Upload folder using huggingface_hub

README.md

@@ -0,0 +1,42 @@
+---
+library_name: lerobot
+pipeline_tag: robotics
+tags: [act, lerobot, robotics, dg5f, ur5e, gelsight, ablation]
+---
+
+# ACT — blue 186ep, GelSight no gelsight
+
+One point of a GelSight-resolution sweep on the DG-5F + UR5e blue-cable task.
+Runs differ only in GelSight resolution, so any gap between them is attributable
+to tactile resolution alone.
+
+- **Dataset**: [Kaz55/dg5f_ur5e_blue_180ep_gs0](https://huggingface.co/datasets/Kaz55/dg5f_ur5e_blue_180ep_gs0) — 186 episodes / 186,152 frames
+- **GelSight**: no gelsight
+- **RealSense**: 640x480 (identical across the sweep)
+- **Policy**: ACT, chunk_size=60, n_action_steps=60
+- **Training**: 100,000 steps (~4.3 epochs), batch 8, seed 1000
+
+## Inputs
+
+`observation.state` (26) + RealSense x2
+
+`observation.velocity` and `observation.effort` are present in the dataset but
+**deliberately excluded**. Feature auto-derivation would otherwise feed them to
+the policy, adding a second difference between runs and breaking the ablation.
+
+## Sweep (186 episodes)
+
+| GelSight | model |
+|---|---|
+| 500x375 | act-blue-180ep-gs500-ac60 |
+| 320x240 | act-blue-180ep-gs320-ac60 |
+| 160x120 | act-blue-180ep-gs160-ac60 |
+| 88x66 | act-blue-180ep-gs88-ac60 |
+| none | act-blue-180ep-gs0-ac60 |
+
+## Caveat
+
+On the related 180-episode `combined` sweep, final training loss was 0.118 across
+*every* resolution **including no-GelSight-at-all** — training loss did not detect
+the tactile input. Treat these numbers as a sanity check, not as evidence that
+tactile resolution matters; that requires on-robot evaluation.

config.json

@@ -0,0 +1,88 @@
+{
+    "type": "act",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.images.realsense1": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        },
+        "observation.images.realsense2": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        },
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                26
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                26
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "use_peft": false,
+    "push_to_hub": false,
+    "repo_id": null,
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": null,
+    "chunk_size": 60,
+    "n_action_steps": 60,
+    "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": 512,
+    "n_heads": 8,
+    "dim_feedforward": 3200,
+    "feedforward_activation": "relu",
+    "n_encoder_layers": 4,
+    "n_decoder_layers": 1,
+    "use_vae": true,
+    "latent_dim": 32,
+    "n_vae_encoder_layers": 4,
+    "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,
+    "use_finger_tactile_encoder": false,
+    "thumb_tactile_key": "observation.images.gelsight2",
+    "index_tactile_key": "observation.images.gelsight1",
+    "thumb_state_indices": [
+        6,
+        7,
+        8,
+        9
+    ],
+    "index_state_indices": [
+        10,
+        11,
+        12,
+        13
+    ],
+    "tactile_keep_spatial_tokens": false,
+    "drop_finger_dims_from_state_token": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fb725497e9c92e0e07464e9f68a436b4c21fadcda5aa717acdcce3746854b36
+size 206699816

policy_postprocessor.json

@@ -0,0 +1,32 @@
+{
+  "name": "policy_postprocessor",
+  "steps": [
+    {
+      "registry_name": "unnormalizer_processor",
+      "config": {
+        "eps": 1e-08,
+        "features": {
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              26
+            ]
+          }
+        },
+        "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:ff702f40310398f5ca94ae5322af85e86104d10035b206af82bb0fb55274b5f0
+size 12776

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.images.realsense1": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              480,
+              640
+            ]
+          },
+          "observation.images.realsense2": {
+            "type": "VISUAL",
+            "shape": [
+              3,
+              480,
+              640
+            ]
+          },
+          "observation.state": {
+            "type": "STATE",
+            "shape": [
+              26
+            ]
+          },
+          "action": {
+            "type": "ACTION",
+            "shape": [
+              26
+            ]
+          }
+        },
+        "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:d9f040a625a254a7a44e2cd7321cee1e4d7d0c4f556bc3374197096856b4e24c
+size 12784

train_config.json

@@ -0,0 +1,221 @@
+{
+    "dataset": {
+        "repo_id": "Kaz55/dg5f_ur5e_blue_180ep_gs0",
+        "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",
+        "return_uint8": false,
+        "streaming": false
+    },
+    "env": null,
+    "policy": {
+        "type": "act",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.images.realsense1": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            },
+            "observation.images.realsense2": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            },
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    26
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    26
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "use_peft": false,
+        "push_to_hub": false,
+        "repo_id": null,
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": null,
+        "chunk_size": 60,
+        "n_action_steps": 60,
+        "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": 512,
+        "n_heads": 8,
+        "dim_feedforward": 3200,
+        "feedforward_activation": "relu",
+        "n_encoder_layers": 4,
+        "n_decoder_layers": 1,
+        "use_vae": true,
+        "latent_dim": 32,
+        "n_vae_encoder_layers": 4,
+        "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,
+        "use_finger_tactile_encoder": false,
+        "thumb_tactile_key": "observation.images.gelsight2",
+        "index_tactile_key": "observation.images.gelsight1",
+        "thumb_state_indices": [
+            6,
+            7,
+            8,
+            9
+        ],
+        "index_state_indices": [
+            10,
+            11,
+            12,
+            13
+        ],
+        "tactile_keep_spatial_tokens": false,
+        "drop_finger_dims_from_state_token": false
+    },
+    "reward_model": null,
+    "output_dir": "outputs/train/act_blue_180ep_gs0_ac60",
+    "job_name": "act_blue_180ep_gs0_ac60",
+    "resume": false,
+    "seed": 1000,
+    "cudnn_deterministic": false,
+    "num_workers": 4,
+    "batch_size": 8,
+    "prefetch_factor": 4,
+    "persistent_workers": true,
+    "steps": 100000,
+    "eval_freq": 20000,
+    "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": 22,
+        "use_async_envs": true
+    },
+    "wandb": {
+        "enable": false,
+        "disable_artifact": false,
+        "project": "lerobot",
+        "entity": null,
+        "notes": null,
+        "run_id": null,
+        "mode": null,
+        "add_tags": true
+    },
+    "peft": null,
+    "sample_weighting": null,
+    "phase_sampling": null,
+    "rename_map": {},
+    "checkpoint_path": null
+}