pi05-franka-graspnet

openpi π₀.₅ policy checkpoint.

• Train config: pi05_Franka_GRASPNET
• Experiment: GRASPNET
• Step: 29999
• Training dataset: saifahmad123/Franka_GRASPNET

Contents

Path	Purpose
params/	Model weights. Required to serve the policy.
assets/	Normalization statistics. Required to serve the policy.
train_state/	Optimizer state. Only present if uploaded with --include-train-state; needed to resume training.

Usage

from huggingface_hub import snapshot_download
from openpi.policies import policy_config
from openpi.training import config as _config

ckpt = snapshot_download("saifahmad123/pi05-franka-graspnet")
train_config = _config.get_config("pi05_Franka_GRASPNET")
policy = policy_config.create_trained_policy(train_config, ckpt)

action_chunk = policy.infer(observation)["actions"]