Files
lerobot-clone/src/lerobot/policies/act/processor_act.py

97 lines
3.6 KiB
Python

#!/usr/bin/env python
# Copyright 2024 Tony Z. Zhao and 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.
from typing import Any
import torch
from lerobot.datasets.utils import DEFAULT_AUDIO_CHUNK_DURATION
from lerobot.policies.act.configuration_act import ACTConfig
from lerobot.processor import (
AddBatchDimensionProcessorStep,
AudioProcessorStep,
DeviceProcessorStep,
NormalizerProcessorStep,
PolicyAction,
PolicyProcessorPipeline,
RenameObservationsProcessorStep,
UnnormalizerProcessorStep,
)
from lerobot.processor.converters import policy_action_to_transition, transition_to_policy_action
from lerobot.utils.constants import POLICY_POSTPROCESSOR_DEFAULT_NAME, POLICY_PREPROCESSOR_DEFAULT_NAME
def make_act_pre_post_processors(
config: ACTConfig,
dataset_stats: dict[str, dict[str, torch.Tensor]] | None = None,
) -> tuple[
PolicyProcessorPipeline[dict[str, Any], dict[str, Any]],
PolicyProcessorPipeline[PolicyAction, PolicyAction],
]:
"""Creates the pre- and post-processing pipelines for the ACT policy.
The pre-processing pipeline handles normalization, batching, and device placement for the model inputs.
The post-processing pipeline handles unnormalization and moves the model outputs back to the CPU.
Args:
config (ACTConfig): The ACT policy configuration object.
dataset_stats (dict[str, dict[str, torch.Tensor]] | None): A dictionary containing dataset
statistics (e.g., mean and std) used for normalization. Defaults to None.
Returns:
tuple[PolicyProcessorPipeline[dict[str, Any], dict[str, Any]], PolicyProcessorPipeline[PolicyAction, PolicyAction]]: A tuple containing the
pre-processor pipeline and the post-processor pipeline.
"""
input_steps = [
RenameObservationsProcessorStep(rename_map={}),
AddBatchDimensionProcessorStep(),
DeviceProcessorStep(device=config.device),
NormalizerProcessorStep(
features={**config.input_features, **config.output_features},
norm_map=config.normalization_mapping,
stats=dataset_stats,
device=config.device,
),
AudioProcessorStep(
output_height=224,
output_width=224,
output_channels=3,
input_audio_chunk_duration=DEFAULT_AUDIO_CHUNK_DURATION,
input_sample_rate=48000,
intermediate_sample_rate=16000,
n_fft=1024,
),
]
output_steps = [
UnnormalizerProcessorStep(
features=config.output_features, norm_map=config.normalization_mapping, stats=dataset_stats
),
DeviceProcessorStep(device="cpu"),
]
return (
PolicyProcessorPipeline[dict[str, Any], dict[str, Any]](
steps=input_steps,
name=POLICY_PREPROCESSOR_DEFAULT_NAME,
),
PolicyProcessorPipeline[PolicyAction, PolicyAction](
steps=output_steps,
name=POLICY_POSTPROCESSOR_DEFAULT_NAME,
to_transition=policy_action_to_transition,
to_output=transition_to_policy_action,
),
)