Upload checkpoint from step 008209

config.json

@@ -0,0 +1,90 @@
+{
+    "type": "diffusion",
+    "n_obs_steps": 4,
+    "input_features": {
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                6
+            ]
+        },
+        "observation.images.gripper": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                6
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": true,
+    "use_peft": false,
+    "push_to_hub": true,
+    "repo_id": "open-cloth/diffusion-cloth-v2",
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": null,
+    "horizon": 64,
+    "n_action_steps": 32,
+    "normalization_mapping": {
+        "VISUAL": "MEAN_STD",
+        "STATE": "MIN_MAX",
+        "ACTION": "MIN_MAX"
+    },
+    "drop_n_last_frames": 7,
+    "vision_backbone": "resnet18",
+    "resize_shape": [
+        320,
+        480
+    ],
+    "crop_ratio": 0.9,
+    "crop_shape": [
+        288,
+        432
+    ],
+    "crop_is_random": true,
+    "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
+    "use_group_norm": false,
+    "spatial_softmax_num_keypoints": 64,
+    "use_separate_rgb_encoder_per_camera": false,
+    "down_dims": [
+        256,
+        512,
+        1024
+    ],
+    "kernel_size": 5,
+    "n_groups": 8,
+    "diffusion_step_embed_dim": 128,
+    "use_film_scale_modulation": true,
+    "noise_scheduler_type": "DDIM",
+    "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
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a59df10639a3ba727aacc21ecd4dfd9cca9c2d66566e26e00f57085a6aec46e3
+size 327664088

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 sha256:53843a8a03b085e5a2ffa8f82afd6cfce7238d538bbc2f7450fa945a5e17780e
+size 6584

policy_preprocessor.json

@@ -0,0 +1,56 @@
+{
+  "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.gripper": {
+            "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 sha256:53843a8a03b085e5a2ffa8f82afd6cfce7238d538bbc2f7450fa945a5e17780e
+size 6584

train_config.json

@@ -0,0 +1,238 @@
+{
+    "dataset": {
+        "repo_id": "open-cloth/so101-full-fold-merged-g8",
+        "root": null,
+        "episodes": null,
+        "image_transforms": {
+            "enable": true,
+            "max_num_transforms": 4,
+            "random_order": true,
+            "tfs": {
+                "brightness": {
+                    "weight": 3.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "brightness": [
+                            0.75,
+                            1.25
+                        ]
+                    }
+                },
+                "contrast": {
+                    "weight": 3.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "contrast": [
+                            0.6,
+                            1.4
+                        ]
+                    }
+                },
+                "saturation": {
+                    "weight": 3.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "saturation": [
+                            0.8,
+                            1.2
+                        ]
+                    }
+                },
+                "hue": {
+                    "weight": 2.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "hue": [
+                            -0.15,
+                            0.15
+                        ]
+                    }
+                },
+                "sharpness": {
+                    "weight": 2.0,
+                    "type": "SharpnessJitter",
+                    "kwargs": {
+                        "sharpness": [
+                            0.6,
+                            1.4
+                        ]
+                    }
+                },
+                "rotation": {
+                    "weight": 2.0,
+                    "type": "RandomAffine",
+                    "kwargs": {
+                        "degrees": [
+                            -5.0,
+                            5.0
+                        ]
+                    }
+                },
+                "translation": {
+                    "weight": 2.0,
+                    "type": "RandomAffine",
+                    "kwargs": {
+                        "degrees": [
+                            0.0,
+                            0.0
+                        ],
+                        "translate": [
+                            0.1,
+                            0.1
+                        ]
+                    }
+                }
+            }
+        },
+        "revision": null,
+        "use_imagenet_stats": true,
+        "video_backend": "torchcodec",
+        "streaming": false
+    },
+    "env": null,
+    "policy": {
+        "type": "diffusion",
+        "n_obs_steps": 4,
+        "input_features": {
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    6
+                ]
+            },
+            "observation.images.gripper": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    6
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": true,
+        "use_peft": false,
+        "push_to_hub": true,
+        "repo_id": "open-cloth/diffusion-cloth-v2",
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": null,
+        "horizon": 64,
+        "n_action_steps": 32,
+        "normalization_mapping": {
+            "VISUAL": "MEAN_STD",
+            "STATE": "MIN_MAX",
+            "ACTION": "MIN_MAX"
+        },
+        "drop_n_last_frames": 7,
+        "vision_backbone": "resnet18",
+        "resize_shape": [
+            320,
+            480
+        ],
+        "crop_ratio": 0.9,
+        "crop_shape": [
+            288,
+            432
+        ],
+        "crop_is_random": true,
+        "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
+        "use_group_norm": false,
+        "spatial_softmax_num_keypoints": 64,
+        "use_separate_rgb_encoder_per_camera": false,
+        "down_dims": [
+            256,
+            512,
+            1024
+        ],
+        "kernel_size": 5,
+        "n_groups": 8,
+        "diffusion_step_embed_dim": 128,
+        "use_film_scale_modulation": true,
+        "noise_scheduler_type": "DDIM",
+        "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": "outputs/train/diffusion",
+    "job_name": "diffusion-v2",
+    "resume": false,
+    "seed": 1000,
+    "cudnn_deterministic": false,
+    "num_workers": 8,
+    "batch_size": 64,
+    "steps": 98505,
+    "eval_freq": 20000,
+    "log_freq": 3,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 8209,
+    "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": true,
+        "disable_artifact": false,
+        "project": "open-cloth",
+        "entity": null,
+        "notes": null,
+        "run_id": "kcic4bgo",
+        "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.gripper": "observation.images.camera1"
+    },
+    "checkpoint_path": null
+}