| 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. | |
| - **Training dataset:** [saifahmad123/GRASPNET_FINAL_moreData](https://huggingface.co/datasets/saifahmad123/GRASPNET_FINAL_moreData) | |
| ## 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 | |
| ```python | |
| 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"] | |
| ``` | |