ydy0615/lerobot-clone
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-06-01 19:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add OpenPi, Pi0 and Pi0.5 (#1910)

Browse Source 
* initial commit

* change device in test

* do detailed import

* adhere to python 3.11 syntax

* fix autodocstring

* additionally

* do same in other files

* add model. prefix to all keys in state dict

* use dummy stats

* add pi05

* also shorten action_steps

* fix test

* all test pass! and fix tokenizer max length between 05 and 0

* remove test

* fix transformer dependency

* fix test

* split pi0 and pi05 policy in seperate files

* fix test

* fix push to hub test

* add some comments, license and readme

* remove warning in config

* add pi05 to factory

* remove check

* rename action_horizon to chunk_size

* clean up padding of state and action (more in line with lerobot pi0)

* add openpi image transforms for training and add more flexibility to _preprocess_images similar to lerobot pi0

* fix key match from pytorch state dict (similar keys to openpi implementation now)

* also for pi05

* update to python 3.11

* revert to openpi transformer replace python 3.11

* fix(modeling pi0): nit  warning message

* use safeauto_docstring

* fix: remove unused param

* fix from pretrained

* add preprocess tests

* also compile forward method

* Do not add model prefix to normalization

* use same name for action and state dim as lerobot pi0 and remove fixed image keys

* load from pretrained_path

* temp: hardcode base model

* fix override self.pretrained_path = None overwrite

* rename to loss

* remove additional image augmentations, lerobot dataset already does this

* Add docs

* put tests in test folder

* Add test to instatiate all base models

* go back to python 3.10

* update docs

* adapt docs pi05

* change docs: finetune base model options

* minor docs fixes and dependencies

* remove todo

* cast float64 to float32 for mps

* skip if no transformers

* fix tests

* add new models to modelcard

* add back init

* fix circular input

* feat: only run pi test on GPU

* remove require_nightly_gpu

* replace decorator test_pi0_openpi

* rename action_dim, state_dim to max_action_dim, max_state_dim

* fix doc and constants

* cleanup tests

* fix from pretrained

* fix tests

* add comment pi0 pi05 tests, add image features to pi0 pi05 hub tests

* fix, state is included in language not in flow head

* Move test to specific folder

* and paligemma task with newline

* remove add_special_tokens, not needed

* feedback pr

* Remove previous pi0 and rename pi0_openpi and pi05_openpi

* Add Quantile stats to LeRobotDataset (#1985)

* - Add RunningQuantileStats class for efficient histogram-based quantile computation
- Integrate quantile parameters (compute_quantiles, quantiles) into LeRobotDataset
- Support quantile computation during episode collection and aggregation
- Add comprehensive function-based test suite (24 tests) for quantile functionality
- Maintain full backward compatibility with existing stats computation
- Enable configurable quantiles (default: [0.01, 0.99]) for robust normalization

* style fixes, make quantiles computation by default to new datasets

* fix tests

* - Added DEFAULT_QUANTILES=[0.01, 0.10, 0.50, 0.90, 0.99] to be computed for each features instead of being chosen by the user
- Fortified tests.

* - add helper functions to reshape stats
- add missing test for quantiles

* - Add QUANTILE normalization mode to normalize the data with the 1st and 99th percentiles.
- Add QUANTILE10 normalization mode to normalize the data with the 10th and 90th percentiles.

* style fixes

* Added missing lisence

* Simplify compute_stats

* - added script `augment_dataset_quantile_stats.py` so that we can add quantile stats to existing v3 datasets that dont have quatniles
- modified quantile computation instead of using the edge for the value, interpolate the values in the bin

* rename pi0/pi05 files

* Remove open pi patch and use custom transformer branch for now

* renaming

* fix

* Revert "fix"

This reverts commit 1ea65730ac.

* fix naming

* feet(pi0/pi0.5): add pipeline (#2009)

* feat(processor): convert openpi model with processor

* TODO: Make test works

* fix(modeling_pi0openpi): update attention mask value and time scaling; improve task handling in tests

- Changed the attention mask value from `self.config.attention_mask_value` to a fixed value of `-2.3819763e38`.
- Updated time scaling in the `sample_noise` method to use a constant factor of `0.999` and an offset of `0.001`.
- Enhanced task handling in tests to ensure proper formatting and batch size consistency.
- Cleaned up commented-out test code for clarity.

* refactor(pi0): rename PI0OpenPIConfig and PI0OpenPIPolicy to PI0Config and PI0Policy

- Updated imports and references throughout the codebase to reflect the new naming convention.
- Introduced a new processor file for PI0 to handle pre-processing and post-processing steps.
- Adjusted tests to utilize the renamed classes, ensuring consistency and functionality.
- Enhanced clarity and maintainability by removing outdated naming conventions.

* refactor(pi05): rename PI0OpenPIPolicy to PI0Policy and update configuration

- Renamed `PI0OpenPIPolicy` to `PI0Policy` for consistency with naming conventions.
- Updated the `PI05OpenPIConfig` to include a new `tokenizer_max_length` attribute and changed the normalization mode for state from `MEAN_STD` to `QUANTILES`.
- Simplified model initialization in `PI05OpenPIPolicy` by removing unused `dataset_stats` parameter.
- Added a new processor class for `Pi05PrepareStateTokenizerProcessorStep` with `@dataclass` for improved readability.
- Introduced a test script to compare the integration of the PI0OpenPI policy with the original implementation, ensuring local testing compatibility.

* feat(processor): convert openpi model with processor

* TODO: Make test works

* fix(modeling_pi0openpi): update attention mask value and time scaling; improve task handling in tests

- Changed the attention mask value from `self.config.attention_mask_value` to a fixed value of `-2.3819763e38`.
- Updated time scaling in the `sample_noise` method to use a constant factor of `0.999` and an offset of `0.001`.
- Enhanced task handling in tests to ensure proper formatting and batch size consistency.
- Cleaned up commented-out test code for clarity.

* refactor(pi0): rename PI0OpenPIConfig and PI0OpenPIPolicy to PI0Config and PI0Policy

- Updated imports and references throughout the codebase to reflect the new naming convention.
- Introduced a new processor file for PI0 to handle pre-processing and post-processing steps.
- Adjusted tests to utilize the renamed classes, ensuring consistency and functionality.
- Enhanced clarity and maintainability by removing outdated naming conventions.

* refactor(pi05): rename PI0OpenPIPolicy to PI0Policy and update configuration

- Renamed `PI0OpenPIPolicy` to `PI0Policy` for consistency with naming conventions.
- Updated the `PI05OpenPIConfig` to include a new `tokenizer_max_length` attribute and changed the normalization mode for state from `MEAN_STD` to `QUANTILES`.
- Simplified model initialization in `PI05OpenPIPolicy` by removing unused `dataset_stats` parameter.
- Added a new processor class for `Pi05PrepareStateTokenizerProcessorStep` with `@dataclass` for improved readability.
- Introduced a test script to compare the integration of the PI0OpenPI policy with the original implementation, ensuring local testing compatibility.

* refactor(pi05): update imports and rename configuration classes

- Changed imports to reflect the new naming convention for PI05 configuration and policy classes.
- Renamed `PI05OpenPIConfig` to `PI05Config` and `PI05OpenPIPolicy` to `PI05Policy` for consistency.
- Introduced a new processor file for PI05, implementing pre-processing and post-processing steps.
- Updated tests to utilize the renamed classes, ensuring functionality and consistency across the codebase.

* update(pi05): increase tokenizer_max_length for improved processing

- Changed the `tokenizer_max_length` from 48 to 200 to enhance the model's capability in handling longer sequences.
- This adjustment aims to improve the overall performance and flexibility of the PI05 configuration.

* add default for state (max_state_dim)

* correct naming

* fix import

* cleanup code

* remove unused test

* us quantiles for action

* move to device

* remove discrete state assert

* fix pi05 test

* move pi05 to device

* use base models in comparison tests

* small renames for tests

* change number of tokens pi05 test

* fix openpi tokenization in test

* fix hub test

* fix test

* assert lerobot vs openpi tests

---------

Co-authored-by: Pepijn <pepijn@huggingface.co>

* add headers

* add back previously removed imports

* update if statement load processor with dataset stats

* remove to avoid circular import

* inject dataset stats for pretrained models

* check normalization before applying

* add link to  quantile augument script

* fix(policies): transformers import for ci in PI0 & PI05 (#2039)

* fix(policies): transformers import for ci in PI0

* fix(policies): transformers import for ci in PI05

* test(processor): fix expected raise when normalization types are missing (#2040)

* switch normalization order pipeline for pi05

* Fix/quantiles script (#2064)

* refactor augment stats with quantiles script
add parallelization for faster processing
shift the quantile normalization between -1 1

* fix replay buffer tests

* fix comment

* overwrite the pipeline normalization features with the policy features

* remove double normalization overwrite

* cleanup from pretrained

* remove typo

* also set norm_map

* fix(augment_quantiles) images incorrectly divided by 255

* clamp quantiles

* link to lerobot base models

* rename tests

* encorperate PR feedback

* update docstring for RunningQuantileStats

* update doc links

* Revert "clamp quantiles"

This reverts commit 172207471c.

* fix self.paligemma

* fix tests related to quantiles that were scaled to [0,1], the new range is [-1, 1]

* fix libero doc and use different transformer branch

* use fix branch instead of feat

* update results libero

* add new line

* fix formatting

* precommit

* update results libero

* update libero doc

* update title

* final changes

* add quantiles to test

* run pre commit

---------

Signed-off-by: Steven Palma <imstevenpmwork@ieee.org>
Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co>
Co-authored-by: Adil Zouitine <adilzouitinegm@gmail.com>
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org>
Co-authored-by: Steven Palma <steven.palma@huggingface.co>
This commit is contained in:
Pepijn
2025-10-02 13:14:45 +02:00
committed by GitHub
parent b6c528a438
commit abde7be3b3
43 changed files with 5886 additions and 2288 deletions
Download Patch File Download Diff File Expand all files Collapse all files

69
src/lerobot/processor/normalize_processor.py
View File

@@ -281,8 +281,14 @@ class _NormalizationMixin:
"""
Core logic to apply a normalization or unnormalization transformation to a tensor.
This method selects the appropriate normalization mode (e.g., mean/std, min/max)
based on the feature type and applies the corresponding mathematical operation.
This method selects the appropriate normalization mode based on the feature type
and applies the corresponding mathematical operation.
Normalization Modes:
- MEAN_STD: Centers data around zero with unit variance.
- MIN_MAX: Scales data to [-1, 1] range using actual min/max values.
- QUANTILES: Scales data to [-1, 1] range using 1st and 99th percentiles (q01/q99).
- QUANTILE10: Scales data to [-1, 1] range using 10th and 90th percentiles (q10/q90).
Args:
tensor: The input tensor to transform.
@@ -300,7 +306,12 @@ class _NormalizationMixin:
if norm_mode == NormalizationMode.IDENTITY or key not in self._tensor_stats:
return tensor
if norm_mode not in (NormalizationMode.MEAN_STD, NormalizationMode.MIN_MAX):
if norm_mode not in (
NormalizationMode.MEAN_STD,
NormalizationMode.MIN_MAX,
NormalizationMode.QUANTILES,
NormalizationMode.QUANTILE10,
):
raise ValueError(f"Unsupported normalization mode: {norm_mode}")
# For Accelerate compatibility: Ensure stats are on the same device and dtype as the input tensor
@@ -311,7 +322,14 @@ class _NormalizationMixin:
stats = self._tensor_stats[key]
if norm_mode == NormalizationMode.MEAN_STD and "mean" in stats and "std" in stats:
if norm_mode == NormalizationMode.MEAN_STD:
mean = stats.get("mean", None)
std = stats.get("std", None)
if mean is None or std is None:
raise ValueError(
"MEAN_STD normalization mode requires mean and std stats, please update the dataset with the correct stats"
)
mean, std = stats["mean"], stats["std"]
# Avoid division by zero by adding a small epsilon.
denom = std + self.eps
@@ -319,7 +337,14 @@ class _NormalizationMixin:
return tensor * std + mean
return (tensor - mean) / denom
if norm_mode == NormalizationMode.MIN_MAX and "min" in stats and "max" in stats:
if norm_mode == NormalizationMode.MIN_MAX:
min_val = stats.get("min", None)
max_val = stats.get("max", None)
if min_val is None or max_val is None:
raise ValueError(
"MIN_MAX normalization mode requires min and max stats, please update the dataset with the correct stats"
)
min_val, max_val = stats["min"], stats["max"]
denom = max_val - min_val
# When min_val == max_val, substitute the denominator with a small epsilon
@@ -334,6 +359,40 @@ class _NormalizationMixin:
# Map from [min, max] to [-1, 1]
return 2 * (tensor - min_val) / denom - 1
if norm_mode == NormalizationMode.QUANTILES:
q01 = stats.get("q01", None)
q99 = stats.get("q99", None)
if q01 is None or q99 is None:
raise ValueError(
"QUANTILES normalization mode requires q01 and q99 stats, please update the dataset with the correct stats using the `augment_dataset_quantile_stats.py` script"
)
denom = q99 - q01
# Avoid division by zero by adding epsilon when quantiles are identical
denom = torch.where(
denom == 0, torch.tensor(self.eps, device=tensor.device, dtype=tensor.dtype), denom
)
if inverse:
return (tensor + 1.0) * denom / 2.0 + q01
return 2.0 * (tensor - q01) / denom - 1.0
if norm_mode == NormalizationMode.QUANTILE10:
q10 = stats.get("q10", None)
q90 = stats.get("q90", None)
if q10 is None or q90 is None:
raise ValueError(
"QUANTILE10 normalization mode requires q10 and q90 stats, please update the dataset with the correct stats using the `augment_dataset_quantile_stats.py` script"
)
denom = q90 - q10
# Avoid division by zero by adding epsilon when quantiles are identical
denom = torch.where(
denom == 0, torch.tensor(self.eps, device=tensor.device, dtype=tensor.dtype), denom
)
if inverse:
return (tensor + 1.0) * denom / 2.0 + q10
return 2.0 * (tensor - q10) / denom - 1.0
# If necessary stats are missing, return input unchanged.
return tensor