pip install 'lerobot[multi_task_dit]'

policy.type=multi_task_dit

lerobot-train \
  --dataset.repo_id=YOUR_DATASET \
  --output_dir=./outputs/multitask_dit_training \
  --batch_size=32 \
  --steps=5000 \
  --save_freq=500 \
  --log_freq=100 \
  --policy.type=multi_task_dit \
  --policy.device=cuda \
  --policy.repo_id="HF_USER/multitask-dit-your-robot" \
  --trackio.enable=true

lerobot-train \
  --dataset.repo_id=YOUR_DATASET \
  --output_dir=./outputs/mutitask_dit_training \
  --batch_size=320 \
  --steps=30000 \
  --policy.type=multi_task_dit \
  --policy.device=cuda \
  --policy.horizon=32 \
  --policy.n_action_steps=24 \
  --policy.objective=diffusion \
  --policy.noise_scheduler_type=DDPM \
  --policy.num_train_timesteps=100 \
  --policy.repo_id="HF_USER/multitask-dit-your-robot" \
  --trackio.enable=true

# Diffusion objective (default)
--policy.objective=diffusion \
--policy.noise_scheduler_type=DDPM \
--policy.num_train_timesteps=100 \
--policy.num_inference_steps=10 \
--policy.beta_schedule=squaredcos_cap_v2 \
--policy.prediction_type=epsilon \
--policy.clip_sample=true \
--policy.clip_sample_range=1.0

# Flow matching objective
--policy.objective=flow_matching \
--policy.timestep_sampling_strategy=beta \
--policy.num_integration_steps=100 \
--policy.integration_method=euler \
--policy.sigma_min=0.0

# Small datasets (< 100 examples)
--policy.num_layers=4 \
--policy.hidden_dim=512 \
--policy.num_heads=8  # should ideally be hidden_dim // 64

# Medium datasets (100-5k examples) - default
--policy.num_layers=6 \
--policy.hidden_dim=512 \
--policy.num_heads=8  # should ideally be hidden_dim // 64

# Large datasets (> 5k examples)
--policy.num_layers=8 \
--policy.hidden_dim=512 \
--policy.num_heads=8   # should ideally be hidden_dim // 64

# Rotary Position Embedding (RoPE) - default, recommended
--policy.use_rope=true \
--policy.rope_base=10000.0  # Base frequency for RoPE

# Absolute positional encoding
--policy.use_positional_encoding=true  # Disables RoPE when true

--policy.dropout=0.1  # Dropout rate for DiT blocks (0.0-1.0)
--policy.timestep_embed_dim=256  # Timestep embedding dimension

# Use different CLIP model for more expressivity at the cost of inference time
# experiment with larger or smaller models depending on the complexity of your tasks and size of dataset
--policy.vision_encoder_name=openai/clip-vit-large-patch14

# Use separate vision encoder per camera
# This may be useful when cameras have significantly different characteristics, but
# be wary of increased VRAM footprint.
--policy.use_separate_rgb_encoder_per_camera=true

# Image preprocessing (you may need to resize your images for inference speed ups)
--policy.image_resize_shape=[XXX,YYY] \
--policy.image_crop_shape=[224,224] \
--policy.image_crop_is_random=true  # Random during training, center at inference

# Use different CLIP text encoder model
# same as vision: experiment with larger or smaller models depending on the
# complexity of your tasks and size of dataset
--policy.text_encoder_name=openai/clip-vit-large-patch14

--policy.optimizer_lr=2e-5 \
--policy.vision_encoder_lr_multiplier=0.1  # Vision encoder LR = 0.1 * optimizer_lr

--policy.objective=flow_matching \
--policy.timestep_sampling_strategy=beta \
--policy.timestep_sampling_alpha=1.5 \
--policy.timestep_sampling_beta=1.0 \
--policy.timestep_sampling_s=0.999

--policy.noise_scheduler_type=DDIM \
--policy.num_inference_steps=10

lerobot-train \
  --config_path=./outputs/mutitask_dit_training/checkpoints/last/pretrained_model/train_config.json \
  --resume=true

lerobot-train \
  --dataset.repo_id=YOUR_DATASET \
  --output_dir=./outputs/mutitask_dit_training \
  --batch_size=320 \
  --steps=30000 \
  --save_freq=1000 \
  --log_freq=100 \
  --env_eval_freq=1000 \
  --policy.type=multi_task_dit \
  --policy.device=cuda \
  --policy.horizon=32 \
  --policy.n_action_steps=24 \
  --policy.objective=diffusion \
  --policy.noise_scheduler_type=DDPM \
  --policy.num_layers=6 \
  --policy.hidden_dim=512 \
  --policy.vision_encoder_name=openai/clip-vit-base-patch16 \
  --policy.image_resize_shape=[320,240] \
  --policy.image_crop_shape=[224,224] \
  --policy.repo_id="HF_USER/multitask-dit-your-robot" \
  --trackio.enable=true \
  --trackio.project=multitask_dit

lerobot-train \
  --dataset.repo_id=HuggingFaceVLA/libero \
  --policy.type=multi_task_dit \
  --policy.push_to_hub=false \
  --output_dir="./outputs/multitask_dit_libero" \
  --job_name="multitask-dit-libero" \
  --trackio.enable=true \
  --trackio.project=multitask_dit_libero \
  --dataset.image_transforms.enable=true \
  --dataset.image_transforms.max_num_transforms=4 \
  --dataset.image_transforms.tfs='{"brightness":{"type":"ColorJitter","kwargs":{"brightness":[0.75,1.25]}},"contrast":{"type":"ColorJitter","kwargs":{"contrast":[0.6,1.4]}},"saturation":{"type":"ColorJitter","kwargs":{"saturation":[0.8,1.2]}},"hue":{"type":"ColorJitter","kwargs":{"hue":[-0.05,0.05]}},"sharpness":{"type":"SharpnessJitter","kwargs":{"sharpness":[0.6,1.4]}},"rotation":{"type":"RandomRotation","kwargs":{"degrees":[-5,5]}},"translation":{"type":"RandomAffine","kwargs":{"degrees":0,"translate":[0.1,0.1]}}}' \
  --dataset.video_backend=torchcodec \
  --policy.use_amp=true \
  --policy.horizon=48 \
  --policy.n_obs_steps=2 \
  --policy.use_rope=true \
  --policy.use_positional_encoding=false \
  --policy.hidden_dim=768 \
  --policy.num_layers=8 \
  --policy.num_heads=12 \
  --policy.dropout=0.1 \
  --policy.timestep_embed_dim=256 \
  --policy.objective=diffusion \
  --policy.optimizer_lr=3e-4 \
  --policy.optimizer_weight_decay=0 \
  --policy.scheduler_warmup_steps=0 \
  --policy.vision_encoder_name=openai/clip-vit-base-patch16 \
  --policy.image_resize_shape=[256,256] \
  --policy.image_crop_is_random=true \
  --policy.text_encoder_name=openai/clip-vit-base-patch16 \
  --policy.vision_encoder_lr_multiplier=0.1 \
  --policy.device=cuda \
  --num_workers=8 \
  --save_freq=4000 \
  --log_freq=100 \
  --steps=100000 \
  --batch_size=320