Upload policy weights, train config and readme

README.md

@@ -5,9 +5,9 @@ license: apache-2.0
 model_name: act
 pipeline_tag: robotics
 tags:
+- act
 - robotics
 - lerobot
-- act
 ---
 
 # Model Card for act

config.json

@@ -1,63 +1,63 @@
-{
-    "type": "act",
-    "n_obs_steps": 1,
-    "input_features": {
-        "observation.state": {
-            "type": "STATE",
-            "shape": [
-                6
-            ]
-        },
-        "observation.images.front": {
-            "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": "maximellerbach/act_pickandplace",
-    "private": null,
-    "tags": null,
-    "license": null,
-    "pretrained_path": "outputs\\train\\act_pickandplace\\checkpoints\\last\\pretrained_model",
-    "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": 0,
-    "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
+{
+    "type": "act",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                6
+            ]
+        },
+        "observation.images.front": {
+            "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": "maximellerbach/act_pickandplace",
+    "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": 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
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a80af2d0cd0fbe32f4d1b73de09f3fe96782b8b06d8e212c8802d160195dc790
+oid sha256:3e3084ff4e532572d12530155fdabcb62b3a0196e12f58e3070b69884e33d291
 size 206699736

train_config.json

@@ -1,193 +1,194 @@
-{
-    "dataset": {
-        "repo_id": "maximellerbach/pickandplace",
-        "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": "pyav",
-        "streaming": false
-    },
-    "env": null,
-    "policy": {
-        "type": "act",
-        "n_obs_steps": 1,
-        "input_features": {
-            "observation.state": {
-                "type": "STATE",
-                "shape": [
-                    6
-                ]
-            },
-            "observation.images.front": {
-                "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": "maximellerbach/act_pickandplace",
-        "private": null,
-        "tags": null,
-        "license": null,
-        "pretrained_path": "outputs\\train\\act_pickandplace\\checkpoints\\last\\pretrained_model",
-        "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": 0,
-        "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
-    },
-    "output_dir": "outputs\\train\\act_pickandplace",
-    "job_name": "act",
-    "resume": true,
-    "seed": 1000,
-    "num_workers": 4,
-    "batch_size": 8,
-    "steps": 8000,
-    "eval_freq": 20000,
-    "log_freq": 200,
-    "tolerance_s": 0.0001,
-    "save_checkpoint": true,
-    "save_freq": 2000,
-    "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
-    },
-    "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": "outputs\\train\\act_pickandplace\\checkpoints\\last"
+{
+    "dataset": {
+        "repo_id": "maximellerbach/pickandplace",
+        "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.front": {
+                "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": "maximellerbach/act_pickandplace",
+        "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": 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
+    },
+    "output_dir": "outputs/train/act_pickandplace",
+    "job_name": "act",
+    "resume": false,
+    "seed": 1000,
+    "cudnn_deterministic": false,
+    "num_workers": 4,
+    "batch_size": 8,
+    "steps": 10000,
+    "eval_freq": 20000,
+    "log_freq": 200,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 2000,
+    "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
+    },
+    "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
 }