feat: model card + processors + config + demo video

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+demo.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,75 @@
+---
+license: apache-2.0
+library_name: lerobot
+pipeline_tag: robotics
+tags:
+  - flow-matching
+  - diffusion-policy
+  - rectified-flow
+  - lerobot
+  - so101
+  - leisaac
+  - pick-orange
+  - isaac-sim
+base_model: []
+datasets:
+  - LightwheelAI/leisaac-pick-orange
+language:
+  - en
+---
+
+# FlowHeads-DiffusionPolicy-PickOrange (DP-FlowHead)
+
+**DP-FlowHead** — a [LeRobot](https://github.com/huggingface/lerobot) Diffusion-Policy
+conv-UNet (ResNet-18 + SpatialSoftmax + FiLM 1D-conv UNet, ~267M) whose **DDPM
+denoising head is replaced by a rectified-flow head**: predict the straight-line
+velocity `v = x1 − x0` and sample by **Euler ODE** integration (NFE=10). Trained
+**from scratch** on [LeIsaac SO-101 PickOrange](https://github.com/LightwheelAI/leisaac)
+(single arm, 2 RGB cams, 60 demos). This ckpt = **step-9800 ≈ 4.3 epoch (best)**.
+
+针对 [LeIsaac SO-101 PickOrange](https://github.com/LightwheelAI/leisaac) **从头训练**的
+LeRobot 策略:在 Diffusion-Policy 的 conv-UNet 骨干上,把 **DDPM 去噪头换成 rectified-flow 头**
+(速度场 `v=x1−x0` + Euler 10 步积分)。本 ckpt = **step-9800 ≈ 4.3 epoch(best)**。
+
+<video controls width="640" src="https://huggingface.co/wsagi/FlowHeads-DiffusionPolicy-PickOrange/resolve/main/demo.mp4"></video>
+
+> _Closed-loop demo in Isaac Sim — SO-101 picking oranges into the plate._
+
+## 🔗 Project repos / 项目仓库
+
+- [**vitorcen/FlowHeads**](https://github.com/vitorcen/FlowHeads) — the flow-matching action-head umbrella (this model's code: `flowdp/`)
+- [**vitorcen/LeIsaac-Training**](https://github.com/vitorcen/LeIsaac-Training) — the LeIsaac PickOrange benchmark + eval harness
+- [**vitorcen/isaaclab-experience**](https://github.com/vitorcen/isaaclab-experience) — Isaac Lab multi-policy umbrella (parent project)
+
+## Results — strict 20-round (PickOrange, closed-loop Isaac)
+
+**Headed, 20 rounds (60 episodes), `EPISODE_LENGTH_S=120`, `MAX_ROUND_WALL_S=180`, h=8.**
+
+| metric | value |
+|---|---|
+| E(🍊)/ep | **1.35 / 3 = 45.0 %** (27/60) |
+| P(3) — full round (all 3) | 20 % (4/20) |
+| P(≥2) | 40 % |
+| avg episode | 171 s |
+| 20-ep raw | `[3,1,2,3,1,2,1,0,3,1,0,2,2,1,1,1,3,0,0,0]` |
+
+**45.0 % ties the strongest baseline ACT (43.3 %)** on this 60-demo task (a single
+20-round run carries ±~9 %, so this is a tie, not a win). Notably, an earlier
+5-round *quick* eval with a tight 90 s wall-cap had **mis-scored this policy near zero**:
+DP-FlowHead is slow (successful episodes take ~136 s) and the 90 s cap truncated its
+completions. The strict 180 s eval is what reveals the real 45 %. See the
+[FlowHeads architecture × objective study](https://github.com/vitorcen/FlowHeads) for the
+full {conv-UNet, DiT} × {DDPM, flow} matrix.
+
+## Usage
+
+```python
+from lerobot.policies.factory import get_policy_class
+# requires the FlowHeads package on PYTHONPATH so "flowdp" is registered:
+#   pip install -e .  # from https://github.com/vitorcen/FlowHeads
+policy = get_policy_class("flowdp").from_pretrained("wsagi/FlowHeads-DiffusionPolicy-PickOrange")
+```
+
+Config: `type=flowdp`, `n_action_steps=8`, `num_inference_steps=10` (Euler NFE).
+Closed-loop scoring uses the LeIsaac benchmark harness
+(`scripts/benchmark/run_one.sh`, eval-side lerobot 0.4.x).

config.json

@@ -0,0 +1,95 @@
+{
+    "type": "flowdp",
+    "n_obs_steps": 2,
+    "input_features": {
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                6
+            ]
+        },
+        "observation.images.front": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        },
+        "observation.images.wrist": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                6
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "use_peft": false,
+    "push_to_hub": false,
+    "repo_id": null,
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": null,
+    "horizon": 16,
+    "n_action_steps": 8,
+    "normalization_mapping": {
+        "VISUAL": "MEAN_STD",
+        "STATE": "MIN_MAX",
+        "ACTION": "MIN_MAX"
+    },
+    "drop_n_last_frames": 7,
+    "vision_backbone": "resnet18",
+    "resize_shape": [
+        480,
+        640
+    ],
+    "crop_ratio": 1.0,
+    "crop_shape": null,
+    "crop_is_random": true,
+    "pretrained_backbone_weights": null,
+    "use_group_norm": true,
+    "spatial_softmax_num_keypoints": 32,
+    "use_separate_rgb_encoder_per_camera": false,
+    "down_dims": [
+        512,
+        1024,
+        2048
+    ],
+    "kernel_size": 5,
+    "n_groups": 8,
+    "diffusion_step_embed_dim": 128,
+    "use_film_scale_modulation": true,
+    "noise_scheduler_type": "DDPM",
+    "num_train_timesteps": 100,
+    "beta_schedule": "squaredcos_cap_v2",
+    "beta_start": 0.0001,
+    "beta_end": 0.02,
+    "prediction_type": "epsilon",
+    "clip_sample": true,
+    "clip_sample_range": 1.0,
+    "num_inference_steps": 10,
+    "compile_model": false,
+    "compile_mode": "reduce-overhead",
+    "do_mask_loss_for_padding": false,
+    "optimizer_lr": 0.0001,
+    "optimizer_betas": [
+        0.95,
+        0.999
+    ],
+    "optimizer_eps": 1e-08,
+    "optimizer_weight_decay": 1e-06,
+    "scheduler_name": "cosine",
+    "scheduler_warmup_steps": 500
+}

demo.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6b1eb61623923f08dad4f976844ac04e7777fba5454bd50d8a693eeaebb2f82
+size 23091369

policy_postprocessor.json

@@ -0,0 +1,32 @@
+{
+  "name": "policy_postprocessor",
+  "steps": [
+    {
+      "registry_name": "unnormalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              6
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "MEAN_STD",
+          "STATE": "MIN_MAX",
+          "ACTION": "MIN_MAX"
+        }
+      },
+      "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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b9214914398156f17ddf08a5082c20b24efb70a7ba7677e8bc3d3ff68a722db
+size 3756

policy_preprocessor.json

@@ -0,0 +1,64 @@
+{
+  "name": "policy_preprocessor",
+  "steps": [
+    {
+      "registry_name": "rename_observations_processor",
+      "config": {
+        "rename_map": {}
+      }
+    },
+    {
+      "registry_name": "to_batch_processor",
+      "config": {}
+    },
+    {
+      "registry_name": "device_processor",
+      "config": {
+        "device": "cuda",
+        "float_dtype": null
+      }
+    },
+    {
+      "registry_name": "normalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "observation.state": {
+            "type": "STATE",
+            "shape": [
+              6
+            ]
+          },
+          "observation.images.front": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              480,
+              640
+            ]
+          },
+          "observation.images.wrist": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              480,
+              640
+            ]
+          },
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              6
+            ]
+          }
+        },
+        "norm_map": {
+          "VISUAL": "MEAN_STD",
+          "STATE": "MIN_MAX",
+          "ACTION": "MIN_MAX"
+        }
+      },
+      "state_file": "policy_preprocessor_step_3_normalizer_processor.safetensors"
+    }
+  ]
+}

policy_preprocessor_step_3_normalizer_processor.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b9214914398156f17ddf08a5082c20b24efb70a7ba7677e8bc3d3ff68a722db
+size 3756

train_config.json

@@ -0,0 +1,229 @@
+{
+    "dataset": {
+        "repo_id": "LightwheelAI/leisaac-pick-orange",
+        "root": "/root/autodl-tmp/datasets/leisaac-pick-orange",
+        "episodes": null,
+        "image_transforms": {
+            "enable": false,
+            "max_num_transforms": 3,
+            "random_order": false,
+            "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": "pyav",
+        "streaming": false
+    },
+    "env": null,
+    "policy": {
+        "type": "flowdp",
+        "n_obs_steps": 2,
+        "input_features": {
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    6
+                ]
+            },
+            "observation.images.front": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            },
+            "observation.images.wrist": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    6
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "use_peft": false,
+        "push_to_hub": false,
+        "repo_id": null,
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": null,
+        "horizon": 16,
+        "n_action_steps": 8,
+        "normalization_mapping": {
+            "VISUAL": "MEAN_STD",
+            "STATE": "MIN_MAX",
+            "ACTION": "MIN_MAX"
+        },
+        "drop_n_last_frames": 7,
+        "vision_backbone": "resnet18",
+        "resize_shape": [
+            480,
+            640
+        ],
+        "crop_ratio": 1.0,
+        "crop_shape": null,
+        "crop_is_random": true,
+        "pretrained_backbone_weights": null,
+        "use_group_norm": true,
+        "spatial_softmax_num_keypoints": 32,
+        "use_separate_rgb_encoder_per_camera": false,
+        "down_dims": [
+            512,
+            1024,
+            2048
+        ],
+        "kernel_size": 5,
+        "n_groups": 8,
+        "diffusion_step_embed_dim": 128,
+        "use_film_scale_modulation": true,
+        "noise_scheduler_type": "DDPM",
+        "num_train_timesteps": 100,
+        "beta_schedule": "squaredcos_cap_v2",
+        "beta_start": 0.0001,
+        "beta_end": 0.02,
+        "prediction_type": "epsilon",
+        "clip_sample": true,
+        "clip_sample_range": 1.0,
+        "num_inference_steps": 10,
+        "compile_model": false,
+        "compile_mode": "reduce-overhead",
+        "do_mask_loss_for_padding": false,
+        "optimizer_lr": 0.0001,
+        "optimizer_betas": [
+            0.95,
+            0.999
+        ],
+        "optimizer_eps": 1e-08,
+        "optimizer_weight_decay": 1e-06,
+        "scheduler_name": "cosine",
+        "scheduler_warmup_steps": 500
+    },
+    "output_dir": "/root/autodl-tmp/outputs/flowdp-hires-pickorange",
+    "job_name": "flowdp",
+    "resume": false,
+    "seed": 1000,
+    "num_workers": 4,
+    "batch_size": 16,
+    "steps": 14000,
+    "eval_freq": 20000,
+    "log_freq": 200,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 1400,
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adam",
+        "lr": 0.0001,
+        "weight_decay": 1e-06,
+        "grad_clip_norm": 10.0,
+        "betas": [
+            0.95,
+            0.999
+        ],
+        "eps": 1e-08
+    },
+    "scheduler": {
+        "type": "diffuser",
+        "num_warmup_steps": 500,
+        "name": "cosine"
+    },
+    "eval": {
+        "n_episodes": 50,
+        "batch_size": 50,
+        "use_async_envs": false
+    },
+    "wandb": {
+        "enable": false,
+        "disable_artifact": false,
+        "project": "lerobot",
+        "entity": null,
+        "notes": null,
+        "run_id": null,
+        "mode": null
+    },
+    "peft": null,
+    "use_rabc": false,
+    "rabc_progress_path": null,
+    "rabc_kappa": 0.01,
+    "rabc_epsilon": 1e-06,
+    "rabc_head_mode": "sparse",
+    "rename_map": {},
+    "checkpoint_path": null
+}