52 lines
1.6 KiB
YAML
52 lines
1.6 KiB
YAML
# π0.5 VLA: one diffusion stage, one GPU, eager, bsz 1 (OpenPI policy serving is
|
|
# one observation -> one action reply). Every key below is documented in
|
|
# recipes/lerobot/Pi05.md.
|
|
|
|
pipeline: pi05
|
|
async_chunk: false
|
|
distributed_executor_backend: mp
|
|
# float32 or bfloat16. bfloat16 is faster and halves memory at a numerical cost;
|
|
# read "Choosing a dtype" in the recipe before switching.
|
|
dtype: float32
|
|
|
|
stages:
|
|
- stage_id: 0
|
|
devices: "0"
|
|
max_num_seqs: 1
|
|
enforce_eager: true
|
|
model_class_name: Pi05Pipeline
|
|
model_config:
|
|
paligemma_variant: gemma_2b
|
|
action_expert_variant: gemma_300m
|
|
chunk_size: 50
|
|
# Must equal chunk_size: this endpoint returns the whole chunk and keeps no
|
|
# action queue, so "execute the first N steps, then replan" is not available.
|
|
n_action_steps: 50
|
|
max_action_dim: 32
|
|
max_state_dim: 32
|
|
num_inference_steps: 10
|
|
image_resolution: [224, 224]
|
|
tokenizer_max_length: 200
|
|
state_num_bins: 256
|
|
max_cameras: 3
|
|
image_feature_keys:
|
|
- observation.images.base_0_rgb
|
|
- observation.images.left_wrist_0_rgb
|
|
- observation.images.right_wrist_0_rgb
|
|
image_key_map: {}
|
|
use_relative_actions: false
|
|
relative_exclude_joints:
|
|
- gripper
|
|
# OpenPI handshake metadata advertised to the robot client.
|
|
policy_server_config:
|
|
image_resolution: [224, 224]
|
|
n_external_cameras: 1
|
|
needs_wrist_camera: true
|
|
needs_stereo_camera: false
|
|
needs_session_id: false
|
|
action_space: joint_position
|
|
action_horizon: 50
|
|
action_dim: 32
|
|
max_action_dim: 32
|
|
max_cameras: 3
|