LeRobotDataset v3.0

lerobot-record \
  --robot.type=so101_follower \
  --robot.port=/dev/tty.usbmodem585A0076841 \
  --robot.id=my_awesome_follower_arm \
  --robot.cameras="{ front: {type: opencv, index_or_path: 0, width: 1920, height: 1080, fps: 30}}" \
  --teleop.type=so101_leader \
  --teleop.port=/dev/tty.usbmodem58760431551 \
  --teleop.id=my_awesome_leader_arm \
  --display_data=true \
  --dataset.repo_id=${HF_USER}/record-test \
  --dataset.num_episodes=5 \
  --dataset.single_task="Grab the black cube" \
  --dataset.streaming_encoding=true \
  --dataset.encoder_threads=2
# Optional: --dataset.rgb_encoder.vcodec=auto

import torch
from lerobot.datasets import LeRobotDataset

repo_id = "yaak-ai/L2D-v3"

# 1) Load from the Hub (cached locally)
dataset = LeRobotDataset(repo_id)

# 2) Random access by index
sample = dataset[100]
print(sample)
# {
#   'observation.state': tensor([...]),
#   'action': tensor([...]),
#   'observation.images.front_left': tensor([C, H, W]),
#   'timestamp': tensor(1.234),
#   ...
# }

# 3) Temporal windows via delta_timestamps (seconds relative to t)
delta_timestamps = {
    "observation.images.front_left": [-0.2, -0.1, 0.0]  # 0.2s and 0.1s before current frame
}

dataset = LeRobotDataset(repo_id, delta_timestamps=delta_timestamps)

# Accessing an index now returns a stack for the specified key(s)
sample = dataset[100]
print(sample["observation.images.front_left"].shape)  # [T, C, H, W], where T=3

# 4) Wrap with a DataLoader for training
batch_size = 16
data_loader = torch.utils.data.DataLoader(dataset, batch_size=batch_size)

device = "cuda" if torch.cuda.is_available() else "cpu"
for batch in data_loader:
    observations = batch["observation.state"].to(device)
    actions = batch["action"].to(device)
    images = batch["observation.images.front_left"].to(device)
    # model.forward(batch)

from lerobot.datasets import StreamingLeRobotDataset

repo_id = "yaak-ai/L2D-v3"
dataset = StreamingLeRobotDataset(repo_id)  # streams directly from the Hub

dataset = StreamingLeRobotDataset("my-org/my-bucket", repo_type="bucket")

lerobot-train \
  --dataset.repo_id=my-org/my-bucket \
  --dataset.repo_type=bucket \
  --dataset.streaming=true \
  ...

from lerobot.datasets import LeRobotDataset
from lerobot.transforms import ImageTransforms, ImageTransformsConfig, ImageTransformConfig

# Option 1: Use default transform configuration (disabled by default)
transforms_config = ImageTransformsConfig(
    enable=True,  # Enable transforms
    max_num_transforms=3,  # Apply up to 3 transforms per frame
    random_order=False,  # Apply in standard order
)
transforms = ImageTransforms(transforms_config)

dataset = LeRobotDataset(
    repo_id="your-username/your-dataset",
    image_transforms=transforms
)

# Option 2: Create custom transform configuration
custom_transforms_config = ImageTransformsConfig(
    enable=True,
    max_num_transforms=2,
    random_order=True,
    tfs={
        "brightness": ImageTransformConfig(
            weight=1.0,
            type="ColorJitter",
            kwargs={"brightness": (0.7, 1.3)}  # Adjust brightness range
        ),
        "contrast": ImageTransformConfig(
            weight=2.0,  # Higher weight = more likely to be selected
            type="ColorJitter",
            kwargs={"contrast": (0.8, 1.2)}
        ),
        "sharpness": ImageTransformConfig(
            weight=0.5,  # Lower weight = less likely to be selected
            type="SharpnessJitter",
            kwargs={"sharpness": (0.3, 2.0)}
        ),
    }
)

dataset = LeRobotDataset(
    repo_id="your-username/your-dataset",
    image_transforms=ImageTransforms(custom_transforms_config)
)

# Option 3: Use pure torchvision transforms
from torchvision.transforms import v2

torchvision_transforms = v2.Compose([
    v2.ColorJitter(brightness=0.2, contrast=0.2, saturation=0.2, hue=0.1),
    v2.GaussianBlur(kernel_size=3, sigma=(0.1, 2.0)),
])

dataset = LeRobotDataset(
    repo_id="your-username/your-dataset",
    image_transforms=torchvision_transforms
)

lerobot-imgtransform-viz \
  --repo-id=your-username/your-dataset \
  --output-dir=./transform_examples \
  --n-examples=5

# Pre-release build with v3 support:
pip install "https://github.com/huggingface/lerobot/archive/33cad37054c2b594ceba57463e8f11ee374fa93c.zip"

# Convert an existing v2.1 dataset hosted on the Hub:
python -m lerobot.scripts.convert_dataset_v21_to_v30 --repo-id=<HF_USER/DATASET_ID>

from lerobot.datasets import LeRobotDataset

# Create dataset and record episodes
dataset = LeRobotDataset.create(...)

for episode in range(num_episodes):
    # Record frames
    for frame in episode_data:
        dataset.add_frame(frame)
    dataset.save_episode()

# Call finalize() when done recording and before push_to_hub()
dataset.finalize()  # Closes parquet writers, writes metadata footers
dataset.push_to_hub()

from lerobot.datasets import LeRobotDatasetMetadata
from lerobot.policies.diffusion.configuration_diffusion import DiffusionConfig
from lerobot_lancedb import LeRobotLanceDataset, LeRobotLanceVideoDataset

cfg = DiffusionConfig(...)
meta = LeRobotDatasetMetadata(root=local_dataset_path)  # or use repo_id=... to load metadata from the Hub
delta_timestamps = {...}

# Use LeRobotLanceDataset for image datasets
dataset = LeRobotLanceDataset(
    root=local_dataset_path,                            # or use repo_id=... to stream from the Hub
    delta_timestamps=delta_timestamps,
    return_uint8=True,
)
# Or use LeRobotLanceVideoDataset for video datasets:
dataset = LeRobotLanceVideoDataset(
    root=local_dataset_path,                            # or use repo_id=... to stream from the Hub
    delta_timestamps=delta_timestamps,
    return_uint8=True,
)