Upload pi0.5 UR7e PickandPlace 30-epoch (step 4300) with model card

Browse files

Files changed (8) hide show

README.md +100 -0
config.json +108 -0
model.safetensors +3 -0
policy_postprocessor.json +32 -0
policy_postprocessor_step_0_unnormalizer_processor.safetensors +3 -0
policy_preprocessor.json +90 -0
policy_preprocessor_step_2_normalizer_processor.safetensors +3 -0
train_config.json +251 -0

README.md ADDED Viewed

	@@ -0,0 +1,100 @@

+---
+license: apache-2.0
+library_name: lerobot
+pipeline_tag: robotics
+model_name: pi05
+base_model: lerobot/pi05_base
+datasets:
+- CoRL2026-CSI/UR7e_CaP_PickandPlace_100epi_10fps
+tags:
+- robotics
+- lerobot
+- pi05
+- vision-language-action
+- imitation-learning
+- safetensors
+- ur7e
+---
+# Model Card for π0.5 — UR7e PickandPlace (30 epoch)
+**π₀.₅ (Pi05) Policy**
+π₀.₅ is a Vision-Language-Action model with open-world generalization, from
+Physical Intelligence. The LeRobot implementation is adapted from their open
+source OpenPI repository. See the
+[Physical Intelligence π₀.₅ blog post](https://www.physicalintelligence.company/blog/pi05).
+This checkpoint is a **fine-tune of [`lerobot/pi05_base`](https://huggingface.co/lerobot/pi05_base)**
+on the [`CoRL2026-CSI/UR7e_CaP_PickandPlace_100epi_10fps`](https://huggingface.co/datasets/CoRL2026-CSI/UR7e_CaP_PickandPlace_100epi_10fps)
+dataset for a UR7e single-arm pick-and-place task.
+This policy has been trained and pushed to the Hub using
+[LeRobot](https://github.com/huggingface/lerobot). See the full documentation at
+[LeRobot Docs](https://huggingface.co/docs/lerobot/index).
+---
+## Training Summary
+| Field | Value |
+|---|---|
+| Base model | `lerobot/pi05_base` |
+| Dataset | `CoRL2026-CSI/UR7e_CaP_PickandPlace_100epi_10fps` (100 eps, 35,878 frames, 10 fps) |
+| Robot | UR7e single-arm, 7-DoF (6 joints + gripper) |
+| Cameras | `realsense_topview`, `realsense_wrist` (renamed → `base_0_rgb`/`left_wrist_0_rgb`) |
+| Steps | 4,300  (≈ 30 epoch · 35878 × 30 / 256) |
+| Batch | 32 × 2 GPU × 4 grad_accum = 256 per optimizer-step samples |
+| VLM / Action expert | PaliGemma `gemma_2b` / `gemma_300m`, `bfloat16` |
+| Optimizer | AdamW (lr 1e-4, betas (0.9, 0.95), wd 1e-10), cosine decay w/ warmup 1000 |
+| Chunk / Action steps | 50 / 50 |
+| Memory | `gradient_checkpointing=true`, `compile_model=false` |
+| Normalization | ACTION/STATE = `MEAN_STD`, VISUAL = `IDENTITY` |
+| Image augmentation | brightness, contrast, saturation, hue, sharpness, affine (max 3, random order) |
+| Hardware | 2× NVIDIA RTX PRO 6000 Blackwell |
+`action`/`observation.state` dim 은 7 이며, π0.5 의 `max_action_dim=32`, `max_state_dim=32` 으로 자동 zero-pad 됩니다.
+---
+## How to Get Started
+### Inference (load + step)
+```python
+import torch
+from lerobot.policies.pi05.modeling_pi05 import PI05Policy
+policy = PI05Policy.from_pretrained("CoRL2026-CSI/pi05-UR7e-PickandPlace-30epoch")
+policy.to("cuda").eval()
+# observation 의 카메라 키는 학습 시 사용한 이름(`observation.images.base_0_rgb`,
+# `observation.images.left_wrist_0_rgb`) 과 동일해야 합니다.
+with torch.inference_mode():
+    action = policy.select_action(observation)
+```
+### Continue fine-tuning
+```bash
+lerobot-train \
+  --policy.path=CoRL2026-CSI/pi05-UR7e-PickandPlace-30epoch \
+  --dataset.repo_id=CoRL2026-CSI/UR7e_CaP_PickandPlace_100epi_10fps \
+  --output_dir=outputs/train/pi05_ur7e_pickandplace_ft \
+  --job_name=pi05_ur7e_pickandplace_ft \
+  --batch_size=32 --gradient_accumulation_steps=4 --steps=1000 \
+  --policy.device=cuda --policy.dtype=bfloat16 \
+  --policy.gradient_checkpointing=true --wandb.enable=true
+```
+원본 학습 스크립트는 `scripts/cap/pi05_cap_ur7e_pickandplace.sh` 이며,
+정확한 hyperparameter 는 이 리포의 `train_config.json` 으로도 재구성 가능합니다.
+---
+## Model Details
+- **License:** apache-2.0
+- **Base model:** [`lerobot/pi05_base`](https://huggingface.co/lerobot/pi05_base)
+- **Library:** [LeRobot](https://github.com/huggingface/lerobot)
+- **Trained by:** CoRL2026-CSI

config.json ADDED Viewed

	@@ -0,0 +1,108 @@

+{
+    "type": "pi05",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.images.base_0_rgb": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                224,
+                224
+            ]
+        },
+        "observation.images.left_wrist_0_rgb": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                224,
+                224
+            ]
+        },
+        "observation.images.right_wrist_0_rgb": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                224,
+                224
+            ]
+        },
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                32
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                7
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "use_peft": false,
+    "push_to_hub": false,
+    "repo_id": null,
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": "lerobot/pi05_base",
+    "paligemma_variant": "gemma_2b",
+    "action_expert_variant": "gemma_300m",
+    "dtype": "bfloat16",
+    "chunk_size": 50,
+    "n_action_steps": 50,
+    "max_state_dim": 32,
+    "max_action_dim": 32,
+    "num_inference_steps": 10,
+    "time_sampling_beta_alpha": 1.5,
+    "time_sampling_beta_beta": 1.0,
+    "time_sampling_scale": 0.999,
+    "time_sampling_offset": 0.001,
+    "min_period": 0.004,
+    "max_period": 4.0,
+    "use_relative_actions": false,
+    "relative_exclude_joints": [
+        "gripper"
+    ],
+    "action_feature_names": [
+        "shoulder_pan.pos",
+        "shoulder_lift.pos",
+        "elbow.pos",
+        "wrist_1.pos",
+        "wrist_2.pos",
+        "wrist_3.pos",
+        "gripper.pos"
+    ],
+    "rtc_config": null,
+    "image_resolution": [
+        224,
+        224
+    ],
+    "empty_cameras": 0,
+    "tokenizer_max_length": 200,
+    "normalization_mapping": {
+        "ACTION": "MEAN_STD",
+        "STATE": "MEAN_STD",
+        "VISUAL": "IDENTITY"
+    },
+    "gradient_checkpointing": true,
+    "compile_model": false,
+    "compile_mode": "max-autotune",
+    "freeze_vision_encoder": false,
+    "train_expert_only": false,
+    "optimizer_lr": 2.5e-05,
+    "optimizer_betas": [
+        0.9,
+        0.95
+    ],
+    "optimizer_eps": 1e-08,
+    "optimizer_weight_decay": 0.01,
+    "optimizer_grad_clip_norm": 1.0,
+    "scheduler_warmup_steps": 1000,
+    "scheduler_decay_steps": 30000,
+    "scheduler_decay_lr": 2.5e-06
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:59130fbaffbf1ed7ad611dcc85de8d03a2a9827a064b77eb26017342c9797693
+size 9354050752

policy_postprocessor.json ADDED Viewed

	@@ -0,0 +1,32 @@

+{
+  "name": "policy_postprocessor",
+  "steps": [
+    {
+      "registry_name": "unnormalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              7
+            ]
+          }
+        },
+        "norm_map": {
+          "ACTION": "MEAN_STD",
+          "STATE": "MEAN_STD",
+          "VISUAL": "IDENTITY"
+        }
+      },
+      "state_file": "policy_postprocessor_step_0_unnormalizer_processor.safetensors"
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cpu",
+        "float_dtype": null
+      }
+    }
+  ]
+}

policy_postprocessor_step_0_unnormalizer_processor.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c3994c388ba8dbf283e60b9b240d944c58ca6472bc933a52c48708db2be8e2b3
+size 15124

policy_preprocessor.json ADDED Viewed

	@@ -0,0 +1,90 @@

+{
+  "name": "policy_preprocessor",
+  "steps": [
+    {
+      "registry_name": "rename_observations_processor",
+      "config": {
+        "rename_map": {
+          "observation.images.realsense_topview": "observation.images.base_0_rgb",
+          "observation.images.realsense_wrist": "observation.images.left_wrist_0_rgb"
+        }
+      }
+    },
+    {
+      "registry_name": "to_batch_processor",
+      "config": {}
+    },
+    {
+      "registry_name": "normalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "observation.images.base_0_rgb": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              224,
+              224
+            ]
+          },
+          "observation.images.left_wrist_0_rgb": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              224,
+              224
+            ]
+          },
+          "observation.images.right_wrist_0_rgb": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              224,
+              224
+            ]
+          },
+          "observation.state": {
+            "type": "STATE",
+            "shape": [
+              32
+            ]
+          },
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              7
+            ]
+          }
+        },
+        "norm_map": {
+          "ACTION": "MEAN_STD",
+          "STATE": "MEAN_STD",
+          "VISUAL": "IDENTITY"
+        }
+      },
+      "state_file": "policy_preprocessor_step_2_normalizer_processor.safetensors"
+    },
+    {
+      "registry_name": "pi05_prepare_state_tokenizer_processor_step",
+      "config": {}
+    },
+    {
+      "registry_name": "tokenizer_processor",
+      "config": {
+        "max_length": 200,
+        "task_key": "task",
+        "padding_side": "right",
+        "padding": "max_length",
+        "truncation": true,
+        "tokenizer_name": "google/paligemma-3b-pt-224"
+      }
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cuda",
+        "float_dtype": null
+      }
+    }
+  ]
+}

policy_preprocessor_step_2_normalizer_processor.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c3994c388ba8dbf283e60b9b240d944c58ca6472bc933a52c48708db2be8e2b3
+size 15124

train_config.json ADDED Viewed

	@@ -0,0 +1,251 @@

+{
+    "dataset": {
+        "repo_id": "CoRL2026-CSI/UR7e_CaP_PickandPlace_100epi_10fps",
+        "root": null,
+        "episodes": null,
+        "image_transforms": {
+            "enable": true,
+            "max_num_transforms": 3,
+            "random_order": true,
+            "tfs": {
+                "brightness": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "brightness": [
+                            0.8,
+                            1.2
+                        ]
+                    }
+                },
+                "contrast": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "contrast": [
+                            0.8,
+                            1.2
+                        ]
+                    }
+                },
+                "saturation": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "saturation": [
+                            0.5,
+                            1.5
+                        ]
+                    }
+                },
+                "hue": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "hue": [
+                            -0.05,
+                            0.05
+                        ]
+                    }
+                },
+                "sharpness": {
+                    "weight": 1.0,
+                    "type": "SharpnessJitter",
+                    "kwargs": {
+                        "sharpness": [
+                            0.5,
+                            1.5
+                        ]
+                    }
+                },
+                "affine": {
+                    "weight": 1.0,
+                    "type": "RandomAffine",
+                    "kwargs": {
+                        "degrees": [
+                            -5.0,
+                            5.0
+                        ],
+                        "translate": [
+                            0.05,
+                            0.05
+                        ]
+                    }
+                }
+            }
+        },
+        "revision": null,
+        "use_imagenet_stats": true,
+        "video_backend": "torchcodec",
+        "streaming": false
+    },
+    "env": null,
+    "policy": {
+        "type": "pi05",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.images.base_0_rgb": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    224,
+                    224
+                ]
+            },
+            "observation.images.left_wrist_0_rgb": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    224,
+                    224
+                ]
+            },
+            "observation.images.right_wrist_0_rgb": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    224,
+                    224
+                ]
+            },
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    32
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    7
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "use_peft": false,
+        "push_to_hub": false,
+        "repo_id": null,
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": "lerobot/pi05_base",
+        "paligemma_variant": "gemma_2b",
+        "action_expert_variant": "gemma_300m",
+        "dtype": "bfloat16",
+        "chunk_size": 50,
+        "n_action_steps": 50,
+        "max_state_dim": 32,
+        "max_action_dim": 32,
+        "num_inference_steps": 10,
+        "time_sampling_beta_alpha": 1.5,
+        "time_sampling_beta_beta": 1.0,
+        "time_sampling_scale": 0.999,
+        "time_sampling_offset": 0.001,
+        "min_period": 0.004,
+        "max_period": 4.0,
+        "use_relative_actions": false,
+        "relative_exclude_joints": [
+            "gripper"
+        ],
+        "action_feature_names": [
+            "shoulder_pan.pos",
+            "shoulder_lift.pos",
+            "elbow.pos",
+            "wrist_1.pos",
+            "wrist_2.pos",
+            "wrist_3.pos",
+            "gripper.pos"
+        ],
+        "rtc_config": null,
+        "image_resolution": [
+            224,
+            224
+        ],
+        "empty_cameras": 0,
+        "tokenizer_max_length": 200,
+        "normalization_mapping": {
+            "ACTION": "MEAN_STD",
+            "STATE": "MEAN_STD",
+            "VISUAL": "IDENTITY"
+        },
+        "gradient_checkpointing": true,
+        "compile_model": false,
+        "compile_mode": "max-autotune",
+        "freeze_vision_encoder": false,
+        "train_expert_only": false,
+        "optimizer_lr": 2.5e-05,
+        "optimizer_betas": [
+            0.9,
+            0.95
+        ],
+        "optimizer_eps": 1e-08,
+        "optimizer_weight_decay": 0.01,
+        "optimizer_grad_clip_norm": 1.0,
+        "scheduler_warmup_steps": 1000,
+        "scheduler_decay_steps": 30000,
+        "scheduler_decay_lr": 2.5e-06
+    },
+    "output_dir": "/workspace/train_with_lerobot/outputs/train/cap_pi05_ur7e_pickandplace",
+    "job_name": "cap_pi05_ur7e_pickandplace",
+    "resume": false,
+    "seed": 1000,
+    "cudnn_deterministic": false,
+    "num_workers": 16,
+    "persistent_workers": false,
+    "batch_size": 32,
+    "gradient_accumulation_steps": 4,
+    "steps": 4300,
+    "eval_freq": 0,
+    "log_freq": 100,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 4300,
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 2.5e-05,
+        "weight_decay": 0.01,
+        "grad_clip_norm": 1.0,
+        "betas": [
+            0.9,
+            0.95
+        ],
+        "eps": 1e-08
+    },
+    "scheduler": {
+        "type": "cosine_decay_with_warmup",
+        "num_warmup_steps": 1000,
+        "num_decay_steps": 30000,
+        "peak_lr": 2.5e-05,
+        "decay_lr": 2.5e-06
+    },
+    "eval": {
+        "n_episodes": 50,
+        "batch_size": 44,
+        "use_async_envs": true
+    },
+    "wandb": {
+        "enable": true,
+        "disable_artifact": false,
+        "project": "lerobot-pi05-cap",
+        "entity": null,
+        "notes": null,
+        "run_id": "h96me86l",
+        "mode": null,
+        "add_tags": true
+    },
+    "peft": null,
+    "use_rabc": false,
+    "rabc_progress_path": null,
+    "rabc_kappa": 0.01,
+    "rabc_epsilon": 1e-06,
+    "rabc_head_mode": "sparse",
+    "rename_map": {
+        "observation.images.realsense_topview": "observation.images.base_0_rgb",
+        "observation.images.realsense_wrist": "observation.images.left_wrist_0_rgb"
+    },
+    "checkpoint_path": null
+}