mirror of
https://github.com/huggingface/lerobot.git
synced 2026-05-15 16:49:55 +00:00
add scripts for convert behavior-1k to datasetv3
This commit is contained in:
Michel Aractingi
committed by
fracapuano
fracapuano
parent
0f551df8f4
commit
950a6fb83d
@@ -0,0 +1,223 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
import json
|
||||
import numpy as np
|
||||
import torch as th
|
||||
from pathlib import Path
|
||||
from typing import Dict, Any
|
||||
|
||||
from lerobot.datasets.lerobot_dataset import LeRobotDataset
|
||||
|
||||
from .behaviour_1k_constants import (
|
||||
TASK_INDICES_TO_NAMES,
|
||||
ROBOT_CAMERA_NAMES,
|
||||
PROPRIOCEPTION_INDICES,
|
||||
BEHAVIOR_DATASET_FEATURES,
|
||||
)
|
||||
|
||||
import logging
|
||||
from lerobot.utils.utils import init_logging
|
||||
|
||||
init_logging()
|
||||
|
||||
class BehaviorLeRobotDatasetV3(LeRobotDataset):
|
||||
"""
|
||||
Extends LeRobotDataset v3.0 for BEHAVIOR-1K specific requirements.
|
||||
Handles task-based episode organization and BEHAVIOR-1K metadata.
|
||||
"""
|
||||
@classmethod
|
||||
def create(
|
||||
cls,
|
||||
repo_id: str,
|
||||
fps: int = 30,
|
||||
root: str | Path | None = None,
|
||||
robot_type: str = "R1Pro",
|
||||
use_videos: bool = True,
|
||||
video_backend: str = "pyav",
|
||||
batch_encoding_size: int = 1,
|
||||
image_writer_processes: int = 0,
|
||||
image_writer_threads: int = 4,
|
||||
) -> "BehaviorLeRobotDatasetV3":
|
||||
"""
|
||||
Create a new BEHAVIOR-1K dataset in v3.0 format.
|
||||
|
||||
Args:
|
||||
repo_id: HuggingFace repository ID
|
||||
fps: Frames per second (default: 30)
|
||||
root: Local directory for the dataset
|
||||
robot_type: Robot type (default: "R1Pro")
|
||||
use_videos: Whether to encode videos (default: True)
|
||||
video_backend: Video backend to use (default: "pyav")
|
||||
batch_encoding_size: Number of episodes to batch before encoding videos
|
||||
image_writer_processes: Number of processes for async image writing
|
||||
image_writer_threads: Number of threads per process for image writing
|
||||
|
||||
Returns:
|
||||
BehaviorLeRobotDatasetV3 instance
|
||||
"""
|
||||
# Create the dataset using parent class method with BEHAVIOR-1K features
|
||||
obj = super().create(
|
||||
repo_id=repo_id,
|
||||
fps=fps,
|
||||
features=BEHAVIOR_DATASET_FEATURES,
|
||||
root=root,
|
||||
robot_type=robot_type,
|
||||
use_videos=use_videos,
|
||||
tolerance_s=1e-4,
|
||||
image_writer_processes=image_writer_processes,
|
||||
image_writer_threads=image_writer_threads,
|
||||
video_backend=video_backend,
|
||||
batch_encoding_size=batch_encoding_size,
|
||||
)
|
||||
|
||||
# Convert to BehaviorLeRobotDatasetV3 instance
|
||||
obj.__class__ = cls
|
||||
|
||||
# Initialize BEHAVIOR-1K specific attributes
|
||||
obj.task_episode_mapping = {} # Maps task_id to list of episode indices
|
||||
obj.episode_task_mapping = {} # Maps episode_index to task info
|
||||
|
||||
# Additional metadata for BEHAVIOR-1K
|
||||
obj.behavior_metadata = {
|
||||
"robot_type": robot_type,
|
||||
"task_names": TASK_INDICES_TO_NAMES,
|
||||
"proprioception_indices": PROPRIOCEPTION_INDICES[robot_type],
|
||||
"camera_names": ROBOT_CAMERA_NAMES[robot_type],
|
||||
}
|
||||
|
||||
logging.info(f"Created BehaviorLeRobotDatasetV3 with repo_id: {repo_id}")
|
||||
return obj
|
||||
|
||||
def __init__(self, *args, **kwargs):
|
||||
"""
|
||||
Initialize from existing dataset.
|
||||
Use the create() classmethod to create a new dataset.
|
||||
"""
|
||||
super().__init__(*args, **kwargs)
|
||||
|
||||
# Initialize BEHAVIOR-1K specific attributes for loading existing datasets
|
||||
self.task_episode_mapping = {}
|
||||
self.episode_task_mapping = {}
|
||||
self.behavior_metadata = {}
|
||||
|
||||
# Try to load BEHAVIOR-1K metadata if it exists
|
||||
metadata_path = self.root / "meta" / "behavior_metadata.json"
|
||||
if metadata_path.exists():
|
||||
with open(metadata_path, "r") as f:
|
||||
stored_metadata = json.load(f)
|
||||
self.behavior_metadata = stored_metadata
|
||||
self.task_episode_mapping = stored_metadata.get("task_episode_mapping", {})
|
||||
self.episode_task_mapping = stored_metadata.get("episode_task_mapping", {})
|
||||
|
||||
def add_episode_from_hdf5(
|
||||
self,
|
||||
hdf5_data: Dict[str, Any],
|
||||
task_id: int,
|
||||
episode_id: int,
|
||||
include_videos: bool = True,
|
||||
) -> None:
|
||||
"""
|
||||
Add an episode from HDF5 data to the dataset.
|
||||
|
||||
Args:
|
||||
hdf5_data: Dictionary containing the HDF5 episode data
|
||||
task_id: Task ID for this episode
|
||||
episode_id: Episode ID (should be task_id * 10000 + local_episode_id)
|
||||
include_videos: Whether to include video data
|
||||
"""
|
||||
task_name = TASK_INDICES_TO_NAMES[task_id]
|
||||
num_frames = len(hdf5_data["action"])
|
||||
|
||||
logging.info(f"Adding episode {episode_id} (task: {task_name}) with {num_frames} frames")
|
||||
|
||||
# Process each frame
|
||||
for frame_idx in range(num_frames):
|
||||
frame_data = {
|
||||
"action": hdf5_data["action"][frame_idx],
|
||||
"observation.state": hdf5_data["obs"]["robot_r1::proprio"][frame_idx],
|
||||
"observation.cam_rel_poses": hdf5_data["obs"]["robot_r1::cam_rel_poses"][frame_idx],
|
||||
"observation.task_info": hdf5_data["obs"]["task::low_dim"][frame_idx],
|
||||
"task": task_name,
|
||||
"timestamp": frame_idx / self.fps,
|
||||
}
|
||||
|
||||
# Add video frames if requested
|
||||
if include_videos:
|
||||
for modality in ["rgb", "depth_linear", "seg_instance_id"]:
|
||||
# Map depth_linear to depth for consistency
|
||||
output_modality = "depth" if modality == "depth_linear" else modality
|
||||
|
||||
for camera_name, robot_camera_name in ROBOT_CAMERA_NAMES[self.robot_type].items():
|
||||
key = f"observation.images.{output_modality}.{camera_name}"
|
||||
hdf5_key = f"{robot_camera_name}::{modality}"
|
||||
|
||||
if hdf5_key in hdf5_data["obs"]:
|
||||
# Get the frame data
|
||||
frame = hdf5_data["obs"][hdf5_key][frame_idx]
|
||||
|
||||
# Handle different data types
|
||||
if isinstance(frame, th.Tensor):
|
||||
frame = frame.numpy()
|
||||
|
||||
# Ensure correct shape
|
||||
if modality == "seg_instance_id" and len(frame.shape) == 2:
|
||||
# Add channel dimension for grayscale
|
||||
frame = np.expand_dims(frame, axis=-1)
|
||||
elif modality == "depth_linear" and len(frame.shape) == 2:
|
||||
frame = np.expand_dims(frame, axis=-1)
|
||||
|
||||
frame_data[key] = frame
|
||||
|
||||
# Add frame to dataset
|
||||
self.add_frame(frame_data)
|
||||
|
||||
# Save episode with metadata
|
||||
episode_metadata = {
|
||||
"task_id": task_id,
|
||||
"task_name": task_name,
|
||||
"original_episode_id": episode_id,
|
||||
}
|
||||
|
||||
# Add any additional HDF5 attributes as metadata
|
||||
if "attrs" in hdf5_data:
|
||||
for attr_name, attr_value in hdf5_data["attrs"].items():
|
||||
if isinstance(attr_value, (list, np.ndarray)):
|
||||
episode_metadata[attr_name] = list(attr_value)
|
||||
else:
|
||||
episode_metadata[attr_name] = attr_value
|
||||
|
||||
# Save the episode
|
||||
self.save_episode(episode_data=None)
|
||||
|
||||
# Track task-episode mapping
|
||||
if task_id not in self.task_episode_mapping:
|
||||
self.task_episode_mapping[task_id] = []
|
||||
self.task_episode_mapping[task_id].append(self.num_episodes - 1)
|
||||
self.episode_task_mapping[self.num_episodes - 1] = {
|
||||
"task_id": task_id,
|
||||
"task_name": task_name,
|
||||
"original_episode_id": episode_id,
|
||||
}
|
||||
|
||||
def finalize(self) -> None:
|
||||
"""Finalize the dataset and save additional BEHAVIOR-1K metadata."""
|
||||
# Save BEHAVIOR-1K specific metadata
|
||||
metadata_path = self.root / "meta" / "behavior_metadata.json"
|
||||
metadata_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
self.behavior_metadata.update({
|
||||
"task_episode_mapping": self.task_episode_mapping,
|
||||
"episode_task_mapping": self.episode_task_mapping,
|
||||
"total_tasks": len(self.task_episode_mapping),
|
||||
"total_episodes": self.num_episodes,
|
||||
"total_frames": self.num_frames,
|
||||
})
|
||||
|
||||
with open(metadata_path, "w") as f:
|
||||
json.dump(self.behavior_metadata, f, indent=2)
|
||||
|
||||
# Finalize the parent dataset
|
||||
super().finalize()
|
||||
|
||||
logging.info(f"Finalized dataset with {self.num_episodes} episodes "
|
||||
f"and {self.num_frames} frames across {len(self.task_episode_mapping)} tasks")
|
||||
@@ -0,0 +1,320 @@
|
||||
import numpy as np
|
||||
import torch as th
|
||||
from collections import OrderedDict
|
||||
|
||||
|
||||
ROBOT_CAMERA_NAMES = {
|
||||
"A1": {
|
||||
"external": "external::external_camera",
|
||||
"wrist": "external::wrist_camera",
|
||||
},
|
||||
"R1Pro": {
|
||||
"left_wrist": "robot_r1::robot_r1:left_realsense_link:Camera:0",
|
||||
"right_wrist": "robot_r1::robot_r1:right_realsense_link:Camera:0",
|
||||
"head": "robot_r1::robot_r1:zed_link:Camera:0",
|
||||
},
|
||||
}
|
||||
|
||||
# Camera resolutions and corresponding intrinstics
|
||||
HEAD_RESOLUTION = (720, 720)
|
||||
WRIST_RESOLUTION = (480, 480)
|
||||
# TODO: Fix A1
|
||||
CAMERA_INTRINSICS = {
|
||||
"A1": {
|
||||
"external": np.array([[306.0, 0.0, 360.0], [0.0, 306.0, 360.0], [0.0, 0.0, 1.0]], dtype=np.float32), # 240x240
|
||||
"wrist": np.array(
|
||||
[[388.6639, 0.0, 240.0], [0.0, 388.6639, 240.0], [0.0, 0.0, 1.0]], dtype=np.float32
|
||||
), # 240x240
|
||||
},
|
||||
"R1Pro": {
|
||||
"head": np.array([[306.0, 0.0, 360.0], [0.0, 306.0, 360.0], [0.0, 0.0, 1.0]], dtype=np.float32), # 720x720
|
||||
"left_wrist": np.array(
|
||||
[[388.6639, 0.0, 240.0], [0.0, 388.6639, 240.0], [0.0, 0.0, 1.0]], dtype=np.float32
|
||||
), # 480x480
|
||||
"right_wrist": np.array(
|
||||
[[388.6639, 0.0, 240.0], [0.0, 388.6639, 240.0], [0.0, 0.0, 1.0]], dtype=np.float32
|
||||
), # 480x480
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
# Dataset features for BEHAVIOR-1K LeRobotDataset v3.0
|
||||
BEHAVIOR_DATASET_FEATURES = {
|
||||
# Actions
|
||||
"action": {
|
||||
"dtype": "float32",
|
||||
"shape": (23,), # 23-dimensional action space for R1Pro
|
||||
"names": None,
|
||||
},
|
||||
# Proprioception
|
||||
"observation.state": {
|
||||
"dtype": "float32",
|
||||
"shape": (256,), # Full proprioception state
|
||||
"names": None,
|
||||
},
|
||||
# Camera relative poses
|
||||
"observation.cam_rel_poses": {
|
||||
"dtype": "float32",
|
||||
"shape": (21,), # 3 cameras * 7 (pos + quat)
|
||||
"names": None,
|
||||
},
|
||||
# Task information
|
||||
"observation.task_info": {
|
||||
"dtype": "float32",
|
||||
"shape": (None,), # Variable size
|
||||
"names": None,
|
||||
},
|
||||
# RGB images
|
||||
"observation.images.rgb.head": {
|
||||
"dtype": "video",
|
||||
"shape": [720, 720, 3],
|
||||
"names": ["height", "width", "channels"],
|
||||
},
|
||||
"observation.images.rgb.left_wrist": {
|
||||
"dtype": "video",
|
||||
"shape": [480, 480, 3],
|
||||
"names": ["height", "width", "channels"],
|
||||
},
|
||||
"observation.images.rgb.right_wrist": {
|
||||
"dtype": "video",
|
||||
"shape": [480, 480, 3],
|
||||
"names": ["height", "width", "channels"],
|
||||
},
|
||||
# Depth images
|
||||
"observation.images.depth.head": {
|
||||
"dtype": "video",
|
||||
"shape": [720, 720, 1],
|
||||
"names": ["height", "width", "channels"],
|
||||
},
|
||||
"observation.images.depth.left_wrist": {
|
||||
"dtype": "video",
|
||||
"shape": [480, 480, 1],
|
||||
"names": ["height", "width", "channels"],
|
||||
},
|
||||
"observation.images.depth.right_wrist": {
|
||||
"dtype": "video",
|
||||
"shape": [480, 480, 1],
|
||||
"names": ["height", "width", "channels"],
|
||||
},
|
||||
# Segmentation instance ID images
|
||||
"observation.images.seg_instance_id.head": {
|
||||
"dtype": "video",
|
||||
"shape": [720, 720, 1],
|
||||
"names": ["height", "width", "channels"],
|
||||
},
|
||||
"observation.images.seg_instance_id.left_wrist": {
|
||||
"dtype": "video",
|
||||
"shape": [480, 480, 1],
|
||||
"names": ["height", "width", "channels"],
|
||||
},
|
||||
"observation.images.seg_instance_id.right_wrist": {
|
||||
"dtype": "video",
|
||||
"shape": [480, 480, 1],
|
||||
"names": ["height", "width", "channels"],
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
# Action indices
|
||||
ACTION_QPOS_INDICES = {
|
||||
"A1": OrderedDict(
|
||||
{
|
||||
"arm": np.s_[0:6],
|
||||
"gripper": np.s_[6:7],
|
||||
}
|
||||
),
|
||||
"R1Pro": OrderedDict(
|
||||
{
|
||||
"base": np.s_[0:3],
|
||||
"torso": np.s_[3:7],
|
||||
"left_arm": np.s_[7:14],
|
||||
"left_gripper": np.s_[14:15],
|
||||
"right_arm": np.s_[15:22],
|
||||
"right_gripper": np.s_[22:23],
|
||||
}
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
# Proprioception configuration
|
||||
PROPRIOCEPTION_INDICES = {
|
||||
"A1": OrderedDict(
|
||||
{
|
||||
"joint_qpos": np.s_[0:8],
|
||||
"joint_qpos_sin": np.s_[8:16],
|
||||
"joint_qpos_cos": np.s_[16:24],
|
||||
"joint_qvel": np.s_[24:32],
|
||||
"joint_qeffort": np.s_[32:40],
|
||||
"eef_0_pos": np.s_[40:43],
|
||||
"eef_0_quat": np.s_[43:47],
|
||||
"grasp_0": np.s_[47:48],
|
||||
"gripper_0_qpos": np.s_[48:50],
|
||||
"gripper_0_qvel": np.s_[50:52],
|
||||
}
|
||||
),
|
||||
"R1Pro": OrderedDict(
|
||||
{
|
||||
"joint_qpos": np.s_[
|
||||
0:28
|
||||
], # Full robot joint positions, the first 6 are base joints, which is NOT allowed in standard track
|
||||
"joint_qpos_sin": np.s_[
|
||||
28:56
|
||||
], # Full robot joint positions, the first 6 are base joints, which is NOT allowed in standard track
|
||||
"joint_qpos_cos": np.s_[
|
||||
56:84
|
||||
], # Full robot joint positions, the first 6 are base joints, which is NOT allowed in standard track
|
||||
"joint_qvel": np.s_[84:112],
|
||||
"joint_qeffort": np.s_[112:140],
|
||||
"robot_pos": np.s_[140:143], # Global pos, this is NOT allowed in standard track
|
||||
"robot_ori_cos": np.s_[143:146], # Global ori, this is NOT allowed in standard track
|
||||
"robot_ori_sin": np.s_[146:149], # Global ori, this is NOT allowed in standard track
|
||||
"robot_2d_ori": np.s_[149:150], # 2D global ori, this is NOT allowed in standard track
|
||||
"robot_2d_ori_cos": np.s_[150:151], # 2D global ori, this is NOT allowed in standard track
|
||||
"robot_2d_ori_sin": np.s_[151:152], # 2D global ori, this is NOT allowed in standard track
|
||||
"robot_lin_vel": np.s_[152:155],
|
||||
"robot_ang_vel": np.s_[155:158],
|
||||
"arm_left_qpos": np.s_[158:165],
|
||||
"arm_left_qpos_sin": np.s_[165:172],
|
||||
"arm_left_qpos_cos": np.s_[172:179],
|
||||
"arm_left_qvel": np.s_[179:186],
|
||||
"eef_left_pos": np.s_[186:189],
|
||||
"eef_left_quat": np.s_[189:193],
|
||||
"gripper_left_qpos": np.s_[193:195],
|
||||
"gripper_left_qvel": np.s_[195:197],
|
||||
"arm_right_qpos": np.s_[197:204],
|
||||
"arm_right_qpos_sin": np.s_[204:211],
|
||||
"arm_right_qpos_cos": np.s_[211:218],
|
||||
"arm_right_qvel": np.s_[218:225],
|
||||
"eef_right_pos": np.s_[225:228],
|
||||
"eef_right_quat": np.s_[228:232],
|
||||
"gripper_right_qpos": np.s_[232:234],
|
||||
"gripper_right_qvel": np.s_[234:236],
|
||||
"trunk_qpos": np.s_[236:240],
|
||||
"trunk_qvel": np.s_[240:244],
|
||||
"base_qpos": np.s_[244:247], # Base joint position, this is NOT allowed in standard track
|
||||
"base_qpos_sin": np.s_[247:250], # Base joint position, this is NOT allowed in standard track
|
||||
"base_qpos_cos": np.s_[250:253], # Base joint position, this is NOT allowed in standard track
|
||||
"base_qvel": np.s_[253:256],
|
||||
}
|
||||
),
|
||||
}
|
||||
|
||||
# Proprioception indices
|
||||
PROPRIO_QPOS_INDICES = {
|
||||
"A1": OrderedDict(
|
||||
{
|
||||
"arm": np.s_[0:6],
|
||||
"gripper": np.s_[6:8],
|
||||
}
|
||||
),
|
||||
"R1Pro": OrderedDict(
|
||||
{
|
||||
"torso": np.s_[6:10],
|
||||
"left_arm": np.s_[10:24:2],
|
||||
"right_arm": np.s_[11:24:2],
|
||||
"left_gripper": np.s_[24:26],
|
||||
"right_gripper": np.s_[26:28],
|
||||
}
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
# Joint limits (lower, upper)
|
||||
JOINT_RANGE = {
|
||||
"A1": {
|
||||
"arm": (
|
||||
th.tensor([-2.8798, 0.0, -3.3161, -2.8798, -1.6581, -2.8798], dtype=th.float32),
|
||||
th.tensor([2.8798, 3.1415, 0.0, 2.8798, 1.6581, 2.8798], dtype=th.float32),
|
||||
),
|
||||
"gripper": (th.tensor([0.00], dtype=th.float32), th.tensor([0.03], dtype=th.float32)),
|
||||
},
|
||||
"R1Pro": {
|
||||
"base": (th.tensor([-0.75, -0.75, -1.0], dtype=th.float32), th.tensor([0.75, 0.75, 1.0], dtype=th.float32)),
|
||||
"torso": (
|
||||
th.tensor([-1.1345, -2.7925, -1.8326, -3.0543], dtype=th.float32),
|
||||
th.tensor([1.8326, 2.5307, 1.5708, 3.0543], dtype=th.float32),
|
||||
),
|
||||
"left_arm": (
|
||||
th.tensor([-4.4506, -0.1745, -2.3562, -2.0944, -2.3562, -1.0472, -1.5708], dtype=th.float32),
|
||||
th.tensor([1.3090, 3.1416, 2.3562, 0.3491, 2.3562, 1.0472, 1.5708], dtype=th.float32),
|
||||
),
|
||||
"left_gripper": (th.tensor([0.00], dtype=th.float32), th.tensor([0.05], dtype=th.float32)),
|
||||
"right_arm": (
|
||||
th.tensor([-4.4506, -3.1416, -2.3562, -2.0944, -2.3562, -1.0472, -1.5708], dtype=th.float32),
|
||||
th.tensor([1.3090, 0.1745, 2.3562, 0.3491, 2.3562, 1.0472, 1.5708], dtype=th.float32),
|
||||
),
|
||||
"right_gripper": (th.tensor([0.00], dtype=th.float32), th.tensor([0.05], dtype=th.float32)),
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
EEF_POSITION_RANGE = {
|
||||
"A1": {
|
||||
"0": (th.tensor([0.0, -0.7, 0.0], dtype=th.float32), th.tensor([0.7, 0.7, 0.7], dtype=th.float32)),
|
||||
},
|
||||
"R1Pro": {
|
||||
"left": (th.tensor([0.0, -0.65, 0.0], dtype=th.float32), th.tensor([0.65, 0.65, 2.5], dtype=th.float32)),
|
||||
"right": (th.tensor([0.0, -0.65, 0.0], dtype=th.float32), th.tensor([0.65, 0.65, 2.5], dtype=th.float32)),
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
TASK_NAMES_TO_INDICES = {
|
||||
# B10
|
||||
"turning_on_radio": 0,
|
||||
"picking_up_trash": 1,
|
||||
"putting_away_Halloween_decorations": 2,
|
||||
"cleaning_up_plates_and_food": 3,
|
||||
"can_meat": 4,
|
||||
"setting_mousetraps": 5,
|
||||
"hiding_Easter_eggs": 6,
|
||||
"picking_up_toys": 7,
|
||||
"rearranging_kitchen_furniture": 8,
|
||||
"putting_up_Christmas_decorations_inside": 9,
|
||||
# B20
|
||||
"set_up_a_coffee_station_in_your_kitchen": 10,
|
||||
"putting_dishes_away_after_cleaning": 11,
|
||||
"preparing_lunch_box": 12,
|
||||
"loading_the_car": 13,
|
||||
"carrying_in_groceries": 14,
|
||||
"bringing_in_wood": 15,
|
||||
"moving_boxes_to_storage": 16,
|
||||
"bringing_water": 17,
|
||||
"tidying_bedroom": 18,
|
||||
"outfit_a_basic_toolbox": 19,
|
||||
# B30
|
||||
"sorting_vegetables": 20,
|
||||
"collecting_childrens_toys": 21,
|
||||
"putting_shoes_on_rack": 22,
|
||||
"boxing_books_up_for_storage": 23,
|
||||
"storing_food": 24,
|
||||
"clearing_food_from_table_into_fridge": 25,
|
||||
"assembling_gift_baskets": 26,
|
||||
"sorting_household_items": 27,
|
||||
"getting_organized_for_work": 28,
|
||||
"clean_up_your_desk": 29,
|
||||
# B40
|
||||
"setting_the_fire": 30,
|
||||
"clean_boxing_gloves": 31,
|
||||
"wash_a_baseball_cap": 32,
|
||||
"wash_dog_toys": 33,
|
||||
"hanging_pictures": 34,
|
||||
"attach_a_camera_to_a_tripod": 35,
|
||||
"clean_a_patio": 36,
|
||||
"clean_a_trumpet": 37,
|
||||
"spraying_for_bugs": 38,
|
||||
"spraying_fruit_trees": 39,
|
||||
# B50
|
||||
"make_microwave_popcorn": 40,
|
||||
"cook_cabbage": 41,
|
||||
"chop_an_onion": 42,
|
||||
"slicing_vegetables": 43,
|
||||
"chopping_wood": 44,
|
||||
"cook_hot_dogs": 45,
|
||||
"cook_bacon": 46,
|
||||
"freeze_pies": 47,
|
||||
"canning_food": 48,
|
||||
"make_pizza": 49,
|
||||
}
|
||||
TASK_INDICES_TO_NAMES = {v: k for k, v in TASK_NAMES_TO_INDICES.items()}
|
||||
|
||||
+283
@@ -0,0 +1,283 @@
|
||||
#!/usr/bin/env python
|
||||
|
||||
import argparse
|
||||
import h5py
|
||||
import numpy as np
|
||||
import os
|
||||
import torch as th
|
||||
from pathlib import Path
|
||||
from tqdm import tqdm
|
||||
import logging
|
||||
|
||||
from .behavior_lerobot_dataset_v3 import BehaviorLeRobotDatasetV3
|
||||
from .behaviour_1k_constants import TASK_NAMES_TO_INDICES, TASK_INDICES_TO_NAMES, BEHAVIOR_DATASET_FEATURES
|
||||
|
||||
from lerobot.utils.utils import init_logging
|
||||
|
||||
init_logging()
|
||||
|
||||
def load_hdf5_episode(hdf5_path: str, episode_id: int = 0) -> dict:
|
||||
"""
|
||||
Load episode data from HDF5 file.
|
||||
|
||||
Args:
|
||||
hdf5_path: Path to the HDF5 file
|
||||
episode_id: Episode ID to load (default: 0)
|
||||
|
||||
Returns:
|
||||
Dictionary containing episode data
|
||||
"""
|
||||
episode_data = {}
|
||||
|
||||
with h5py.File(hdf5_path, "r") as f:
|
||||
# Find the episode with most samples if episode_id not specified
|
||||
if episode_id == -1:
|
||||
num_samples = [f["data"][key].attrs["num_samples"] for key in f["data"].keys()]
|
||||
episode_id = num_samples.index(max(num_samples))
|
||||
|
||||
demo_key = f"demo_{episode_id}"
|
||||
if demo_key not in f["data"]:
|
||||
raise ValueError(f"Episode {episode_id} not found in {hdf5_path}")
|
||||
|
||||
demo_data = f["data"][demo_key]
|
||||
|
||||
# Load actions
|
||||
episode_data["action"] = np.array(demo_data["action"][:])
|
||||
|
||||
# Load observations
|
||||
episode_data["obs"] = {}
|
||||
for key in demo_data["obs"].keys():
|
||||
episode_data["obs"][key] = np.array(demo_data["obs"][key][:])
|
||||
|
||||
# Load attributes
|
||||
episode_data["attrs"] = {}
|
||||
for attr_name in demo_data.attrs:
|
||||
episode_data["attrs"][attr_name] = demo_data.attrs[attr_name]
|
||||
|
||||
# Add global attributes
|
||||
for attr_name in f["data"].attrs:
|
||||
episode_data["attrs"][f"global_{attr_name}"] = f["data"].attrs[attr_name]
|
||||
|
||||
return episode_data
|
||||
|
||||
|
||||
def convert_episode(
|
||||
data_folder: str,
|
||||
output_repo_id: str,
|
||||
task_id: int,
|
||||
demo_id: int,
|
||||
dataset: BehaviorLeRobotDatasetV3,
|
||||
include_videos: bool = True,
|
||||
include_segmentation: bool = True,
|
||||
) -> None:
|
||||
"""
|
||||
Convert a single episode from HDF5 to LeRobotDataset v3.0 format.
|
||||
|
||||
Args:
|
||||
data_folder: Base data folder containing HDF5 files
|
||||
output_repo_id: Output repository ID for the dataset
|
||||
task_id: Task ID
|
||||
demo_id: Demo ID (episode ID)
|
||||
dataset: BehaviorLeRobotDatasetV3 instance to add data to
|
||||
include_videos: Whether to include video data
|
||||
include_segmentation: Whether to include segmentation data
|
||||
"""
|
||||
# Construct paths
|
||||
task_name = TASK_INDICES_TO_NAMES[task_id]
|
||||
hdf5_path = f"{data_folder}/2025-challenge-rawdata/task-{task_id:04d}/episode_{demo_id:08d}.hdf5"
|
||||
|
||||
if not os.path.exists(hdf5_path):
|
||||
logging.error(f"HDF5 file not found: {hdf5_path}")
|
||||
return
|
||||
|
||||
logging.info(f"Converting episode {demo_id} from task {task_name}")
|
||||
|
||||
# Load episode data
|
||||
try:
|
||||
episode_data = load_hdf5_episode(hdf5_path, episode_id=0)
|
||||
except Exception as e:
|
||||
logging.error(f"Failed to load episode data: {e}")
|
||||
return
|
||||
|
||||
# Filter out segmentation if not requested
|
||||
if not include_segmentation:
|
||||
keys_to_remove = [k for k in episode_data["obs"].keys() if "seg_instance_id" in k]
|
||||
for key in keys_to_remove:
|
||||
del episode_data["obs"][key]
|
||||
|
||||
# Add episode to dataset
|
||||
dataset.add_episode_from_hdf5(
|
||||
hdf5_data=episode_data,
|
||||
task_id=task_id,
|
||||
episode_id=demo_id,
|
||||
include_videos=include_videos,
|
||||
)
|
||||
|
||||
|
||||
def convert_dataset(
|
||||
data_folder: str,
|
||||
output_repo_id: str,
|
||||
task_names: list = None,
|
||||
episode_ids: list = None,
|
||||
max_episodes_per_task: int = None,
|
||||
include_videos: bool = True,
|
||||
include_segmentation: bool = True,
|
||||
fps: int = 30,
|
||||
batch_encoding_size: int = 1,
|
||||
image_writer_processes: int = 0,
|
||||
image_writer_threads: int = 4,
|
||||
push_to_hub: bool = False,
|
||||
) -> None:
|
||||
"""
|
||||
Convert BEHAVIOR-1K dataset from HDF5 to LeRobotDataset v3.0 format.
|
||||
|
||||
Args:
|
||||
data_folder: Base folder containing HDF5 data
|
||||
output_repo_id: Output repository ID (e.g., "username/dataset-name")
|
||||
task_names: List of task names to convert (None = all tasks)
|
||||
episode_ids: Specific episode IDs to convert (None = all episodes)
|
||||
max_episodes_per_task: Maximum episodes per task to convert
|
||||
include_videos: Whether to include video data
|
||||
include_segmentation: Whether to include segmentation data
|
||||
fps: Frames per second
|
||||
batch_encoding_size: Number of episodes to batch before encoding
|
||||
image_writer_processes: Number of processes for image writing
|
||||
image_writer_threads: Number of threads for image writing
|
||||
push_to_hub: Whether to push to HuggingFace Hub
|
||||
"""
|
||||
# Create output directory
|
||||
output_dir = Path.home() / ".cache/huggingface/lerobot" / output_repo_id
|
||||
output_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
logging.info(f"Converting dataset to: {output_dir}")
|
||||
|
||||
# Initialize dataset
|
||||
dataset = BehaviorLeRobotDatasetV3.create(
|
||||
repo_id=output_repo_id,
|
||||
root=output_dir,
|
||||
fps=fps,
|
||||
robot_type="R1Pro",
|
||||
use_videos=include_videos,
|
||||
video_backend="pyav",
|
||||
batch_encoding_size=batch_encoding_size,
|
||||
image_writer_processes=image_writer_processes,
|
||||
image_writer_threads=image_writer_threads,
|
||||
)
|
||||
|
||||
# Determine which tasks to process
|
||||
if task_names is None:
|
||||
task_names = list(TASK_NAMES_TO_INDICES.keys())
|
||||
|
||||
task_ids = [TASK_NAMES_TO_INDICES[name] for name in task_names]
|
||||
|
||||
# Process each task
|
||||
total_episodes = 0
|
||||
for task_id in tqdm(task_ids, desc="Processing tasks"):
|
||||
task_name = TASK_INDICES_TO_NAMES[task_id]
|
||||
task_folder = f"{data_folder}/2025-challenge-rawdata/task-{task_id:04d}"
|
||||
|
||||
if not os.path.exists(task_folder):
|
||||
logging.warning(f"Task folder not found: {task_folder}")
|
||||
continue
|
||||
|
||||
# Find all episodes for this task
|
||||
if episode_ids is not None:
|
||||
# Use specified episode IDs
|
||||
task_episode_ids = [eid for eid in episode_ids if eid // 10000 == task_id]
|
||||
else:
|
||||
# Find all episodes in the task folder
|
||||
task_episode_ids = []
|
||||
for filename in os.listdir(task_folder):
|
||||
if filename.startswith("episode_") and filename.endswith(".hdf5"):
|
||||
eid = int(filename.split("_")[1].split(".")[0])
|
||||
task_episode_ids.append(eid)
|
||||
task_episode_ids.sort()
|
||||
|
||||
# Limit episodes if requested
|
||||
if max_episodes_per_task is not None:
|
||||
task_episode_ids = task_episode_ids[:max_episodes_per_task]
|
||||
|
||||
logging.info(f"Processing {len(task_episode_ids)} episodes for task {task_name}")
|
||||
|
||||
# Convert each episode
|
||||
for demo_id in tqdm(task_episode_ids, desc=f"Task {task_name}", leave=False):
|
||||
try:
|
||||
convert_episode(
|
||||
data_folder=data_folder,
|
||||
output_repo_id=output_repo_id,
|
||||
task_id=task_id,
|
||||
demo_id=demo_id,
|
||||
dataset=dataset,
|
||||
include_videos=include_videos,
|
||||
include_segmentation=include_segmentation,
|
||||
)
|
||||
total_episodes += 1
|
||||
except Exception as e:
|
||||
logging.error(f"Failed to convert episode {demo_id}: {e}")
|
||||
continue
|
||||
|
||||
logging.info(f"Converted {total_episodes} episodes total")
|
||||
|
||||
# Finalize dataset
|
||||
logging.info("Finalizing dataset...")
|
||||
dataset.finalize()
|
||||
|
||||
# Push to hub if requested
|
||||
if push_to_hub:
|
||||
logging.info("Pushing dataset to HuggingFace Hub...")
|
||||
dataset.push_to_hub(
|
||||
private=True,
|
||||
license="apache-2.0",
|
||||
)
|
||||
|
||||
logging.info("Conversion complete!")
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(description="Convert BEHAVIOR-1K data to LeRobotDataset v3.0")
|
||||
parser.add_argument("--data_folder", type=str, required=True, help="Path to the data folder")
|
||||
parser.add_argument("--output_repo_id", type=str, required=True,
|
||||
help="Output repository ID (e.g., 'username/behavior-dataset-v3')")
|
||||
parser.add_argument("--task_names", type=str, nargs="+", default=None,
|
||||
help="Task names to convert (default: all)")
|
||||
parser.add_argument("--episode_ids", type=int, nargs="+", default=None,
|
||||
help="Specific episode IDs to convert")
|
||||
parser.add_argument("--max_episodes_per_task", type=int, default=None,
|
||||
help="Maximum episodes per task to convert")
|
||||
parser.add_argument("--no_videos", action="store_true",
|
||||
help="Exclude video data")
|
||||
parser.add_argument("--no_segmentation", action="store_true",
|
||||
help="Exclude segmentation data")
|
||||
parser.add_argument("--fps", type=int, default=30,
|
||||
help="Frames per second (default: 30)")
|
||||
parser.add_argument("--batch_encoding_size", type=int, default=1,
|
||||
help="Number of episodes to batch before encoding videos")
|
||||
parser.add_argument("--image_writer_processes", type=int, default=0,
|
||||
help="Number of processes for async image writing")
|
||||
parser.add_argument("--image_writer_threads", type=int, default=4,
|
||||
help="Number of threads for image writing")
|
||||
parser.add_argument("--push_to_hub", action="store_true",
|
||||
help="Push dataset to HuggingFace Hub")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
# Convert dataset
|
||||
convert_dataset(
|
||||
data_folder=args.data_folder,
|
||||
output_repo_id=args.output_repo_id,
|
||||
task_names=args.task_names,
|
||||
episode_ids=args.episode_ids,
|
||||
max_episodes_per_task=args.max_episodes_per_task,
|
||||
include_videos=not args.no_videos,
|
||||
include_segmentation=not args.no_segmentation,
|
||||
fps=args.fps,
|
||||
batch_encoding_size=args.batch_encoding_size,
|
||||
image_writer_processes=args.image_writer_processes,
|
||||
image_writer_threads=args.image_writer_threads,
|
||||
push_to_hub=args.push_to_hub,
|
||||
)
|
||||
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user