels" key by copying observations first and processing images more clearly. - Updated the environment state and agent position assignments to use the new constants, improving maintainability. * feat(pipeline): Add hook unregistration functionality and enhance documentation - Implemented methods to unregister before, after, and reset hooks in the RobotProcessor class, allowing for more flexible hook management. - Enhanced documentation to clarify hook execution semantics and the implications of modifying transitions within hooks. - Added comprehensive tests to verify the correct behavior of hook registration and unregistration, including error handling for non-existent hooks. * refactor(pipeline): Clarify hook behavior and improve documentation - Updated the RobotProcessor class to ensure hooks are strictly for observation and do not modify transitions, enhancing clarity and maintainability. - Refactored hook registration methods to reflect the new behavior, ensuring they accept only functions that do not return modified transitions. - Enhanced documentation to clearly outline the purpose of hooks and their execution semantics. - Added tests to verify that hooks are not executed during the step_through method while ensuring they function correctly during the __call__ method. * feat(pipeline): Add __repr__ method to RobotProcessor for improved readability - Implemented a __repr__ method in the RobotProcessor class to provide a clear string representation of the processor, including step names and optional parameters like name and seed. - Added comprehensive tests to validate the __repr__ output for various scenarios, including empty processors, single and multiple steps, custom names, and seed values. - Ensured that the representation handles long lists of steps with truncation for better readability. * chore(pipeline): Move _CFG_NAME along other class member * refactor(pipeline): Utilize get_safe_torch_device for device assignment - Replaced direct torch.device instantiation with get_safe_torch_device to ensure safe device handling. - This change enhances code readability and maintains consistency in device management across the RobotProcessor class. * refactor(pipeline): Enhance state filename generation and profiling method - Updated state filename generation to use the registry name when available, improving clarity in saved files. - Modified the profile_steps method to include a warmup_runs parameter, allowing for more controlled performance profiling. - Ensured consistent conditions during profiling by deep copying transitions for each run, enhancing accuracy in timing results. * chore(doc): address pip install commant lerobot that not exist yet * feat(pipeline): Enhance configuration filename handling and state file naming - Introduced support for custom configuration filenames in the `save_pretrained` method, allowing users to specify a filename instead of the default. - Improved state file naming to include step indices, preventing conflicts when multiple processors of the same type are saved. - Added automatic detection for configuration files when loading from a directory, with error handling for multiple files. - Updated tests to validate new features, including custom filenames and automatic config detection. * refactor(pipeline): Improve state file naming conventions for clarity and uniqueness - Enhanced state file naming to include the processor's sanitized name, ensuring uniqueness when multiple processors are saved in the same directory. - Updated tests to reflect changes in state file naming, verifying that filenames now include the processor name and step indices to prevent conflicts. - Added a new test to validate state file naming when using multiple processors, ensuring distinct filenames for each processor's state files. * docs(pipeline): Add clarification for repo name sanitization process * feat(processors): Introduce processors for various policy types - Added `make_processor` function to create processor instances for different policy types, including `tdmpc`, `diffusion`, `act`, `vqbet`, `pi0`, `pi0fast`, `sac`, and `reward_classifier`. - Implemented corresponding processor files for each policy type, encapsulating normalization and unnormalization steps. - Updated existing policies to remove direct normalization dependencies, enhancing modularity and clarity. - Enhanced test coverage to validate the integration of new processors with existing policy configurations. * refactor(learner): Remove normalization from cached image features retrieval - Simplified the retrieval of observation features by removing the normalization step from the `get_cached_image_features` method calls. - This change enhances clarity and aligns with the recent updates to policy processors. * refactor(policies): Remove unnormalization step from action predictions - Eliminated the unnormalization of actions in both `TDMPCPolicy` and `VQBeTPolicy` classes to streamline action prediction. - This change improves code clarity and aligns with recent updates to policy processors. * feat(train): Integrate preprocessor into training pipeline * refactor(train): Update preprocessor initialization to include dataset statistics * refactor(policies): Enhance processor creation and add NaN detection hook * feat(record): Integrate RobotProcessor into recording loop and update policy handling - Added support for RobotProcessor in the record_loop function to enhance data processing capabilities. - Updated the logic to reset both policy and processor when provided, ensuring proper state management. - Modified action prediction to utilize the processor, improving the overall functionality of the recording process. - Adjusted the save_checkpoint function to include preprocessor state saving, enhancing checkpointing capabilities. * feat(migration): Add script for migrating policy models with normalization layers * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * feat(migrate): Enhance migration script to create preprocessor and postprocessor for policy models - Updated the migration script to generate both a preprocessor and a postprocessor, improving the handling of normalization for training and inference. - Added functionality to convert features to PolicyFeature objects, ensuring compatibility with the new processor architecture. - Refined the extraction and removal of normalization statistics and layers, streamlining the migration process. - Improved error handling for missing mandatory configuration fields during model instantiation. * feat(migrate): Add model card generation and saving to migration script - Implemented functionality to generate and save a model card for the migrated model, including metadata such as dataset repository ID, license, and tags. - Enhanced the script to push the model card to the hub if requested, improving model documentation and accessibility. - Refactored the saving process to ensure the model card is saved locally and uploaded correctly when pushing to the hub. * feat(processor): Introduce ToBatchProcessor for handling observation batching - Added ToBatchProcessor to ensure observations have proper batch dimensions for model processing. - Implemented functionality to add batch dimensions to state and image observations as needed. - Created comprehensive unit tests to validate the processor's behavior with various tensor dimensions and types. - Ensured compatibility with existing transition keys and maintained the integrity of non-observation data. * feat(processors): Add ToBatchProcessor to multiple policy processors - Integrated ToBatchProcessor into various policy processors to handle observation batching. - Updated make functions for act, diffusion, pi0, pi0fast, sac, smolvla, tdmpc, and vqbet processors to include the new batching functionality. - Ensured consistency across all processor implementations for improved data handling. * refactor(factory): Remove unused imports and NaN detection hook from processor creation * feat(batch_processor): Enhance ToBatchProcessor to handle action batching - Updated ToBatchProcessor to add batch dimensions to actions in addition to observations. - Implemented separate methods for processing observations and actions, improving code readability. - Added comprehensive unit tests to validate action batching functionality across various tensor dimensions and types. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * feat(factory): Enhance make_processor to support preprocessor and postprocessor configuration - Introduced ProcessorConfigKwargs TypedDict for better type safety in processor configuration. - Updated make_processor to accept preprocessor and postprocessor configuration filenames, improving flexibility in processor instantiation. - Refactored the loading of pretrained processors to utilize the new configuration options. * refactor(factory): Clean up imports in factory.py - Removed unused import of IdentityProcessor to streamline the code. * feat(migrate): Extend load_model_from_hub to include train configuration - Updated load_model_from_hub to return the train configuration alongside the model state_dict and config. - Modified main function to handle the additional train configuration when loading models from both the hub and local paths. - Adjusted dataset_repo_id extraction to utilize the train configuration for improved accuracy. * refactor(record): Rename processor parameters and update processing logic - Renamed `processor` to `preprocessor` and added `postprocessor` parameter for clarity. - Updated the `record_loop` and `predict_action` functions to utilize the new preprocessor and postprocessor, enhancing the processing flow. - Ensured compatibility with existing functionality while improving code readability. * feat(batch_processor): Add task field processing to ToBatchProcessor - Enhanced ToBatchProcessor to wrap string tasks in a list, adding batch dimensions for compatibility with model inference. - Implemented a new method for processing complementary data, ensuring that task values are correctly handled as either strings or lists of strings. - Added comprehensive unit tests to validate task processing, including edge cases and in-place mutation of complementary data. * feat(normalization): Implement IDENTITY mode for normalization and unnormalization - Enhanced NormalizerProcessor and UnnormalizerProcessor to support IDENTITY mode, allowing features to bypass normalization when specified. - Updated processing logic to check normalization modes and handle missing statistics gracefully. - Added comprehensive unit tests to validate IDENTITY mode functionality for both observations and actions, ensuring correct behavior across various scenarios. - Improved error handling for unsupported normalization modes. * fix(rebase): remove residual normalization layer: * refactor(diffusion): remove normalization layer from input processing * Add debug + calib * cleanup * Add pipeline * fix int * Add record example * nit * Add feature contract to pipelinestep and pipeline * Add tests * Add processor tests * PR feedback * encorperate pr feedback * type in doc * oops * cleaned up steps and integrated pipeline with feature_contract * refactor steps and robot to pipeline * cleanup pipeline * cleanup code further * make it run * feat(processors): Introduce processors for various policy types - Added `make_processor` function to create processor instances for different policy types, including `tdmpc`, `diffusion`, `act`, `vqbet`, `pi0`, `pi0fast`, `sac`, and `reward_classifier`. - Implemented corresponding processor files for each policy type, encapsulating normalization and unnormalization steps. - Updated existing policies to remove direct normalization dependencies, enhancing modularity and clarity. - Enhanced test coverage to validate the integration of new processors with existing policy configurations. * refactor(learner): Remove normalization from cached image features retrieval - Simplified the retrieval of observation features by removing the normalization step from the `get_cached_image_features` method calls. - This change enhances clarity and aligns with the recent updates to policy processors. * refactor(policies): Remove unnormalization step from action predictions - Eliminated the unnormalization of actions in both `TDMPCPolicy` and `VQBeTPolicy` classes to streamline action prediction. - This change improves code clarity and aligns with recent updates to policy processors. * feat(train): Integrate preprocessor into training pipeline * refactor(train): Update preprocessor initialization to include dataset statistics * refactor(policies): Enhance processor creation and add NaN detection hook * feat(record): Integrate RobotProcessor into recording loop and update policy handling - Added support for RobotProcessor in the record_loop function to enhance data processing capabilities. - Updated the logic to reset both policy and processor when provided, ensuring proper state management. - Modified action prediction to utilize the processor, improving the overall functionality of the recording process. - Adjusted the save_checkpoint function to include preprocessor state saving, enhancing checkpointing capabilities. * feat(migration): Add script for migrating policy models with normalization layers * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * feat(migrate): Enhance migration script to create preprocessor and postprocessor for policy models - Updated the migration script to generate both a preprocessor and a postprocessor, improving the handling of normalization for training and inference. - Added functionality to convert features to PolicyFeature objects, ensuring compatibility with the new processor architecture. - Refined the extraction and removal of normalization statistics and layers, streamlining the migration process. - Improved error handling for missing mandatory configuration fields during model instantiation. * feat(migrate): Add model card generation and saving to migration script - Implemented functionality to generate and save a model card for the migrated model, including metadata such as dataset repository ID, license, and tags. - Enhanced the script to push the model card to the hub if requested, improving model documentation and accessibility. - Refactored the saving process to ensure the model card is saved locally and uploaded correctly when pushing to the hub. * feat(processor): Introduce ToBatchProcessor for handling observation batching - Added ToBatchProcessor to ensure observations have proper batch dimensions for model processing. - Implemented functionality to add batch dimensions to state and image observations as needed. - Created comprehensive unit tests to validate the processor's behavior with various tensor dimensions and types. - Ensured compatibility with existing transition keys and maintained the integrity of non-observation data. * feat(processors): Add ToBatchProcessor to multiple policy processors - Integrated ToBatchProcessor into various policy processors to handle observation batching. - Updated make functions for act, diffusion, pi0, pi0fast, sac, smolvla, tdmpc, and vqbet processors to include the new batching functionality. - Ensured consistency across all processor implementations for improved data handling. * refactor(factory): Remove unused imports and NaN detection hook from processor creation * feat(batch_processor): Enhance ToBatchProcessor to handle action batching - Updated ToBatchProcessor to add batch dimensions to actions in addition to observations. - Implemented separate methods for processing observations and actions, improving code readability. - Added comprehensive unit tests to validate action batching functionality across various tensor dimensions and types. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * feat(factory): Enhance make_processor to support preprocessor and postprocessor configuration - Introduced ProcessorConfigKwargs TypedDict for better type safety in processor configuration. - Updated make_processor to accept preprocessor and postprocessor configuration filenames, improving flexibility in processor instantiation. - Refactored the loading of pretrained processors to utilize the new configuration options. * refactor(factory): Clean up imports in factory.py - Removed unused import of IdentityProcessor to streamline the code. * feat(migrate): Extend load_model_from_hub to include train configuration - Updated load_model_from_hub to return the train configuration alongside the model state_dict and config. - Modified main function to handle the additional train configuration when loading models from both the hub and local paths. - Adjusted dataset_repo_id extraction to utilize the train configuration for improved accuracy. * refactor(record): Rename processor parameters and update processing logic - Renamed `processor` to `preprocessor` and added `postprocessor` parameter for clarity. - Updated the `record_loop` and `predict_action` functions to utilize the new preprocessor and postprocessor, enhancing the processing flow. - Ensured compatibility with existing functionality while improving code readability. * feat(batch_processor): Add task field processing to ToBatchProcessor - Enhanced ToBatchProcessor to wrap string tasks in a list, adding batch dimensions for compatibility with model inference. - Implemented a new method for processing complementary data, ensuring that task values are correctly handled as either strings or lists of strings. - Added comprehensive unit tests to validate task processing, including edge cases and in-place mutation of complementary data. * feat(normalization): Implement IDENTITY mode for normalization and unnormalization - Enhanced NormalizerProcessor and UnnormalizerProcessor to support IDENTITY mode, allowing features to bypass normalization when specified. - Updated processing logic to check normalization modes and handle missing statistics gracefully. - Added comprehensive unit tests to validate IDENTITY mode functionality for both observations and actions, ensuring correct behavior across various scenarios. - Improved error handling for unsupported normalization modes. * fix(rebase): remove residual normalization layer: * refactor(diffusion): remove normalization layer from input processing * refactor(normalization): Remove unused state dict transformation methods and streamline imports - Eliminated the _transform_state_dict_keys and _load_as_safetensor methods from PI0Policy, simplifying the model loading process. - Cleaned up imports in modeling_pi0.py by removing log_model_loading_keys and init_logging. - Updated TDMPCPolicy and VQBeTPolicy to handle action removal from batches during offline evaluation. - Introduced hotswap_stats function in normalize_processor.py to update normalization statistics dynamically, with corresponding tests to ensure functionality. * refactor(normalization): Clean up imports in normalize_processor.py * feat(batch_processor): Add feature_contract method to ToBatchProcessor - Introduced feature_contract method that returns features without modification, maintaining the no-op behavior of the processor. - This addition enhances the flexibility of the ToBatchProcessor for future feature processing needs. * fix(dependencies): Update transformers dependency constraint to allow only versions up to 4.52.0 * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * feat(tokenizer): Introduce TokenizerProcessor for text tokenization - Added TokenizerProcessor class to handle tokenization of task strings using Hugging Face's AutoTokenizer. - Supports both string and list inputs, with customizable parameters for task key, output key, and tokenization settings. - Implemented comprehensive unit tests to validate functionality, including handling of various input scenarios and integration with RobotProcessor. - Updated types.py to include LANGUAGE feature type and modified __init__.py to register the new processor. * feat(language): Enhance language processing in TokenizerProcessor - Added OBS_LANGUAGE constant to define the observation language key. - Updated TokenizerProcessor to store tokenized task data in the observation dictionary, ensuring compatibility with the new language feature. - Introduced Pi0NewLineProcessor to append newlines to tasks for proper tokenization. - Modified tests to validate the integration of language tokens and attention masks in the observation structure. * feat(tokenizer): Add padding configuration to TokenizerProcessor - Introduced `padding_side` parameter to the TokenizerProcessor for customizable padding direction. - Updated the `make_pi0_processor` function to include the new padding configuration. - Enhanced unit tests to validate the functionality of the `padding_side` parameter in various scenarios. * feat(processor): Add state management methods to Pi0NewLineProcessor * feat(normalization): Track normalization and unnormalization info in complementary data - Updated NormalizerProcessor and UnnormalizerProcessor to accept additional parameters for tracking normalization modes. - Enhanced the __call__ methods to store normalization and unnormalization information in the complementary data of transitions. - Added unit tests to verify the correct tracking of normalization info, including scenarios with missing stats and selective normalization keys. * feat(factory): Add preprocessor and postprocessor overrides to ProcessorConfigKwargs - Updated ProcessorConfigKwargs to include optional overrides for preprocessor and postprocessor configurations. - Enhanced the make_processor function to utilize the new overrides, allowing for more flexible processor initialization. * feat(processors): Integrate RenameProcessor into various processor configurations - Added RenameProcessor to the input steps of multiple processor functions, including make_act_processor, make_diffusion_processor, make_pi0_processor, make_sac_processor, make_tdmpc_processor, make_vqbet_processor, and make_smolvla_processor. - Consolidated normalization features from input and output into a single NormalizerProcessor for improved efficiency. - Updated the input steps to ensure compatibility with the new RenameProcessor integration. * Do some todos and cleanup * change feature_contract to dataset_features * use one method for conversion pipeline output to add_frame dict and use base processors where possible * Add back in and use record_loop * update todo * rename to_dataset_frame * feat(smolvla): Refactor language processing and introduce new line processor (#1658) - Removed the prepare_language method and directly accessed language tokens and masks from the batch using the OBS_LANGUAGE constant. - Added SmolVLANewLineProcessor to ensure tasks end with a newline, enhancing tokenization compatibility. - Updated the make_smolvla_processor function to include the new line processor and tokenizer processor for improved input handling. * feat(processors): Integrate DeviceProcessor into multiple processor configurations - Added DeviceProcessor to the input and output steps of various processor functions, including make_act_processor, make_diffusion_processor, make_pi0_processor, make_pi0fast_processor, make_sac_processor, make_tdmpc_processor, make_vqbet_processor, and make_smolvla_processor. - Enhanced the DeviceProcessor class with state management methods and ensured compatibility with existing processor pipelines. - Introduced unit tests for DeviceProcessor to validate functionality across different scenarios, including CPU and CUDA operations. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix * fix reference frame * refactor(pipeline): Remove to() method for device management - Eliminated the to() method from RobotProcessor, which was responsible for moving tensor states to specified devices. - Removed associated unit tests that validated the functionality of the to() method across various scenarios. - Streamlined the pipeline code by focusing on other device management strategies. * feat(processor): Enhance DeviceProcessor with float dtype conversion - Added support for optional float dtype conversion in DeviceProcessor, allowing tensors to be converted to specified floating-point types while preserving non-float types. - Implemented validation for float dtype input and updated the processor's configuration methods to include float dtype. - Refactored tensor processing logic to streamline device movement and dtype conversion. - Introduced comprehensive unit tests to validate the new float dtype functionality across various scenarios. * update data visualization * update teleop example * fix record bugs * Add replay * Not code * feature(pipeline): port tokenizer pipeline for VLA (#1645) * feat(tokenizer): Introduce TokenizerProcessor for text tokenization - Added TokenizerProcessor class to handle tokenization of task strings using Hugging Face's AutoTokenizer. - Supports both string and list inputs, with customizable parameters for task key, output key, and tokenization settings. - Implemented comprehensive unit tests to validate functionality, including handling of various input scenarios and integration with RobotProcessor. - Updated types.py to include LANGUAGE feature type and modified __init__.py to register the new processor. * feat(language): Enhance language processing in TokenizerProcessor - Added OBS_LANGUAGE constant to define the observation language key. - Updated TokenizerProcessor to store tokenized task data in the observation dictionary, ensuring compatibility with the new language feature. - Introduced Pi0NewLineProcessor to append newlines to tasks for proper tokenization. - Modified tests to validate the integration of language tokens and attention masks in the observation structure. * feat(tokenizer): Add padding configuration to TokenizerProcessor - Introduced `padding_side` parameter to the TokenizerProcessor for customizable padding direction. - Updated the `make_pi0_processor` function to include the new padding configuration. - Enhanced unit tests to validate the functionality of the `padding_side` parameter in various scenarios. * feat(processor): Add state management methods to Pi0NewLineProcessor * feat(normalization): Track normalization and unnormalization info in complementary data - Updated NormalizerProcessor and UnnormalizerProcessor to accept additional parameters for tracking normalization modes. - Enhanced the __call__ methods to store normalization and unnormalization information in the complementary data of transitions. - Added unit tests to verify the correct tracking of normalization info, including scenarios with missing stats and selective normalization keys. * feat(factory): Add preprocessor and postprocessor overrides to ProcessorConfigKwargs - Updated ProcessorConfigKwargs to include optional overrides for preprocessor and postprocessor configurations. - Enhanced the make_processor function to utilize the new overrides, allowing for more flexible processor initialization. * feat(processors): Integrate RenameProcessor into various processor configurations - Added RenameProcessor to the input steps of multiple processor functions, including make_act_processor, make_diffusion_processor, make_pi0_processor, make_sac_processor, make_tdmpc_processor, make_vqbet_processor, and make_smolvla_processor. - Consolidated normalization features from input and output into a single NormalizerProcessor for improved efficiency. - Updated the input steps to ensure compatibility with the new RenameProcessor integration. * feat(smolvla): Refactor language processing and introduce new line processor (#1658) - Removed the prepare_language method and directly accessed language tokens and masks from the batch using the OBS_LANGUAGE constant. - Added SmolVLANewLineProcessor to ensure tasks end with a newline, enhancing tokenization compatibility. - Updated the make_smolvla_processor function to include the new line processor and tokenizer processor for improved input handling. * feture(policies): add device processor (#1659) * feat(processors): Integrate DeviceProcessor into multiple processor configurations - Added DeviceProcessor to the input and output steps of various processor functions, including make_act_processor, make_diffusion_processor, make_pi0_processor, make_pi0fast_processor, make_sac_processor, make_tdmpc_processor, make_vqbet_processor, and make_smolvla_processor. - Enhanced the DeviceProcessor class with state management methods and ensured compatibility with existing processor pipelines. - Introduced unit tests for DeviceProcessor to validate functionality across different scenarios, including CPU and CUDA operations. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * refactor(pipeline): Remove to() method for device management - Eliminated the to() method from RobotProcessor, which was responsible for moving tensor states to specified devices. - Removed associated unit tests that validated the functionality of the to() method across various scenarios. - Streamlined the pipeline code by focusing on other device management strategies. * feat(processor): Enhance DeviceProcessor with float dtype conversion - Added support for optional float dtype conversion in DeviceProcessor, allowing tensors to be converted to specified floating-point types while preserving non-float types. - Implemented validation for float dtype input and updated the processor's configuration methods to include float dtype. - Refactored tensor processing logic to streamline device movement and dtype conversion. - Introduced comprehensive unit tests to validate the new float dtype functionality across various scenarios. * feat(policies): Add new line processors and update module exports * feat(processor): Enhance batch and device processors to handle index and task_index fields - Added logic to ToBatchProcessor for unsqueezing 0D tensors for index and task_index fields, ensuring they are processed as 1D tensors. - Updated DeviceProcessor to process index and task_index fields in complementary data, preserving their tensor types and ensuring non-tensor fields remain unchanged. - Enhanced unit tests to validate the correct handling of index and task_index fields across various scenarios, including device compatibility and dtype preservation. * Add eval script * fix `q_curr` in InverseKinematicsEEToJoints to the IK solution * feat(processors): Introduce processors for various policy types - Added `make_processor` function to create processor instances for different policy types, including `tdmpc`, `diffusion`, `act`, `vqbet`, `pi0`, `pi0fast`, `sac`, and `reward_classifier`. - Implemented corresponding processor files for each policy type, encapsulating normalization and unnormalization steps. - Updated existing policies to remove direct normalization dependencies, enhancing modularity and clarity. - Enhanced test coverage to validate the integration of new processors with existing policy configurations. * refactor(learner): Remove normalization from cached image features retrieval - Simplified the retrieval of observation features by removing the normalization step from the `get_cached_image_features` method calls. - This change enhances clarity and aligns with the recent updates to policy processors. * refactor(policies): Remove unnormalization step from action predictions - Eliminated the unnormalization of actions in both `TDMPCPolicy` and `VQBeTPolicy` classes to streamline action prediction. - This change improves code clarity and aligns with recent updates to policy processors. * feat(train): Integrate preprocessor into training pipeline * refactor(train): Update preprocessor initialization to include dataset statistics * refactor(policies): Enhance processor creation and add NaN detection hook * feat(record): Integrate RobotProcessor into recording loop and update policy handling - Added support for RobotProcessor in the record_loop function to enhance data processing capabilities. - Updated the logic to reset both policy and processor when provided, ensuring proper state management. - Modified action prediction to utilize the processor, improving the overall functionality of the recording process. - Adjusted the save_checkpoint function to include preprocessor state saving, enhancing checkpointing capabilities. * feat(migration): Add script for migrating policy models with normalization layers * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * feat(migrate): Enhance migration script to create preprocessor and postprocessor for policy models - Updated the migration script to generate both a preprocessor and a postprocessor, improving the handling of normalization for training and inference. - Added functionality to convert features to PolicyFeature objects, ensuring compatibility with the new processor architecture. - Refined the extraction and removal of normalization statistics and layers, streamlining the migration process. - Improved error handling for missing mandatory configuration fields during model instantiation. * feat(migrate): Add model card generation and saving to migration script - Implemented functionality to generate and save a model card for the migrated model, including metadata such as dataset repository ID, license, and tags. - Enhanced the script to push the model card to the hub if requested, improving model documentation and accessibility. - Refactored the saving process to ensure the model card is saved locally and uploaded correctly when pushing to the hub. * feat(processor): Introduce ToBatchProcessor for handling observation batching - Added ToBatchProcessor to ensure observations have proper batch dimensions for model processing. - Implemented functionality to add batch dimensions to state and image observations as needed. - Created comprehensive unit tests to validate the processor's behavior with various tensor dimensions and types. - Ensured compatibility with existing transition keys and maintained the integrity of non-observation data. * feat(processors): Add ToBatchProcessor to multiple policy processors - Integrated ToBatchProcessor into various policy processors to handle observation batching. - Updated make functions for act, diffusion, pi0, pi0fast, sac, smolvla, tdmpc, and vqbet processors to include the new batching functionality. - Ensured consistency across all processor implementations for improved data handling. * refactor(factory): Remove unused imports and NaN detection hook from processor creation * feat(batch_processor): Enhance ToBatchProcessor to handle action batching - Updated ToBatchProcessor to add batch dimensions to actions in addition to observations. - Implemented separate methods for processing observations and actions, improving code readability. - Added comprehensive unit tests to validate action batching functionality across various tensor dimensions and types. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * feat(factory): Enhance make_processor to support preprocessor and postprocessor configuration - Introduced ProcessorConfigKwargs TypedDict for better type safety in processor configuration. - Updated make_processor to accept preprocessor and postprocessor configuration filenames, improving flexibility in processor instantiation. - Refactored the loading of pretrained processors to utilize the new configuration options. * refactor(factory): Clean up imports in factory.py - Removed unused import of IdentityProcessor to streamline the code. * feat(migrate): Extend load_model_from_hub to include train configuration - Updated load_model_from_hub to return the train configuration alongside the model state_dict and config. - Modified main function to handle the additional train configuration when loading models from both the hub and local paths. - Adjusted dataset_repo_id extraction to utilize the train configuration for improved accuracy. * refactor(record): Rename processor parameters and update processing logic - Renamed `processor` to `preprocessor` and added `postprocessor` parameter for clarity. - Updated the `record_loop` and `predict_action` functions to utilize the new preprocessor and postprocessor, enhancing the processing flow. - Ensured compatibility with existing functionality while improving code readability. * feat(batch_processor): Add task field processing to ToBatchProcessor - Enhanced ToBatchProcessor to wrap string tasks in a list, adding batch dimensions for compatibility with model inference. - Implemented a new method for processing complementary data, ensuring that task values are correctly handled as either strings or lists of strings. - Added comprehensive unit tests to validate task processing, including edge cases and in-place mutation of complementary data. * feat(normalization): Implement IDENTITY mode for normalization and unnormalization - Enhanced NormalizerProcessor and UnnormalizerProcessor to support IDENTITY mode, allowing features to bypass normalization when specified. - Updated processing logic to check normalization modes and handle missing statistics gracefully. - Added comprehensive unit tests to validate IDENTITY mode functionality for both observations and actions, ensuring correct behavior across various scenarios. - Improved error handling for unsupported normalization modes. * fix(rebase): remove residual normalization layer: * refactor(diffusion): remove normalization layer from input processing * refactor(normalization): Remove unused state dict transformation methods and streamline imports - Eliminated the _transform_state_dict_keys and _load_as_safetensor methods from PI0Policy, simplifying the model loading process. - Cleaned up imports in modeling_pi0.py by removing log_model_loading_keys and init_logging. - Updated TDMPCPolicy and VQBeTPolicy to handle action removal from batches during offline evaluation. - Introduced hotswap_stats function in normalize_processor.py to update normalization statistics dynamically, with corresponding tests to ensure functionality. * refactor(normalization): Clean up imports in normalize_processor.py * feat(batch_processor): Add feature_contract method to ToBatchProcessor - Introduced feature_contract method that returns features without modification, maintaining the no-op behavior of the processor. - This addition enhances the flexibility of the ToBatchProcessor for future feature processing needs. * fix(dependencies): Update transformers dependency constraint to allow only versions up to 4.52.0 * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * feature(pipeline): port tokenizer pipeline for VLA (#1645) * feat(tokenizer): Introduce TokenizerProcessor for text tokenization - Added TokenizerProcessor class to handle tokenization of task strings using Hugging Face's AutoTokenizer. - Supports both string and list inputs, with customizable parameters for task key, output key, and tokenization settings. - Implemented comprehensive unit tests to validate functionality, including handling of various input scenarios and integration with RobotProcessor. - Updated types.py to include LANGUAGE feature type and modified __init__.py to register the new processor. * feat(language): Enhance language processing in TokenizerProcessor - Added OBS_LANGUAGE constant to define the observation language key. - Updated TokenizerProcessor to store tokenized task data in the observation dictionary, ensuring compatibility with the new language feature. - Introduced Pi0NewLineProcessor to append newlines to tasks for proper tokenization. - Modified tests to validate the integration of language tokens and attention masks in the observation structure. * feat(tokenizer): Add padding configuration to TokenizerProcessor - Introduced `padding_side` parameter to the TokenizerProcessor for customizable padding direction. - Updated the `make_pi0_processor` function to include the new padding configuration. - Enhanced unit tests to validate the functionality of the `padding_side` parameter in various scenarios. * feat(processor): Add state management methods to Pi0NewLineProcessor * feat(normalization): Track normalization and unnormalization info in complementary data - Updated NormalizerProcessor and UnnormalizerProcessor to accept additional parameters for tracking normalization modes. - Enhanced the __call__ methods to store normalization and unnormalization information in the complementary data of transitions. - Added unit tests to verify the correct tracking of normalization info, including scenarios with missing stats and selective normalization keys. * feat(factory): Add preprocessor and postprocessor overrides to ProcessorConfigKwargs - Updated ProcessorConfigKwargs to include optional overrides for preprocessor and postprocessor configurations. - Enhanced the make_processor function to utilize the new overrides, allowing for more flexible processor initialization. * feat(processors): Integrate RenameProcessor into various processor configurations - Added RenameProcessor to the input steps of multiple processor functions, including make_act_processor, make_diffusion_processor, make_pi0_processor, make_sac_processor, make_tdmpc_processor, make_vqbet_processor, and make_smolvla_processor. - Consolidated normalization features from input and output into a single NormalizerProcessor for improved efficiency. - Updated the input steps to ensure compatibility with the new RenameProcessor integration. * feat(smolvla): Refactor language processing and introduce new line processor (#1658) - Removed the prepare_language method and directly accessed language tokens and masks from the batch using the OBS_LANGUAGE constant. - Added SmolVLANewLineProcessor to ensure tasks end with a newline, enhancing tokenization compatibility. - Updated the make_smolvla_processor function to include the new line processor and tokenizer processor for improved input handling. * feture(policies): add device processor (#1659) * feat(processors): Integrate DeviceProcessor into multiple processor configurations - Added DeviceProcessor to the input and output steps of various processor functions, including make_act_processor, make_diffusion_processor, make_pi0_processor, make_pi0fast_processor, make_sac_processor, make_tdmpc_processor, make_vqbet_processor, and make_smolvla_processor. - Enhanced the DeviceProcessor class with state management methods and ensured compatibility with existing processor pipelines. - Introduced unit tests for DeviceProcessor to validate functionality across different scenarios, including CPU and CUDA operations. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * refactor(pipeline): Remove to() method for device management - Eliminated the to() method from RobotProcessor, which was responsible for moving tensor states to specified devices. - Removed associated unit tests that validated the functionality of the to() method across various scenarios. - Streamlined the pipeline code by focusing on other device management strategies. * feat(processor): Enhance DeviceProcessor with float dtype conversion - Added support for optional float dtype conversion in DeviceProcessor, allowing tensors to be converted to specified floating-point types while preserving non-float types. - Implemented validation for float dtype input and updated the processor's configuration methods to include float dtype. - Refactored tensor processing logic to streamline device movement and dtype conversion. - Introduced comprehensive unit tests to validate the new float dtype functionality across various scenarios. * feat(policies): Add new line processors and update module exports * feat(processor): Enhance batch and device processors to handle index and task_index fields - Added logic to ToBatchProcessor for unsqueezing 0D tensors for index and task_index fields, ensuring they are processed as 1D tensors. - Updated DeviceProcessor to process index and task_index fields in complementary data, preserving their tensor types and ensuring non-tensor fields remain unchanged. - Enhanced unit tests to validate the correct handling of index and task_index fields across various scenarios, including device compatibility and dtype preservation. * refactor(processors): Standardize processor naming conventions - Updated processor names across various files to use a consistent "robot_preprocessor" and "robot_postprocessor" format. - Modified the make_processor functions in factory, act, diffusion, pi0, pi0fast, sac, smolvla, tdmpc, and vqbet to reflect the new naming scheme. - Enhanced the pipeline configuration to align with the updated processor names, improving clarity and maintainability. * refactor(factory): Update processor configuration and type hints - Changed return type of get_policy_class to type[PreTrainedPolicy] for improved type safety. - Enhanced make_processor function to utilize dataset_stats in processor creation for better flexibility. - Updated ProcessorConfigKwargs to include dataset_stats, allowing for more comprehensive processor configurations. - Streamlined processor initialization by removing unnecessary kwargs and ensuring clarity in processor type handling. * Fix eval and android gripper * add some tests * refactor(factory, pi0fast): Update processor function names and parameters - Renamed make_pi0_processor to make_pi0fast_processor for clarity and consistency. - Updated parameter names in the factory's make_processor function to use pretrained_model_name_or_path instead of source, enhancing readability and alignment with naming conventions. * fix(train.py) push postprocessor with preprocessor - Add preprocesser policy overrides for device and rename_map - Add rename_map to DatasetRecordConfig (record.py) * Cleanup pr * fix more git diff pr issues * add path as type in save_pretrained * small nit * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * rename test file * fix: make dataset_features/feature_contract is optional * fix tests * Encorperate pr feedback * clean up record.py * add ascii art, fix normal record * remove merge issues * fix merge * remove features * Add feedback PR * fix last 4 tests * remove features check * rename to transform_features * add transform_features * fix lekiwi eval and update eval api example --------- Signed-off-by: Adil Zouitine <adilzouitinegm@gmail.com> Signed-off-by: Pepijn <138571049+pkooij@users.noreply.github.com> Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com> Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co> * refactor(TokenizerProcessor): improve dependency handling and observation management - Updated TokenizerProcessor to conditionally import AutoTokenizer based on the availability of the transformers library, enhancing flexibility. - Modified tokenizer attribute type to Any to accommodate scenarios where transformers may not be installed. - Improved observation handling by using a more concise approach to manage the transition dictionary, ensuring compatibility with existing data structures. - Added error handling for missing transformers library, providing clear guidance for users on installation requirements. * feat(dependencies): Add scipy as a required dependency - Included `scipy>=1.15.2` in the project dependencies to enhance functionality and support for scientific computing tasks. * feat(policies): convert save_policy_to_safetensors with pipeline * refactor(normalization): remove Normalize and Unnormalize classes - Deleted the Normalize and Unnormalize classes from the normalization module to streamline the codebase. - Updated tests to ensure compatibility with the removal of these classes, focusing on the new NormalizerProcessor and UnnormalizerProcessor implementations. - Enhanced the handling of normalization statistics and improved overall code clarity. * refactor(factory): streamline processor loading by removing unused comments - Removed commented-out code related to loading pretrained processors in the make_processor function. - This change enhances code clarity and maintains focus on the current implementation. * feat(DeviceProcessor): Enhance tensor processing with device detection and float dtype conversion - Improved the _process_tensor method to preserve GPU placement for tensors already on a GPU, facilitating multi-GPU training scenarios. - Introduced a new _detect_device method in TokenizerProcessor to ensure tokenized tensors match the device of existing tensors in transitions. - Added comprehensive unit tests to validate the functionality of device detection and float dtype conversion across various scenarios. * feat(tests): Add comprehensive tests for various policy processors - Introduced new test files for ACT, Classifier, Diffusion, PI0, SAC, SmolVLA, TDMPC, and VQBeT policy processors. - Each test file includes unit tests to validate functionality, including handling of batch sizes, device management, and data type conversions. - Enhanced test coverage to ensure robustness and reliability of processor implementations across different scenarios. * refactor(train): Remove unnecessary tensor device handling in training loop * Refactor`gym_manipulator.py` using the universal pipeline (#1650) * Migrate gym_manipulator to use the pipeline Added get_teleop_events function to capture relevant events from teleop devices unrelated to actions * Added the capability to record a dataset * Added the replay functionality with the pipeline * Refactored `actor.py` to use the pipeline * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * RL works at this commit - fixed actor.py and bugs in gym_manipulator * change folder structure to reduce the size of gym_manip * Refactored hilserl config * Remove dataset and mode from HilSerlEnvConfig to a GymManipulatorConfig to reduce verbose of configs during training * format docs * removed get_teleop_events from abc * Refactor environment configuration and processing pipeline for GymHIL support. Removed device attribute from HILSerlRobotEnvConfig, added DummyTeleopDevice for simulation, and updated processor creation to accommodate GymHIL environments. * Improved typing for HILRobotEnv config and GymManipulator config * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Migrated `gym_manipulator` to use a more modular structure similar to phone teleop * Refactor gripper handling and transition processing in HIL and robot kinematic processors - Updated gripper position handling to use a consistent key format across processors - Improved the EEReferenceAndDelta class to handle reference joint positions. - Added support for discrete gripper actions in the GripperVelocityToJoint processor. - Refactored the gym manipulator to improve modularity and clarity in processing steps. * Added delta_action_processor mapping wrapper * Added missing file delta_action_processor and improved imports in `gym_manipulator` * nit * Added missing file joint_observation_processor * Enhance processing architecture with new teleoperation processors - Introduced `AddTeleopActionAsComplimentaryData` and `AddTeleopEventsAsInfo` for integrating teleoperator actions and events into transitions. - Added `Torch2NumpyActionProcessor` and `Numpy2TorchActionProcessor` for seamless conversion between PyTorch tensors and NumPy arrays. - Updated `__init__.py` to include new processors in module exports, improving modularity and clarity in the processing pipeline. - GymHIL is now fully supported with HIL using the pipeline * Refactor configuration structure for gym_hil integration - Renamed sections for better readability, such as changing "Gym Wrappers Configuration" to "Processor Configuration." - Enhanced documentation with clear examples for dataset collection and policy evaluation configurations. * Enhance reset configuration and teleoperation event handling - Added `terminate_on_success` parameter to `ResetConfig` and `InterventionActionProcessor` for controlling episode termination behavior upon success detection. - Updated documentation to clarify the impact of `terminate_on_success` on data collection for reward classifier training. - Refactored teleoperation event handling to use `TeleopEvents` constants for improved readability and maintainability across various modules. * fix(keyboard teleop), delta action keys * Added transform features and feature contract * Added transform features for image crop * Enum for TeleopEvents * Update tranform_features delta action proc --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * Remove HILEnvConfig references * chore(processor): Add default names for preprocessor and postprocessor in constants - Introduced `PREPROCESSOR_DEFAULT_NAME` and `POSTPROCESSOR_DEFAULT_NAME` constants for consistent naming across various processor implementations. - Updated processor creation in multiple policy files to utilize these constants, enhancing code readability and maintainability. - Modified the training script to load and save the preprocessor and postprocessor using the new constants. * feat(processor): multiple improvements to the pipeline porting (#1749) * [Port codebase pipeline] General fixes for RL and scripts (#1748) * Refactor dataset configuration in documentation and codebase - Updated dataset configuration keys from `dataset_root` to `root` and `num_episodes` to `num_episodes_to_record` for consistency. - Adjusted replay episode handling by renaming `episode` to `replay_episode`. - Enhanced documentation - added specific processor to transform from policy actions to delta actions * Added Robot action to tensor processor Added new processor script for dealing with gym specific action processing * removed RobotAction2Tensor processor; imrpoved choosing observations in actor * nit in delta action * added missing reset functions to kinematics * Adapt teleoperate and replay to pipeline similar to record * refactor(processors): move to inheritance (#1750) * fix(teleoperator): improvements phone implementation (#1752) * fix(teleoperator): protect shared state in phone implementation * refactor(teleop): separate classes in phone * fix: solve breaking changes (#1753) * refactor(policies): multiple improvements (#1754) * refactor(processor): simpler logic in device processor (#1755) * refactor(processor): euclidean distance in delta action processor (#1757) * refactor(processor): improvements to joint observations processor migration (#1758) * refactor(processor): improvements to tokenizer migration (#1759) * refactor(processor): improvements to tokenizer migration * fix(tests): tokenizer tests regression from #1750 * fix(processors): fix float comparison and config in hil processors (#1760) * chore(teleop): remove unnecessary callbacks in KeyboardEndEffectorTeleop (#1761) * refactor(processor): improvements normalize pipeline migration (#1756) * refactor(processor): several improvements normalize processor step * refactor(processor): more improvements normalize processor * refactor(processor): more changes to normalizer * refactor(processor): take a different approach to DRY * refactor(processor): final design * chore(record): revert comment and continue deleted (#1764) * refactor(examples): pipeline phone examples (#1769) * refactor(examples): phone teleop + teleop script * refactor(examples): phone replay + replay * chore(examples): rename phone example files & folders * feat(processor): fix improvements to the pipeline porting (#1796) * refactor(processor): enhance tensor device handling in normalization process (#1795) * refactor(tests): remove unsupported device detection test for complementary data (#1797) * chore(tests): update ToBatchProcessor test (#1798) * refactor(tests): remove in-place mutation tests for actions and complementary data in batch processor * test(tests): add tests for action and task processing in batch processor * add names for android and ios phone (#1799) * use _tensor_stats in normalize processor (#1800) * fix(normalize_processor): correct device reference for tensor epsilon handling (#1801) * add point 5 add missing feature contracts (#1806) * Fix PR comments 1452 (#1807) * use key to determine image * Address rest of PR comments * use PolicyFeatures in transform_features --------- Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com> --------- Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co> Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com> Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com> * refactor(constants, processor): standardize action and observation keys across multiple files (#1808) - Added new constants for truncated and done states in constants.py. - Updated references to action and observation keys in pipeline_features.py, converters.py, hil_processor.py, tokenizer_processor.py, and robot_kinematic_processor.py to use the new constants for improved readability and maintainability. * refactor(processor): improve processor pipeline typing with generic type (#1810) * refactor(processor): introduce generic type for to_output - Always return `TOutput` - Remove `_prepare_transition`, so `__call__` now always returns `TOutput` - Update tests accordingly - This refactor paves the way for adding settings for `to_transition` and `to_output` in `make_processor` and the post-processor * refactor(processor): consolidate ProcessorKwargs usage across policies - Removed the ProcessorTypes module and integrated ProcessorKwargs directly into the processor pipeline. - Updated multiple policy files to utilize the new ProcessorKwargs structure for preprocessor and postprocessor arguments. - Simplified the handling of processor kwargs by initializing them to empty dictionaries when not provided. * refactor(converters): implement unified tensor conversion function (#1830) - Introduced `to_tensor` function using `singledispatch` to handle various input types, including scalars, arrays, and dictionaries, converting them to PyTorch tensors. - Replaced previous tensor conversion logic in `gym_action_processor`, `normalize_processor`, and `test_converters` with the new `to_tensor` function for improved readability and maintainability. - Updated tests to cover new functionality and ensure correct tensor conversion behavior. * Revert "refactor(converters): implement unified tensor conversion function (#…" (#1840) This reverts commit a837685bf870919fc07ada287a71711cebabb1ea. * refactor(converters): implement unified tensor conversion function (#1841) - Introduced `to_tensor` function using `singledispatch` to handle various input types, including scalars, arrays, and dictionaries, converting them to PyTorch tensors. - Replaced previous tensor conversion logic in `gym_action_processor`, `normalize_processor`, and `test_converters` with the new `to_tensor` function for improved readability and maintainability. - Updated tests to cover new functionality and ensure correct tensor conversion behavior. Co-authored-by: AdilZouitine <adilzouitinegm@gmail.com> * refactor(converters): gather converters and refactor the logic (#1833) * refactor(converters): move batch transition functions to converters module - Moved `_default_batch_to_transition` and `_default_transition_to_batch` functions from `pipeline.py` to `converters.py` for better organization and separation of concerns. - Updated references in `RobotProcessor` to use the new location of these functions. - Added tests to ensure correct functionality of the transition functions, including handling of index and task_index fields. - Removed redundant tests from `pipeline.py` to streamline the test suite. * refactor(processor): reorganize EnvTransition and TransitionKey definitions - Moved `EnvTransition` and `TransitionKey` classes from `pipeline.py` to a new `core.py` module for better structure and maintainability. - Updated import statements across relevant modules to reflect the new location of these definitions, ensuring consistent access throughout the codebase. * refactor(converters): rename and update dataset frame conversion functions - Replaced `to_dataset_frame` with `transition_to_dataset_frame` for clarity and consistency in naming. - Updated references in `record.py`, `pipeline.py`, and tests to use the new function name. - Introduced `merge_transitions` to streamline the merging of transitions, enhancing readability and maintainability. - Adjusted related tests to ensure correct functionality with the new naming conventions. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * fix(processor): solve conflict artefacts * refactor(converters): remove unused identity function and update type hints for merge_transitions * refactor(processor): remove unused identity import and clean up gym_manipulator.py --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Steven Palma <steven.palma@huggingface.co> * refactor(processors): add transform_features method to various processors (#1843) * refactor(processors): update transition handling in RewardClassifierProcessor and InverseKinematicsEEToJoints (#1844) * refactor(processors): unify import statements by consolidating pipeline imports into the main processor module (#1845) * refactor(processors): add extended api for specialized pipelines (#1848) * refactor(processors): enhance transform_features method across multiple processors (#1849) * refactor(processors): enhance transform_features method across multiple processors - Updated the transform_features method in various processors to utilize a copy of the features dictionary, ensuring immutability of the original features. - Added handling for new feature keys and removed obsolete ones in the MapTensorToDeltaActionDict, JointVelocityProcessor, and others. - Improved readability and maintainability by following consistent patterns in feature transformation. * refactor(processors): standardize action and observation keys in delta_action_processor and joint_observations_processor - Updated action and observation keys to use constants for improved readability and maintainability. - Refactored the transform_features method in multiple processors to ensure consistent handling of feature keys. - Enhanced error handling by raising exceptions for missing required components in action and observation processing. - Removed obsolete code and improved overall structure for better clarity. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * refactor(processors): remove unused import in joint_observations_processor * refactor(processors): simplify transform_features method in delta_action_processor * refactor(processors): streamline transform_features method in ImageCropResizeProcessor * refactor(processors): improve error handling and streamline transform_features method in phone_processor - Raised a ValueError for missing position and rotation in action to enhance error handling. * refactor(processors): enhance error handling in JointVelocityProcessor - Added a ValueError raise for missing current joint positions in the observation method to improve error handling and ensure the integrity of the transform_features method. * refactor(processors): simplify transform_features method in robot kinematic processors * refactor(processors): standardize action keys in phone_processor * fix(processor): RKP feature obs -> act --------- Signed-off-by: Adil Zouitine <adilzouitinegm@gmail.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Steven Palma <steven.palma@huggingface.co> * chore(processor): rename RobotProcessor -> DataProcessorPipeline (#1850) * chore(processor): rename specialized processor -> XYZProcessorStep (#1852) * chore(processor): rename converters function names (#1853) * chore(processor): rename to_transition_teleop_action -> action_to_transition * chore(processor): rename to_transition_robot_observation -> observation_to_transition * chore(processor): rename to_output_robot_action -> transition_to_robot_action * chore(processor): add Step suffix to all processors (#1854) * refactor(processor): rename MapDeltaActionToRobotAction and MapTensorToDeltaActionDict for consistency * refactor(processor): rename DeviceProcessor to DeviceProcessorStep for consistency across modules * refactor(processor): rename Torch2NumpyActionProcessor to Torch2NumpyActionProcessorStep for consistency * refactor(processor): rename Numpy2TorchActionProcessor to Numpy2TorchActionProcessorStep for consistency * refactor(processor): rename AddTeleopActionAsComplimentaryData to AddTeleopActionAsComplimentaryDataStep for consistency * refactor(processor): rename ImageCropResizeProcessor and AddTeleopEventsAsInfo for consistency * refactor(processor): rename TimeLimitProcessor to TimeLimitProcessorStep for consistency * refactor(processor): rename GripperPenaltyProcessor to GripperPenaltyProcessorStep for consistency * refactor(processor): rename InterventionActionProcessor to InterventionActionProcessorStep for consistency * refactor(processor): rename RewardClassifierProcessor to RewardClassifierProcessorStep for consistency * refactor(processor): rename JointVelocityProcessor to JointVelocityProcessorStep for consistency * refactor(processor): rename MotorCurrentProcessor to MotorCurrentProcessorStep for consistency * refactor(processor): rename NormalizerProcessor and UnnormalizerProcessor to NormalizerProcessorStep and UnnormalizerProcessorStep for consistency * refactor(processor): rename VanillaObservationProcessor to VanillaObservationProcessorStep for consistency * refactor(processor): rename RenameProcessor to RenameProcessorStep for consistency * refactor(processor): rename TokenizerProcessor to TokenizerProcessorStep for consistency * refactor(processor): rename ToBatchProcessor to AddBatchDimensionProcessorStep for consistency * refactor(processor): update config file name in test for RenameProcessorStep consistency * refactor(processor): rename internal tokenizer variable for clarity (#1855) - Changed the internal tokenizer variable name from `_tokenizer` to `input_tokenizer` for improved readability and consistency. - Updated references throughout the class to reflect the new variable name. * chore(processor): rename merge_features -> combine_feature_dicts (#1856) * refactor(processor): rename internal device variable for clarity (#1857) - Changed the internal device variable from `_device` to `tensor_device` for improved readability and consistency. - Updated references throughout the class to reflect the new variable name. * chore(processor): rename teleop_phone variable names (#1858) * chore(processor): add type alias RobotProcessorPipeline and PolicyProcessorPipeline (#1859) * feat(processor): introduce PolicyProcessorPipeline and RobotProcessorPipeline as type aliases for DataProcessorPipeline - Added PolicyProcessorPipeline and RobotProcessorPipeline type aliases to enhance clarity and maintainability in the processor module. - Updated the __all__ list to include the new pipelines for better module export consistency. * refactor(processor): replace DataProcessorPipeline with PolicyProcessorPipeline across multiple modules - Updated all instances of DataProcessorPipeline to PolicyProcessorPipeline in various processor files for consistency and clarity. - Adjusted function signatures to reflect the new pipeline type, enhancing maintainability and readability. * refactor(processor): update hotswap_stats function to use PolicyProcessorPipeline - Changed the parameter name from robot_processor to policy_processor for clarity. - Ensured consistency with recent updates to the processor module by reflecting the new pipeline type in the function signature. * refactor(processor): replace DataProcessorPipeline with PolicyProcessorPipeline in migrate_policy_normalization.py - Updated the preprocessor and postprocessor to use PolicyProcessorPipeline for consistency with recent changes in the processor module. - Enhanced clarity and maintainability by aligning with the new pipeline structure. * refactor(processor): update hotswap_stats to use PolicyProcessorPipeline - Changed the parameter type in hotswap_stats from DataProcessorPipeline to PolicyProcessorPipeline for consistency with recent updates. - Enhanced clarity by updating the function documentation to reflect the new pipeline type. * refactor(processor): replace DataProcessorPipeline with RobotProcessorPipeline across multiple files - Updated instances of DataProcessorPipeline to RobotProcessorPipeline in evaluate.py, record.py, replay.py, teleoperate.py, and other relevant files for consistency and clarity. - Adjusted function signatures and variable types to reflect the new pipeline structure, enhancing maintainability and readability. * refactor(processor): enforce config_filename requirement for HF Hub loading (#1860) - Updated the DataProcessorPipeline to require a specific config_filename when loading from Hugging Face Hub, enhancing clarity and preventing errors. - Simplified local path checks and improved error handling for invalid paths. - Adjusted tests to reflect the new requirement and ensure proper error handling for various loading scenarios. * feat(record): add transition features to dataset and handle scalar vs array formatting in converters (#1861) - Introduced new transition features (`next.reward`, `next.done`, `next.truncated`) in the dataset during recording. - Updated the `transition_to_dataset_frame` function to handle scalar values correctly, ensuring compatibility with expected array formats for reward, done, and truncated features. * refactor(pipeline): enforce ProcessorStep inheritance for pipeline steps (#1862) - Updated the DataProcessorPipeline to require that all steps inherit from ProcessorStep, enhancing type safety and clarity. - Adjusted tests to utilize a MockTokenizerProcessorStep that adheres to the ProcessorStep interface, ensuring consistent behavior across tests. - Refactored various mock step classes in tests to inherit from ProcessorStep for improved consistency and maintainability. * refactor(dependencies): remove scipy dependency and introduce custom rotation utilities (#1863) - Removed the scipy dependency from the project to streamline requirements. - Added a new `rotation.py` module containing a custom `Rotation` class that replicates essential functionalities of `scipy.spatial.transform.Rotation`, allowing for rotation vector, matrix, and quaternion conversions without external dependencies. - Updated the `robot_kinematic_processor.py` to utilize the new custom rotation utilities. * feat(teleoperation): introduce HasTeleopEvents protocol and enhance teleop event handling (#1866) - Added the HasTeleopEvents protocol to define a standard for teleoperators that provide control events. - Implemented a runtime check to ensure teleoperators implement the get_teleop_events() method. - Updated AddTeleopEventsAsInfoStep to utilize the new protocol, enhancing compatibility with custom teleoperators. - Improved documentation for clarity on teleoperation event extraction and compatibility with built-in teleoperators. * fix(deps): use in-house rotation utils over scipy throughout the codebase * refactor(constants): rename preprocessor and postprocessor constants for clarity (#1868) - Updated constant names from PREPROCESSOR_DEFAULT_NAME and POSTPROCESSOR_DEFAULT_NAME to POLICY_PREPROCESSOR_DEFAULT_NAME and POLICY_POSTPROCESSOR_DEFAULT_NAME for better context. - Adjusted references across multiple files to use the new constant names, ensuring consistency in the codebase. * refactor(tests): update processor test assertions to reflect new preprocessor and postprocessor names (#1869) - Changed assertions in multiple processor test files to verify the updated names from "robot_preprocessor" and "robot_postprocessor" to "policy_preprocessor" and "policy_postprocessor" for consistency with recent refactoring. * refactor(utils): simplify log_rerun_data function (#1864) * refactor(logging): enhance log_rerun_data to handle observation and action separately - Updated the `log_rerun_data` function to accept and log observation and action data more clearly, improving readability and maintainability. - Refactored the `record_loop` and `teleop_loop` functions to extract and pass observation and action data to `log_rerun_data`, ensuring consistent logging format. * refactor(tests): update test_log_rerun_data to align with log_rerun_data changes - Modified test cases in `test_visualization_utils.py` to extract and pass observation and action data separately to `log_rerun_data`, improving clarity and consistency with recent function updates. - Ensured that the tests reflect the new structure of `log_rerun_data` for better maintainability. * refactor(processors): simplify calls to log_rerun + replace lambda functions with identity_transition --------- Co-authored-by: Steven Palma <steven.palma@huggingface.co> * fix(processor): recover type inference for use of processors (#1873) * refactor(processors): Improve Normalization Processor Performance and Device/Dtype Adaptability (#1880) * refactor(processors): reorder processor steps for consistency across implementations - Updated the order of processor steps in multiple files to ensure consistency, placing AddBatchDimensionProcessorStep and DeviceProcessorStep before NormalizerProcessorStep. - Adjusted related test assertions to reflect the new order of steps in the preprocessor, enhancing clarity and maintainability. * refactor(normalization): remove dtype specification in tensor conversion for adaptation logic - Updated tensor conversion in the _NormalizationMixin class to remove explicit dtype specification, allowing for automatic adaptation of tensor types. - Adjusted related tests to ensure proper functionality with the new tensor conversion logic, verifying that normalizers adapt correctly to input types. * chore(docs): update doctrines pipeline files (#1872) * docs(processor): update docstrings batch_processor * docs(processor): update docstrings device_processor * docs(processor): update docstrings tokenizer_processor * update docstrings processor_act * update docstrings for pipeline_features * update docstrings for utils * update docstring for processor_diffusion * update docstrings factory * add docstrings to pi0 processor * add docstring to pi0fast processor * add docstring classifier processor * add docstring to sac processor * add docstring smolvla processor * add docstring to tdmpc processor * add docstring to vqbet processor * add docstrings to converters * add docstrings for delta_action_processor * add docstring to gym action processor * update hil processor * add docstring to joint obs processor * add docstring to migrate_normalize_processor * update docstrings normalize processor * update docstring normalize processor * update docstrings observation processor * update docstrings rename_processor * add docstrings robot_kinematic_processor * cleanup rl comments * add docstring to train.py * add docstring to teleoperate.py * add docstrings to phone_processor.py * add docstrings to teleop_phone.py * add docstrings to control_utils.py * add docstrings to visualization_utils.py --------- Co-authored-by: Pepijn <pepijn@huggingface.co> * refactor(eval): integrate preprocessor and postprocessor into rollout and eval_policy functions (#1900) * refactor(eval): integrate preprocessor and postprocessor into rollout and eval_policy functions - Updated the `rollout` and `eval_policy` functions to accept preprocessor and postprocessor parameters, enhancing the flexibility of the evaluation pipeline. - Adjusted the implementation to apply preprocessing and postprocessing steps during policy evaluation, improving the overall data handling and processing flow. * refactor(eval): remove redundant observation device conversion in rollout function - Eliminated unnecessary device conversion for the observation dictionary within the `rollout` function, streamlining the code and enhancing readability. - This change simplifies the observation handling process, aligning with the preference for clearer solutions. * debug * refactor(utils): enhance task handling in add_envs_task function - Improved the `add_envs_task` function to validate the output of `task_description` and `task` calls, ensuring they return lists of strings. - Removed the use of `else` statement for environments without language instructions, simplifying the logic and enhancing readability. - Streamlined the observation dictionary handling by ensuring consistent data types for task attributes. * refactor(converters): rename _from_tensor to from_tensor_to_numpy for clarity (#1902) - Updated the function name from _from_tensor to from_tensor_to_numpy to better reflect its purpose of converting PyTorch tensors to numpy arrays or scalars. - Adjusted all references to the renamed function throughout the codebase to maintain consistency. - Enhanced the _NormalizationMixin class to reconstruct the stats dictionary from tensor stats using the new function, ensuring compatibility after loading state dicts. - Added tests to verify the correct reconstruction of stats and functionality of methods dependent on self.stats after loading. * refactor(pipeline): feature contract now categorizes between OBS or Action (#1867) * refactor(processor): signature of transform_features * refactor(processor): remove prefixes + processor respect new transform_features signature + update test accordingly * refactor(processor): rename now is only for visual * refactor(processor): update normalize processor * refactor(processor): update vanilla processor features * refactor(processor): feature contract now uses its own enum * chore(processor): rename renameprocessor * chore(processor): minor changes * refactor(processor): add create & change aggregate * refactor(processor): update aggregate * refactor(processor): simplify to functions, fix features contracts and rename function * test(processor): remove to converter tests as now they are very simple * chore(docs): recover docs joint observations processor * fix(processor): update RKP * fix(tests): recv diff test_pipeline * chore(tests): add docs to test * chore(processor): leave obs language constant untouched * fix(processor): correct new shape of feature in crop image processor * refactor(eval): specify type parameters for preprocessor and postprocessor in eval_policy function (#1904) * chore(processor): remove action prefixes (#1905) * test(processor): all processors use now the same create_transition (#1906) * test(processor): all processors use now the same create_transition * test(processor): use identity instead of lambda for transition in pipelines * fix(processor): specialized processors respect contract by raising if none (#1909) * fix(processor): specialized processor now raise * test(processor): fix tests for now raise specialized processors * test(processor): use identity in newly introduced pipeline * refactor(processor): clarify action types, distinguish PolicyAction, RobotAction, and EnvAction (#1908) * refactor(processor): split action from policy, robots and environment - Updated function names to robot_action_to_transition and robot_transition_to_action across multiple files to better reflect their purpose in processing robot actions. - Adjusted references in the RobotProcessorPipeline and related components to ensure compatibility with the new naming convention. - Enhanced type annotations for action parameters to improve code readability and maintainability. * refactor(converters): rename robot_transition_to_action to transition_to_robot_action - Updated function names across multiple files to improve clarity and consistency in processing robot actions. - Adjusted references in RobotProcessorPipeline and related components to align with the new naming convention. - Simplified action handling in the AddBatchDimensionProcessorStep by removing unnecessary checks for action presence. * refactor(converters): update references to transition_to_robot_action - Renamed all instances of robot_transition_to_action to transition_to_robot_action across multiple files for consistency and clarity in the processing of robot actions. - Adjusted the RobotProcessorPipeline configurations to reflect the new naming convention, enhancing code readability. * refactor(processor): update Torch2NumpyActionProcessorStep to extend ActionProcessorStep - Changed the base class of Torch2NumpyActionProcessorStep from PolicyActionProcessorStep to ActionProcessorStep, aligning it with the current architecture of action processing. - This modification enhances the clarity of the class's role in the processing pipeline. * fix(processor): main action processor can take also EnvAction --------- Co-authored-by: Steven Palma <steven.palma@huggingface.co> * refactor(processor): phone processor is now an RobotActionProcessorStep * fix(processor): use subprocessors in AddBatchDimensionProcessorStep only if we have the ingredients * fix(robots): remove action prefix hard-coded in teleop keyboard and gamepad * feat(processor): enhance type safety with generic DataProcessorPipeline for policy and robot pipelines (#1915) * refactor(processor): enhance type annotations for processors in record, replay, teleoperate, and control utils - Updated type annotations for preprocessor and postprocessor parameters in record_loop and predict_action functions to specify the expected dictionary types. - Adjusted robot_action_processor type in ReplayConfig and TeleoperateConfig to improve clarity and maintainability. - Ensured consistency in type definitions across multiple files, enhancing overall code readability. * refactor(processor): enhance type annotations for RobotProcessorPipeline in various files - Updated type annotations for RobotProcessorPipeline instances in evaluate.py, record.py, replay.py, teleoperate.py, and other related files to specify input and output types more clearly. - Introduced new type conversions for PolicyAction and EnvTransition to improve type safety and maintainability across the processing pipelines. - Ensured consistency in type definitions, enhancing overall code readability and reducing potential runtime errors. * refactor(processor): update transition handling in processors to use transition_to_batch - Replaced direct transition handling with transition_to_batch in various processor tests and implementations to ensure consistent batching of input data. - Updated assertions in tests to reflect changes in data structure, enhancing clarity and maintainability. - Improved overall code readability by standardizing the way transitions are processed across different processor types. * refactor(tests): standardize transition key usage in processor tests - Updated assertions in processor test files to utilize the TransitionKey for action references, enhancing consistency across tests. - Replaced direct string references with TransitionKey constants for improved readability and maintainability. - Ensured that all relevant tests reflect these changes, contributing to a more uniform approach in handling transitions. * refactor(processor): unify action imports and enhance type clarity across multiple files - Updated imports in various files to include RobotAction and PolicyAction directly from the processor module, improving clarity and consistency. - Removed redundant imports from core, streamlining the codebase and enhancing maintainability. - Adjusted type annotations and references in the RobotProcessorPipeline and related components to align with the new import structure, ensuring better type safety and readability. * refactor(processor): migrate policy normalization to use factory functions - Updated the migration script to utilize `make_pre_post_processors` and `make_policy_config` from `lerobot.policies.factory`, enhancing consistency with the current codebase. - Improved normalization statistics extraction and processor pipeline creation, ensuring compatibility with the new `PolicyProcessorPipeline` architecture. - Cleaned up configuration handling by removing unnecessary fields and adding normalization mapping directly to the config. - Enhanced type safety and readability by refining feature type and normalization mode handling. * debug(scripts): simplify record with processors (#1918) Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com> * refactor(processor): update migration script for policy normalization and hub integration - Modified the migration script to include a branch argument for pushing to the hub, enhancing flexibility in version control. - Improved error handling by ensuring the policy type is extracted from the configuration, promoting robustness. - Streamlined the process of saving and pushing model components to the hub, allowing for a single commit with optional PR creation. - Updated the commit message and description for better clarity on the migration changes and benefits, ensuring users are informed of the new architecture and usage. * fixes for processors used in phone teleop * fixes for rotation matrix * add empty obs and act in create_initial_features * use observation instead of obs * docs(processor): update docstrings pipeline (#1920) * chore(docs): Processor doc (#1685) * chore(docs): initialize doc * Added script for the second part of the processor doc * precommit style nit * improved part 2 of processor guide * Add comprehensive documentation for processors in robotics - Introduced a detailed guide on processors, covering their role in transforming raw robot data into model-ready inputs and vice versa. - Explained core concepts such as EnvTransition, ProcessorStep, and RobotProcessor, along with their functionalities. - Included examples of common processor steps like normalization, device management, batch processing, and text tokenization. - Provided insights on building complete pipelines, integrating processors into training loops, and saving/loading configurations. - Emphasized best practices and advanced features for effective usage of processors in robotics applications. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * feat(docs): Enhance introduction to processors with additional converter functions - Updated the introduction to processors documentation to include default batch-to-transition and transition-to-batch converters. - Added detailed descriptions and examples for new specialized converter functions: `to_transition_teleop_action`, `to_transition_robot_observation`, `to_output_robot_action`, and `to_dataset_frame`. - Improved clarity on how these converters facilitate integration with existing robotics applications. * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Improved doc implement_your_own_pipeline - Use normalization processor as default example - Add section on transform features - Add section on overrides. * Add phone docs and use pipeline for robots/teleop docs * Fix typo in documentation for adapters in robots/teleop section * Enhance documentation for processors with detailed explanations and examples - Updated the introduction to processors, clarifying the role of `EnvTransition` and `ProcessorStep`. - Introduced `DataProcessorPipeline` as a generic orchestrator for chaining processor steps. - Added comprehensive descriptions of new converter functions and their applications. - Improved clarity on type safety and the differences between `RobotProcessorPipeline` and `PolicyProcessorPipeline`. - Included examples for various processing scenarios, emphasizing best practices for data handling in robotics. * Enhance documentation for processor migration and debugging - Added detailed sections on the migration of models to the new `PolicyProcessorPipeline` system, including breaking changes and migration scripts. - Introduced a comprehensive guide for debugging processor pipelines, covering common issues, step-by-step inspection, and runtime monitoring techniques. - Updated examples to reflect new usage patterns and best practices for processor implementation and error handling. - Clarified the role of various processor steps and their configurations in the context of robotics applications. --------- Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Pepijn <pepijn@huggingface.co> * docs: Add new section for debugging processor pipelines - Introduced a new documentation entry for debugging processor pipelines, enhancing the existing guide on processors. - This addition aims to provide users with insights and best practices for troubleshooting and optimizing their processor workflows. * fix(processor): phone examples (#1921) * fix(processor): phone examples * chore(processor): simplify gripper in phone example kinematic chain --------- Co-authored-by: Steven Palma <steven.palma@huggingface.co> * refactor(processors): several additions (#1926) * chore(processor): remove merge_transitions functions (#1925) * refactor(processors): move processors out of configs (#1927) * chore(processor): streamline combine_features_dict (#1928) * chore(policies): use new constants (#1929) * fix(deps): right version transformers (#1930) * fix(tests): add none + disable async tests for now (#1931) * refactor(processor): transform_features loop + EAFP (#1932) * fix(processors): make sure nested dict are also shallow copied (#1939) * refactor(processor): replace ModelHubMixin with HubMixin and enhance save_pretrained method (#1937) - Updated DataProcessorPipeline to use HubMixin instead of ModelHubMixin for improved functionality. - Refactored save_pretrained method to handle saving * refactor(docs): streamline monitoring hooks and enhance performance reporting - Removed the log_shapes and measure_performance hooks, simplifying the monitoring process to focus on NaN checks. - Updated performance reporting to include maximum processing times alongside average times for better insights. - Clarified documentation regarding the processing pipeline and feature transformations. * fix teleop, record and eval (#1940) * fix cmd record, eval * chore(processor): update input output of main 3 processors for better semantics (#1942) * chore(processor): update input output of main 3 processors for better semantics * refactor(processor): replace Any with RobotObservation for improved type safety in processors * fix(processors): no PolicyObservation * chore(processor): update with RobotObservation * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: AdilZouitine <adilzouitinegm@gmail.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> * test(processor): fix batch expectation * feat(example): Add SO100 EE pipeline control (teleop+record) (#1943) * feat(examples): add ee so100 processors teleop & record * refactor(processor): improve FK processor for better use compatability * docs(processor): enhance tutorial on implementing custom processors - Updated the tutorial to use `NormalizerProcessorStep` as the primary example, clarifying its role in normalizing observations and actions. - Improved explanations of the need for custom processors, emphasizing data compatibility and processing requirements. - Added code snippets demonstrating the normalization process and the configuration of processor pipelines. - Enhanced the introduction to processors, detailing their function as translators between raw robot data and model inputs. - Included examples of real-world processor configurations for both training and inference scenarios. * docs(debug): enhance debugging guide for processor pipelines - Streamlined the introduction to clarify the challenges of debugging complex processor pipelines. - Expanded the section on hooks, detailing their purpose and implementation for runtime monitoring. - Introduced step-by-step debugging techniques, emphasizing the use of the `step_through()` method for inspecting intermediate states. - Added examples of feature validation to ensure data structure contracts are met. - Consolidated best practices for debugging, highlighting the synergy between hooks, step-through debugging, and feature validation. * chore(processors): tokenizers raises and remove tensor conversion (#1949) * chore(processor): remove unused transition_features dict * feat(ee): add so100_to_so100_EE replay and evaluate examples * chore(examples): homogenize style across example files (#1955) * chore(examples): homogenize style across example files * chore(examples): homogenize style across example files eval + replay * chore(examples): homogenize headers * test(async): fix feature manipulation (#1957) * test(async): fix feature manipulation * chore(processor): remove unused functions * fix(processor): Preserve stats overrides in normalizer load_state_dict and fix training resumption (#1958) * feat(processor): enhance normalization handling and state management - Added support for additional normalization modes including IDENTITY. - Introduced a new function `clean_state_dict` to remove specific substrings from state dict keys. - Implemented preservation of explicitly provided normalization statistics during state loading. - Updated training script to conditionally provide dataset statistics based on resume state. - Expanded tests to verify the correct behavior of stats override preservation and loading. * fix(train): remove redundant comment regarding state loading - Removed a comment that noted the preprocessor and postprocessor state is already loaded when resuming training, as it was deemed unnecessary for clarity. * test(processor): update tests to handle missing or invalid task keys - Modified tests to assert that the processor raises appropriate exceptions when the task key is missing or has an invalid value in the complementary data. - Ensured that the tests cover cases for None, integer, and mixed list task values, improving robustness against invalid inputs. * fix(processor): enforce signatures * chore(processor): update comments in record.py * test(processor): fix isinstance and cuda test * modify phone docs * fix(processor): reorder output steps to ensure correct processing sequence (#1961) - Moved DeviceProcessorStep to the end of the output steps in multiple processor files to maintain the intended processing order. - Updated corresponding tests to reflect the change in step order. * fix(processors): assumptions for robot_action_processor & teleop_action_processor (#1964) * fix(processors): new assumptions pipeline * fix(processors): ee jj phone teleop replay record working * chore(processors): update comments and default vars * chore(processor): remove unnecessary copy * chore(processor): added todo assumption gripper * fix(processors): eval using detected device * finish phone docs * fix correct image link * feat(processor): implement migration detection and error handling for processor configurations (#1968) * feat(processor): implement migration detection and error handling for processor configurations - Added ProcessorMigrationError to handle migration requirements for old model formats. - Enhanced DataProcessorPipeline.from_pretrained to include robust migration detection logic. - Implemented methods for resolving configuration sources, validating loaded configs, and checking for valid processor configurations. - Introduced comprehensive tests for migration detection and configuration validation to ensure correct behavior. * refactor(processor): simplify loading logic and enhance migration detection - Refactored DataProcessorPipeline to implement a simplified three-way loading strategy for configuration files. - Introduced explicit config_filename parameter to avoid ambiguity during loading. - Updated ProcessorMigrationError to provide clearer error messages for migration requirements. - Enhanced tests to cover new loading logic and ensure proper migration detection. - Removed deprecated methods related to config source resolution. * fix(processor) RL (#1953) * fix(gym_manipulator) general fixes to make it compitable * fix for dataset v3.0 * fix for gym_manipulator * add map policy action to robot action wrappers in a seperate scripts * added unittest for policy to robot bridge * fixes for gripper penalty * fix style * fix gamepad controller * fixes for sim teleop * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * modify numpy2torch to a regular processor as a quick fix * missing imports?! * - Removed the use of `AddRobotObservationAsComplimentaryData` from `gym_manipulator` and thus the codebase - Added get_raw_joint_positions functions to RobotEnv - Pass raw_joint_positions as input to the action_pipeline in `gym_manipulator` - Add `InverseKinematicsRLStep` to be tailored towards the need of RL which requires the use of the IK solution as the main reference point of the control loop - Added the option `use_ik_solution` in `EEReferenceDelta` step to rely on the ik solution rather than the joint values * -Updated links to all the config files to place them in the new repo with configs compatible with the pipeline --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Steven Palma <imstevenpmwork@ieee.org> * fix(tests): update test cases for loading pipelines with specific config filenames - Modified test cases to include explicit configuration filenames when loading pipelines in `test_policy_robot_bridge.py`. - Ensured that the tests reflect the correct loading behavior for both robot-to-policy and policy-to-robot transitions. * fix(examples): train mps processor (#1970) * fix(examples): train mps processor * fix(processor): add MPS compatibility for float64 tensors - Implemented a workaround to convert float64 tensors to float32 when using the MPS device, as MPS does not support float64. - Added unit tests to verify the automatic conversion of float64 tensors to float32 and ensure compatibility with various tensor types on the MPS device. --------- Co-authored-by: AdilZouitine <adilzouitinegm@gmail.com> --------- Signed-off-by: Adil Zouitine <adilzouitinegm@gmail.com> Signed-off-by: Pepijn <138571049+pkooij@users.noreply.github.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Co-authored-by: Simon Alibert <75076266+aliberts@users.noreply.github.com> Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com> Co-authored-by: Steven Palma <imstevenpmwork@ieee.org> Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co> Co-authored-by: Steven Palma <steven.palma@huggingface.co> Co-authored-by: Pepijn <pepijn@huggingface.co>
2025-09-18 15:25:26 +02:00
"lerobot[phone]",
"lerobot[libero]; sys_platform == 'linux'",
"lerobot[metaworld]",
Add basic PEFT support to train script + record module (#1411) * Add basic support for PEFT adapter methods This changes adds support for training policies with much less parameters by applying adapter methods such as LoRA on specific parts of the policies and therefore possibly higher learning rates / batch sizes. To make this as accessible as possible I thought it useful to provide defaults for `target_modules` and `modules_to_save`. Currently only SmolVLA has such defaults but when we agree that this change is useful I will set out to generate more such defaults. While the user can override these settings, they are expected to only change the peft_method, rank and init_type parameters. * Implement loading of PEFT adapters Loading a PEFT adapter is currently done by initializing a policy with default config and then applying the adapter on the resulting model. This has the obvious drawback that any configurations done during training are not applied in the adapted model. Currently the `use_peft` attribute of `PreTrainedConfig` is only set during loading to signal the following code that it has to deal with a PEFT adapter. However we could imagine a scenario where this is already set at training time and stored alongside the adapter. * Store policy config alongside PEFT checkpoint Before this change the PEFT-wrapped policy did not save the policy's config alongside the adapter config / weights which prevented us from changing the policy config. Now the policy config is saved both in full training and PEFT training. This change makes loading the PEFT policy adapter much easier as well. * Add default config for ACT * Support targets like `all-linear` * Formatting * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix failing tests * Remove PEFT compatibility changes in config We'll wait for the PEFT release that fixes this for good. * Remove `use_peft` parameter from training script Instead we make the PEFT config optional which has the same effect. * Log adapter config to WandB * Better documentation for CLI arguments * Don't unload & merge the PEFT model This can make things hard when using quantized layers (user expects quantized base layers with unquantized adapters for example, merging defaults to upcast the layers leading to higher memory). * Correct way of identifying when to save config * Add CLI end-to-end tests Currently there don't seem to be any way to test the CLI commands. Since this change mostly happens in those I thought it best to add a way to test these commands end-to-end. More integrated commands like `lerobot-record` need patching but standalone commands like training seem to work fine. * Update default targets Removed ACT since it doesn't make sense to fine-tune ACT without having it pretrained beforehand. SmolVLA and Pi0/0.5 are much more senseful targets. * Clean up loading code - Centralized instantiation of the PEFT wrapper in `make_policy` for inference (e.g. in `lerobot-record`) - Training a PEFT policy also sets `cfg.use_peft` so that all inference code loading the policy can rely on that attribute to identify if PEFT loading is needed - Modified RTC example to also include PEFT policies. Mostly because this is an example I'm currently exploring. * Make sure push_to_hub works Since PEFT only wraps `push_to_hub` and not `push_model_to_hub`, the reference to `self` in `policy.push_model_to_hub` is the unwrapped policy which, of course, doesn't know anything about PEFT. To make the upload process aware of PEFT, we pass the unwrapped policy down to `push_model_to_hub` as a kwarg. This is not ideal but I think it is the best way for now. * formatting * Warn when encountering from-scratch-training * Revamp pretrained model loading There were quite a few factors that convinced me that the status quo is able to load pretrained models from the PEFT adapter config but in fact that didn't work. This commit fixes the following things: - policies wrapped in PEFT will now have a `name_or_path` attribute containing the name or path of the pretrained model we're fine-tuning - we further assume that SmolVLA without `pretrained_path` and `load_vlm_weights==False` must be an user-side error - we assume that using PEFT on from-scratch-policies must be an user-side-error * Make it possible to unset policy features This is necessary to train pre-trained policies on new datasets so that the features are inferred from the new dataset and not from the pretrained policy. * Use correct loading for PEFT in RTC example * Make it possible to use PeftModels in eval * Add test checking that PEFT actually reduces params * Adapt state/action projections instead of full-finetuning There doesn't seem to be a benefit to fully fine-tune these layers over just adapting them, so we do that instead. * Disallow PEFT training on non-pretrained policies At first I thought it would make sense to have this feature in case you want to fine-tune a pre-trained section but in the end it makes more trouble than it's worth. It's still possible to allow this in the future when a concrete need arises. * Add basic documentation * Formatting * Add peft as extra dependency, mark tests Fast tests currently fail because of the missing dependency. * Fix pre-commit issues * Add walx <> peft conflict for uv * Exclude peft from pi install for now --------- Co-authored-by: nemo <git@ningu.net> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com>
2026-01-05 08:51:26 +01:00
"lerobot[sarm]",
"lerobot[topreward]",
Add basic PEFT support to train script + record module (#1411) * Add basic support for PEFT adapter methods This changes adds support for training policies with much less parameters by applying adapter methods such as LoRA on specific parts of the policies and therefore possibly higher learning rates / batch sizes. To make this as accessible as possible I thought it useful to provide defaults for `target_modules` and `modules_to_save`. Currently only SmolVLA has such defaults but when we agree that this change is useful I will set out to generate more such defaults. While the user can override these settings, they are expected to only change the peft_method, rank and init_type parameters. * Implement loading of PEFT adapters Loading a PEFT adapter is currently done by initializing a policy with default config and then applying the adapter on the resulting model. This has the obvious drawback that any configurations done during training are not applied in the adapted model. Currently the `use_peft` attribute of `PreTrainedConfig` is only set during loading to signal the following code that it has to deal with a PEFT adapter. However we could imagine a scenario where this is already set at training time and stored alongside the adapter. * Store policy config alongside PEFT checkpoint Before this change the PEFT-wrapped policy did not save the policy's config alongside the adapter config / weights which prevented us from changing the policy config. Now the policy config is saved both in full training and PEFT training. This change makes loading the PEFT policy adapter much easier as well. * Add default config for ACT * Support targets like `all-linear` * Formatting * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci * Fix failing tests * Remove PEFT compatibility changes in config We'll wait for the PEFT release that fixes this for good. * Remove `use_peft` parameter from training script Instead we make the PEFT config optional which has the same effect. * Log adapter config to WandB * Better documentation for CLI arguments * Don't unload & merge the PEFT model This can make things hard when using quantized layers (user expects quantized base layers with unquantized adapters for example, merging defaults to upcast the layers leading to higher memory). * Correct way of identifying when to save config * Add CLI end-to-end tests Currently there don't seem to be any way to test the CLI commands. Since this change mostly happens in those I thought it best to add a way to test these commands end-to-end. More integrated commands like `lerobot-record` need patching but standalone commands like training seem to work fine. * Update default targets Removed ACT since it doesn't make sense to fine-tune ACT without having it pretrained beforehand. SmolVLA and Pi0/0.5 are much more senseful targets. * Clean up loading code - Centralized instantiation of the PEFT wrapper in `make_policy` for inference (e.g. in `lerobot-record`) - Training a PEFT policy also sets `cfg.use_peft` so that all inference code loading the policy can rely on that attribute to identify if PEFT loading is needed - Modified RTC example to also include PEFT policies. Mostly because this is an example I'm currently exploring. * Make sure push_to_hub works Since PEFT only wraps `push_to_hub` and not `push_model_to_hub`, the reference to `self` in `policy.push_model_to_hub` is the unwrapped policy which, of course, doesn't know anything about PEFT. To make the upload process aware of PEFT, we pass the unwrapped policy down to `push_model_to_hub` as a kwarg. This is not ideal but I think it is the best way for now. * formatting * Warn when encountering from-scratch-training * Revamp pretrained model loading There were quite a few factors that convinced me that the status quo is able to load pretrained models from the PEFT adapter config but in fact that didn't work. This commit fixes the following things: - policies wrapped in PEFT will now have a `name_or_path` attribute containing the name or path of the pretrained model we're fine-tuning - we further assume that SmolVLA without `pretrained_path` and `load_vlm_weights==False` must be an user-side error - we assume that using PEFT on from-scratch-policies must be an user-side-error * Make it possible to unset policy features This is necessary to train pre-trained policies on new datasets so that the features are inferred from the new dataset and not from the pretrained policy. * Use correct loading for PEFT in RTC example * Make it possible to use PeftModels in eval * Add test checking that PEFT actually reduces params * Adapt state/action projections instead of full-finetuning There doesn't seem to be a benefit to fully fine-tune these layers over just adapting them, so we do that instead. * Disallow PEFT training on non-pretrained policies At first I thought it would make sense to have this feature in case you want to fine-tune a pre-trained section but in the end it makes more trouble than it's worth. It's still possible to allow this in the future when a concrete need arises. * Add basic documentation * Formatting * Add peft as extra dependency, mark tests Fast tests currently fail because of the missing dependency. * Fix pre-commit issues * Add walx <> peft conflict for uv * Exclude peft from pi install for now --------- Co-authored-by: nemo <git@ningu.net> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com>
2026-01-05 08:51:26 +01:00
"lerobot[peft]",
feat(robots): Unitree G1 WBC implementation (#2876) * move locomotion from examples to robot, move controller to teleoperator class * modify teleoperate to send back actions to robot * whole body controller * add holosoma to locomotros * various updates * update joint zeroing etc * ensure safefail with locomotion * add unitree locomotion * launch camera from g1 server * publish at varying framerates * fix async read in camera * attempting to fix camera lag * test camera speedup * training * inference works * remove logging from pi0 * remove logging * push local changes * testing * final changes * revert control_utils * revert utils * revert * revert g1 * revert again: * revert utils * push recents * remove examples * remove junk * remove mjlog * revergt edit_dataset * Update lerobot_edit_dataset.py Signed-off-by: Martino Russi <77496684+nepyope@users.noreply.github.com> * undo teleop changes * revert logging * remove loggings * remove loogs * revert dataset tools * Update dataset_tools.py Signed-off-by: Martino Russi <77496684+nepyope@users.noreply.github.com> * move gravity to utils * revert changes * remove matplotlib viewer (rerun works fine) * factory revert * send policy action directly * recent changes * implement flexible action space * send empty command if arms are missing * rename locomotion to controller * add init * implement feedback * add feedback for teleoperator * fix ruff * fix ruff * use read_latest * fix zmq camera * revert exo_serial * simplify PR * revert exo_changes * revert camera_zmq * Update camera_zmq.py Signed-off-by: Martino Russi <77496684+nepyope@users.noreply.github.com> * remove frame duplication from zmq server * revert channerfactoryinitialize * keep channelfactoryinitialize * remove zeroing out logic * fix typo * refactor teleop class * simplify teleop further * import armindex at the top * fix visualizer again * revert ik helper * push stuff * simplify image_server * update image_server * asd * add threading logic * simplify ik helper stuff * simplify holosoma * fix names * fix docs * revert leg override * clean connect * fix controller * fix ruff * clean teleoperator * set_from_wireless * avoid double initializations * refactor robot class * fix pre-commit * update docs * update docs format * add teleop instructions * unitree_g1 specific exception in record/teleoperate * add thumbnail to docs * add thumbnail to doc * refactor(unitree): multiple improvements (#3103) * refactor(unitree): multiple improvements * test(unitree): added tests + improved installation instructions * refactor(robots): minor changes unitree robot kinematic * chore(robots): rename g1 kinematics file --------- Signed-off-by: Martino Russi <77496684+nepyope@users.noreply.github.com> Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> Co-authored-by: Steven Palma <imstevenpmwork@ieee.org> Co-authored-by: Steven Palma <steven.palma@huggingface.co>
2026-03-08 11:33:24 +01:00
# "lerobot[unitree_g1]", TODO: Unitree requires specific installation instructions for unitree_sdk2
]
[project.scripts]
lerobot-calibrate="lerobot.scripts.lerobot_calibrate:main"
lerobot-find-cameras="lerobot.scripts.lerobot_find_cameras:main"
lerobot-find-port="lerobot.scripts.lerobot_find_port:main"
lerobot-record="lerobot.scripts.lerobot_record:main"
lerobot-replay="lerobot.scripts.lerobot_replay:main"
lerobot-setup-motors="lerobot.scripts.lerobot_setup_motors:main"
lerobot-teleoperate="lerobot.scripts.lerobot_teleoperate:main"
lerobot-eval="lerobot.scripts.lerobot_eval:main"
lerobot-train="lerobot.scripts.lerobot_train:main"
lerobot-train-tokenizer="lerobot.scripts.lerobot_train_tokenizer:main"
lerobot-dataset-viz="lerobot.scripts.lerobot_dataset_viz:main"
lerobot-info="lerobot.scripts.lerobot_info:main"
lerobot-find-joint-limits="lerobot.scripts.lerobot_find_joint_limits:main"
lerobot-imgtransform-viz="lerobot.scripts.lerobot_imgtransform_viz:main"
Dataset tools (#2100) * feat(dataset-tools): add dataset utilities and example script - Introduced dataset tools for LeRobotDataset, including functions for deleting episodes, splitting datasets, adding/removing features, and merging datasets. - Added an example script demonstrating the usage of these utilities. - Implemented comprehensive tests for all new functionalities to ensure reliability and correctness. * style fixes * move example to dataset dir * missing lisence * fixes mostly path * clean comments * move tests to functions instead of class based * - fix video editting, decode, delete frames and rencode video - copy unchanged video and parquet files to avoid recreating the entire dataset * Fortify tooling tests * Fix type issue resulting from saving numpy arrays with shape 3,1,1 * added lerobot_edit_dataset * - revert changes in examples - remove hardcoded split names * update comment * fix comment add lerobot-edit-dataset shortcut * Apply suggestion from @Copilot Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> Signed-off-by: Michel Aractingi <michel.aractingi@huggingface.co> * style nit after copilot review * fix: bug in dataset root when editing the dataset in place (without setting new_repo_id * Fix bug in aggregate.py when accumelating video timestamps; add tests to fortify aggregate videos * Added missing output repo id * migrate delete episode to using pyav instead of decoding, writing frames to disk and encoding again. Co-authored-by: Caroline Pascal <caroline8.pascal@gmail.com> * added modified suffix in case repo_id is not set in delete_episode * adding docs for dataset tools * bump av version and add back time_base assignment * linter * modified push_to_hub logic in lerobot_edit_dataset * fix(progress bar): fixing the progress bar issue in dataset tools * chore(concatenate): removing no longer needed concatenate_datasets usage * fix(file sizes forwarding): forwarding files and chunk sizes in metadata info when splitting and aggregating datasets * style fix * refactor(aggregate): Fix video indexing and timestamp bugs in dataset merging There were three critical bugs in aggregate.py that prevented correct dataset merging: 1. Video file indices: Changed from += to = assignment to correctly reference merged video files 2. Video timestamps: Implemented per-source-file offset tracking to maintain continuous timestamps when merging split datasets (was causing non-monotonic timestamp warnings) 3. File rotation offsets: Store timestamp offsets after rotation decision to prevent out-of-bounds frame access (was causing "Invalid frame index" errors with small file size limits) Changes: - Updated update_meta_data() to apply per-source-file timestamp offsets - Updated aggregate_videos() to track offsets correctly during file rotation - Added get_video_duration_in_s import for duration calculation * Improved docs for split dataset and added a check for the possible case that the split size results in zero episodes * chore(docs): update merge documentation details Signed-off-by: Steven Palma <imstevenpmwork@ieee.org> --------- Co-authored-by: CarolinePascal <caroline8.pascal@gmail.com> Co-authored-by: Jack Vial <vialjack@gmail.com> Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
2025-10-10 12:32:07 +02:00
lerobot-edit-dataset="lerobot.scripts.lerobot_edit_dataset:main"
2026-01-26 17:53:25 +01:00
lerobot-setup-can="lerobot.scripts.lerobot_setup_can:main"
feat(rollout): decouple policy deployment from data recording with new `lerobot-rollout` CLI (#3413) * feat(scripts): lerobot-rollout * fix(rollout) require dataset in dagger + use duration too * fix(docs): dagger num_episodes * test(rollout): fix expectations * fix(rollout): features check * fix(rollout): device and task propagation + feature pos + warn fps + move rename_map config * docs(rollout): edit rename_map instructions * chore(rollout): multiple minor improvements * chore(rollout): address coments + minor improvements * fix(rollout): enable default * fix(tests): default value RTCConfig * fix(rollout): robot_observation_processor and notify_observation at policy frequency instead of interpolator rate Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com> * fix(rollout): prevent relativeactions with sync inference engine Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com> * fix(rollout): rtc reanchor to non normalized state Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com> * fix(rollout): fixing the episode length to use hwc (#3469) also reducing default length to 5 minutes * feat(rollout): go back to initial position is now a config * fix(rollout): properly propagating video_files_size_in_mb to lerobot_dataset (#3470) * chore(rollout): note about dagger correction stage * chore(docs): update comments and docstring * fix(test): move rtc relative out of rollout module * fix(rollout): address the review comments --------- Co-authored-by: Pepijn <138571049+pkooij@users.noreply.github.com> Co-authored-by: Maxime Ellerbach <maxime.ellerbach@huggingface.co>
2026-04-28 00:57:35 +02:00
lerobot-rollout="lerobot.scripts.lerobot_rollout:main"
# ---------------- Tool Configurations ----------------
# cu128 wheels keep broad hardware reach; the driver floor is 570.86.
# To use a different CUDA variant, reinstall torch with an explicit index, e.g.:
# uv pip install --force-reinstall torch torchvision \
# --index-url https://download.pytorch.org/whl/cu130
[[tool.uv.index]]
name = "pytorch-cu128"
url = "https://download.pytorch.org/whl/cu128"
explicit = true
[tool.uv.sources]
torch = [{ index = "pytorch-cu128", marker = "sys_platform == 'linux'" }]
torchvision = [{ index = "pytorch-cu128", marker = "sys_platform == 'linux'" }]
[tool.setuptools.package-data]
lerobot = ["envs/*.json"]
[tool.setuptools.packages.find]
where = ["src"]
2024-02-28 19:11:29 +01:00
2024-02-29 12:26:35 +01:00
[tool.ruff]
target-version = "py312"
line-length = 110
exclude = ["tests/artifacts/**/*.safetensors", "*_pb2.py", "*_pb2_grpc.py"]
2024-02-29 12:26:35 +01:00
[tool.ruff.lint]
# E, W: pycodestyle errors and warnings
# F: PyFlakes
# I: isort
# UP: pyupgrade
# B: flake8-bugbear (good practices, potential bugs)
# C4: flake8-comprehensions (more concise comprehensions)
# A: flake8-builtins (shadowing builtins)
# SIM: flake8-simplify
# RUF: Ruff-specific rules
# D: pydocstyle (for docstring style/formatting)
# S: flake8-bandit (some security checks, complements Bandit)
# T20: flake8-print (discourage print statements in production code)
# N: pep8-naming
# TODO: Uncomment rules when ready to use
select = [
"E", "W", "F", "I", "B", "C4", "T20", "N", "UP", "SIM" #, "A", "S", "D", "RUF"
]
ignore = [
"E501", # Line too long
"T201", # Print statement found
"T203", # Pprint statement found
"B008", # Perform function call in argument defaults
]
2024-03-11 12:10:46 +01:00
[tool.ruff.lint.per-file-ignores]
"__init__.py" = ["F401", "F403", "E402"]
# E402: conditional-import guards (TYPE_CHECKING / is_package_available) must precede the imports they protect
"src/lerobot/scripts/convert_dataset_v21_to_v30.py" = ["E402"]
"src/lerobot/policies/wall_x/**" = ["N801", "N812", "SIM102", "SIM108", "SIM210", "SIM211", "B006", "B007", "SIM118"] # Supprese these as they are coming from original Qwen2_5_vl code TODO(pepijn): refactor original
[tool.ruff.lint.isort]
combine-as-imports = true
known-first-party = ["lerobot"]
[tool.ruff.lint.pydocstyle]
convention = "google"
[tool.ruff.format]
quote-style = "double"
indent-style = "space"
skip-magic-trailing-comma = false
line-ending = "auto"
docstring-code-format = true
2025-03-01 19:19:26 +01:00
[tool.bandit]
exclude_dirs = [
"tests",
"benchmarks",
"src/lerobot/datasets/push_dataset_to_hub",
2025-03-01 19:19:26 +01:00
]
skips = ["B101", "B311", "B404", "B603", "B615"]
2024-03-11 12:10:46 +01:00
2025-02-25 23:51:15 +01:00
[tool.typos]
default.extend-ignore-re = [
"(?Rm)^.*(#|//)\\s*spellchecker:disable-line$", # spellchecker:disable-line
"(?s)(#|//)\\s*spellchecker:off.*?\\n\\s*(#|//)\\s*spellchecker:on", # spellchecker:<on|off>
2025-02-25 23:51:15 +01:00
]
default.extend-ignore-identifiers-re = [
# Add individual words here to ignore them
"2nd",
"pn",
"ser",
"ein",
"thw",
"inpt",
"ROBOTIS",
2026-01-26 17:53:25 +01:00
"OT_VALUE"
2025-02-25 23:51:15 +01:00
]
# TODO: Uncomment when ready to use
# [tool.interrogate]
# ignore-init-module = true
# ignore-init-method = true
# ignore-nested-functions = false
# ignore-magic = false
# ignore-semiprivate = false
# ignore-private = false
# ignore-property-decorators = false
# ignore-module = false
# ignore-setters = false
# fail-under = 80
# output-format = "term-missing"
# color = true
# paths = ["src/lerobot"]
# TODO: Enable mypy gradually module by module across multiple PRs
# Uncomment [tool.mypy] first, then uncomment individual module overrides as they get proper type annotations
[tool.mypy]
python_version = "3.12"
ignore_missing_imports = true
follow_imports = "skip"
# warn_return_any = true
# warn_unused_configs = true
# strict = true
# disallow_untyped_defs = true
# disallow_incomplete_defs = true
# check_untyped_defs = true
[[tool.mypy.overrides]]
module = "lerobot.*"
ignore_errors = true
[[tool.mypy.overrides]]
module = "lerobot.envs.*"
ignore_errors = false
# [[tool.mypy.overrides]]
# module = "lerobot.utils.*"
# ignore_errors = false
2025-10-20 19:57:32 +09:00
[[tool.mypy.overrides]]
module = "lerobot.configs.*"
ignore_errors = false
# extra strictness for configs
disallow_untyped_defs = true
disallow_incomplete_defs = true
check_untyped_defs = true
[[tool.mypy.overrides]]
module = "lerobot.optim.*"
ignore_errors = false
[[tool.mypy.overrides]]
module = "lerobot.model.*"
ignore_errors = false
# [[tool.mypy.overrides]]
# module = "lerobot.processor.*"
# ignore_errors = false
# [[tool.mypy.overrides]]
# module = "lerobot.datasets.*"
# ignore_errors = false
[[tool.mypy.overrides]]
module = "lerobot.cameras.*"
ignore_errors = false
chore(linter): ensure motors module passes MyPy type checks (#2939) * fix: ensure motors module passes MyPy type checks This commit fixes 62 mypy type errors in the motors module by: - Updating Protocol classes (PortHandler, PacketHandler, GroupSyncRead, GroupSyncWrite) to use class-level attribute declarations instead of __init__ body declarations - Adding missing `broadcastPing` method to PacketHandler Protocol - Fixing return type annotations (e.g., `_get_motor_model` returns str, not int) - Fixing parameter types to use `Sequence` for covariant list parameters - Fixing `Mapping` for covariant dict value types in `_normalize` - Updating method signatures to be consistent across parent and child classes (disable_torque, enable_torque, _get_half_turn_homings) - Adding explicit `int()` casts for MotorCalibration arguments - Adding explicit `return None` for functions returning Optional types - Adding type annotations for variables like `data_list: dict[int, int]` - Using `# type: ignore[method-assign]` for intentional monkeypatch - Fixing variable references (using `self.groups` instead of `groups`) Fixes #1723 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com> * chore(style): pre-commit after main merge * chore(linter): solve comments * chore(linter): apply pre-commit fixes to damiao * chore(linter): more fixes to damiao --------- Co-authored-by: yurekami <yurekami@users.noreply.github.com> Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-02-10 17:35:39 +01:00
[[tool.mypy.overrides]]
module = "lerobot.motors.*"
ignore_errors = false
# [[tool.mypy.overrides]]
# module = "lerobot.robots.*"
# ignore_errors = false
# [[tool.mypy.overrides]]
# module = "lerobot.teleoperators.*"
# ignore_errors = false
# [[tool.mypy.overrides]]
# module = "lerobot.policies.*"
# ignore_errors = false
# [[tool.mypy.overrides]]
# module = "lerobot.rl.*"
# ignore_errors = false
# [[tool.mypy.overrides]]
# module = "lerobot.async_inference.*"
# ignore_errors = false
[[tool.mypy.overrides]]
module = "lerobot.transport.*"
ignore_errors = false
# [[tool.mypy.overrides]]
# module = "lerobot.scripts.*"
# ignore_errors = false