Hugging Face's logo

saifahmad123
/
GRASPNET_FINAL_moreData_h100

Robotics
openpi
pi0
franka
Model card Files
xet
 Community
GRASPNET_FINAL_moreData_h100 / README.md
saifahmad123's picture
saifahmad123
Upload README.md with huggingface_hub
025a3c3 verified
preview code
|
Raw
History Blame Contribute Delete
1.3 kB
metadata 
library_name: openpi
tags:
  - robotics
  - openpi
  - pi0
  - franka

GRASPNET_FINAL_moreData_h100

openpi π₀.₅ policy checkpoint.

  • Train config: pi05_Franka_GRASPNET_FINAL_moreData

  • Experiment: GRASPNET_FINAL_moreData_h100

  • Checkpoints in this repo:

  • step_50000/

  • step_99999/

Each folder is one training step and is self-contained.

Contents

Path Purpose
step_50000/params/ Model weights. Required to serve the policy.
step_50000/assets/ Normalization statistics. Required to serve the policy.
step_50000/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/GRASPNET_FINAL_moreData_h100", allow_patterns="step_50000/*") + "/step_50000"
train_config = _config.get_config("pi05_Franka_GRASPNET_FINAL_moreData")
policy = policy_config.create_trained_policy(train_config, ckpt)

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