Views
No views yet
pi05_droid model on DROID episodes with 2D gripper/object trajectory overlays rendered on exterior_image_1_left. The overlays were produced by a Gemini ER + SAM2 tracking pipeline (see dataset card).| Setting | Value |
|---|---|
| Base model | gs://openpi-assets/checkpoints/pi05_droid |
| Dataset | brandonyang/droid_1.0.1_trajectory_overlay (4,444 episodes) |
| Config | pi05_droid_finetune |
| Steps | 20,000 |
| Batch size | 32 |
| Hardware | 4× A100 80GB |
| Total train time | ~20.8 hours |
| Final loss | 0.0064 (from initial 2.24) |
| Step | Loss | Grad Norm |
|---|---|---|
| 0 | 2.2385 | 18.17 |
| 1,000 | 0.0228 | 0.43 |
| 5,000 | 0.0130 | 0.23 |
| 10,000 | 0.0098 | 0.17 |
| 15,000 | 0.0083 | 0.13 |
| 19,900 | 0.0064 | 0.12 |
1uv run scripts/serve_policy.py policy:checkpoint \
2 --policy.config=pi05_droid \
3 --policy.dir=<local_path_to_this_checkpoint>1from huggingface_hub import snapshot_download
2snapshot_download("brandonyang/pi05_droid_trajectory_overlay", local_dir="./pi05_droid_trajectory_overlay")exterior_image_1_left observations with trajectory overlays drawn (same style as training data) to the policy.params/ — model weights (12 GB)assets/ — norm stats + metadata (reused from base pi05_droid)_CHECKPOINT_METADATA — orbax checkpoint metadatatrain_state/) is not included — this is an inference-only checkpoint.