Upload folder using huggingface_hub

README.md

@@ -0,0 +1,58 @@
+---
+license: apache-2.0
+library_name: lerobot
+pipeline_tag: robotics
+tags:
+- act-policy
+- pytorch_model_hub_mixin
+- robotics
+- IB-Robot
+- LeRobot
+- so-101
+- banana-pick
+- knowledge-distillation
+---
+
+# Model Card for ACT/BananaPick (Distilled)
+
+Action Chunking Transformer Policy (as per [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://arxiv.org/abs/2304.13705)) trained for banana pick-and-place on a 1-arm SO-101 robot. This checkpoint is a **distilled** model obtained via knowledge distillation.
+
+## How to Get Started with the Model
+
+See the [IB-Robot project](https://gitcode.com/openeuler/IB_Robot) (particularly the [inference_service](https://gitcode.com/openeuler/IB_Robot/tree/main/src/inference_service)) for instructions on how to load and deploy this model with ROS 2.
+
+To load the model directly in Python:
+
+```python
+from lerobot.common.policies.act.modeling_act import ACTPolicy
+
+policy = ACTPolicy.from_pretrained("RightAiknow/act_1arm_2cam_banana_pick_v1_distill")
+```
+
+## Training Details
+
+This model was trained via **knowledge distillation** (`kd: true`) within the IB-Robot framework.
+
+- **Policy:** ACT (Action Chunking with Transformers)
+- **Training method:** Knowledge distillation
+- **Robot:** 1-arm SO-101
+- **Cameras:** top, wrist (480x640)
+- **Action dim:** 6
+- **Training steps:** 500,000 (configured)
+- **Checkpoint:** step_160000
+- **Chunk size:** 100
+- **Batch size:** 32
+- **Vision backbone:** ResNet18
+- **Optimizer:** AdamW (lr=1e-5, weight_decay=1e-4)
+- **Latent dim (VAE):** 32
+- **Dim model:** 1024
+
+## Citation
+
+```bibtex
+@software{ib_robot,
+  title = {IB-Robot: Intelligence Boom Robot},
+  url = {https://gitcode.com/openeuler/IB_Robot},
+  license = {Apache-2.0}
+}
+```

config.json

@@ -0,0 +1,74 @@
+{
+    "type": "act",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                6
+            ]
+        },
+        "observation.images.top": {
+            "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": true,
+    "repo_id": "my_awesome_follower_arm",
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": null,
+    "chunk_size": 100,
+    "n_action_steps": 100,
+    "normalization_mapping": {
+        "VISUAL": "MEAN_STD",
+        "STATE": "MEAN_STD",
+        "ACTION": "MEAN_STD"
+    },
+    "vision_backbone": "resnet18",
+    "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
+    "replace_final_stride_with_dilation": false,
+    "pre_norm": false,
+    "dim_model": 1024,
+    "n_heads": 8,
+    "dim_feedforward": 1200,
+    "feedforward_activation": "relu",
+    "n_encoder_layers": 4,
+    "n_decoder_layers": 2,
+    "use_vae": true,
+    "latent_dim": 32,
+    "n_vae_encoder_layers": 4,
+    "kd": true,
+    "teacher_train_config": "/home/wzl/sx/upload/used_models/1arm_2cam_banana_pick_v1_20260514/ACT_1arm_2cam_banana_pick_v1_step_196000_20260515/pretrained_model/train_config.json",
+    "decoder_out_dim": 2048,
+    "temporal_ensemble_coeff": null,
+    "dropout": 0.1,
+    "kl_weight": 10.0,
+    "optimizer_lr": 1e-05,
+    "optimizer_weight_decay": 0.0001,
+    "optimizer_lr_backbone": 1e-05
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ac2afec5e3f8e6ab8bc4582f02c29c9106e0d9fe2d7f6b21a060bb1e447b8f6
+size 356747176

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": "MEAN_STD",
+          "ACTION": "MEAN_STD"
+        }
+      },
+      "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:dec51b26fb6c8f3153cfce30be83e1b25eaee2b51cdac243f00a2b893b82ea19
+size 7536

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.top": {
+            "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": "MEAN_STD",
+          "ACTION": "MEAN_STD"
+        }
+      },
+      "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:dec51b26fb6c8f3153cfce30be83e1b25eaee2b51cdac243f00a2b893b82ea19
+size 7536

train_config.json

@@ -0,0 +1,209 @@
+{
+    "dataset": {
+        "repo_id": "/home/wzl/sx/upload/dataset/1arm_2cam_banana_pick_v1_20260514",
+        "root": null,
+        "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": "torchcodec",
+        "streaming": false
+    },
+    "env": null,
+    "policy": {
+        "type": "act",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    6
+                ]
+            },
+            "observation.images.top": {
+                "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": true,
+        "repo_id": "my_awesome_follower_arm",
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": null,
+        "chunk_size": 100,
+        "n_action_steps": 100,
+        "normalization_mapping": {
+            "VISUAL": "MEAN_STD",
+            "STATE": "MEAN_STD",
+            "ACTION": "MEAN_STD"
+        },
+        "vision_backbone": "resnet18",
+        "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
+        "replace_final_stride_with_dilation": false,
+        "pre_norm": false,
+        "dim_model": 1024,
+        "n_heads": 8,
+        "dim_feedforward": 1200,
+        "feedforward_activation": "relu",
+        "n_encoder_layers": 4,
+        "n_decoder_layers": 2,
+        "use_vae": true,
+        "latent_dim": 32,
+        "n_vae_encoder_layers": 4,
+        "kd": true,
+        "teacher_train_config": "/home/wzl/sx/upload/used_models/1arm_2cam_banana_pick_v1_20260514/ACT_1arm_2cam_banana_pick_v1_step_196000_20260515/pretrained_model/train_config.json",
+        "decoder_out_dim": 2048,
+        "temporal_ensemble_coeff": null,
+        "dropout": 0.1,
+        "kl_weight": 10.0,
+        "optimizer_lr": 1e-05,
+        "optimizer_weight_decay": 0.0001,
+        "optimizer_lr_backbone": 1e-05
+    },
+    "output_dir": "/home/wzl/sx/upload/train_models/1arm_2cam_banana_pick_v1_20260514_训练20260515_distill",
+    "job_name": "act_train_banana_distill",
+    "resume": false,
+    "seed": 1000,
+    "ada_weight": true,
+    "ada_weight_freq": 200,
+    "damping_coefficient": 0.7,
+    "cudnn_deterministic": false,
+    "num_workers": 10,
+    "batch_size": 32,
+    "steps": 500000,
+    "eval_freq": 2000,
+    "log_freq": 200,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 20000,
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adamw",
+        "lr": 1e-05,
+        "weight_decay": 0.0001,
+        "grad_clip_norm": 10.0,
+        "betas": [
+            0.9,
+            0.999
+        ],
+        "eps": 1e-08
+    },
+    "scheduler": null,
+    "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,
+        "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": {},
+    "checkpoint_path": null
+}