Upload folder using huggingface_hub

README.md

@@ -0,0 +1,13 @@
+---
+library_name: lerobot
+tags:
+- diffusion-policy
+- model_hub_mixin
+- pytorch_model_hub_mixin
+- robotics
+---
+
+This model has been pushed to the Hub using the [PytorchModelHubMixin](https://huggingface.co/docs/huggingface_hub/package_reference/mixins#huggingface_hub.PyTorchModelHubMixin) integration:
+- Code: https://github.com/huggingface/lerobot
+- Paper: [More Information Needed]
+- Docs: [More Information Needed]

config.json

@@ -0,0 +1,85 @@
+{
+  "beta_end": 0.02,
+  "beta_schedule": "squaredcos_cap_v2",
+  "beta_start": 0.0001,
+  "clip_sample": true,
+  "clip_sample_range": 1.0,
+  "crop_is_random": true,
+  "crop_shape": [
+    84,
+    84
+  ],
+  "device": "cuda",
+  "diffusion_step_embed_dim": 128,
+  "do_mask_loss_for_padding": false,
+  "down_dims": [
+    512,
+    1024,
+    2048
+  ],
+  "drop_n_last_frames": 7,
+  "horizon": 16,
+  "input_features": {
+    "observation.images.webcam": {
+      "shape": [
+        3,
+        480,
+        640
+      ],
+      "type": "VISUAL"
+    },
+    "observation.images.wrist": {
+      "shape": [
+        3,
+        480,
+        640
+      ],
+      "type": "VISUAL"
+    },
+    "observation.state": {
+      "shape": [
+        6
+      ],
+      "type": "STATE"
+    }
+  },
+  "kernel_size": 5,
+  "n_action_steps": 8,
+  "n_groups": 8,
+  "n_obs_steps": 2,
+  "noise_scheduler_type": "DDPM",
+  "normalization_mapping": {
+    "ACTION": "MIN_MAX",
+    "STATE": "MIN_MAX",
+    "VISUAL": "MEAN_STD"
+  },
+  "num_inference_steps": null,
+  "num_train_timesteps": 100,
+  "optimizer_betas": [
+    0.95,
+    0.999
+  ],
+  "optimizer_eps": 1e-08,
+  "optimizer_lr": 0.0001,
+  "optimizer_weight_decay": 1e-06,
+  "output_features": {
+    "action": {
+      "shape": [
+        6
+      ],
+      "type": "ACTION"
+    }
+  },
+  "prediction_type": "epsilon",
+  "pretrained_backbone_weights": null,
+  "scheduler_name": "cosine",
+  "scheduler_warmup_steps": 500,
+  "spatial_softmax_num_keypoints": 32,
+  "training_noise_sampling": "uniform",
+  "use_amp": false,
+  "use_film_scale_modulation": true,
+  "use_flow_matching": true,
+  "use_group_norm": true,
+  "use_separate_rgb_encoder_per_camera": false,
+  "vision_backbone": "resnet18"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fce238d4802bdc640ab0c1dbbb834cbb6449ec7549f5655c8ea411f93d52f03
+size 1066517736

train_config.json

@@ -0,0 +1,197 @@
+{
+    "dataset": {
+        "repo_id": "jclinton1/wedgit_stack_single_dual_cam_v3",
+        "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
+                        ]
+                    }
+                }
+            }
+        },
+        "revision": null,
+        "use_imagenet_stats": true,
+        "video_backend": "torchcodec"
+    },
+    "env": null,
+    "policy": {
+        "type": "diffusion",
+        "n_obs_steps": 2,
+        "normalization_mapping": {
+            "VISUAL": "MEAN_STD",
+            "STATE": "MIN_MAX",
+            "ACTION": "MIN_MAX"
+        },
+        "input_features": {
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    6
+                ]
+            },
+            "observation.images.wrist": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            },
+            "observation.images.webcam": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    6
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "horizon": 16,
+        "n_action_steps": 8,
+        "drop_n_last_frames": 7,
+        "vision_backbone": "resnet18",
+        "crop_shape": [
+            84,
+            84
+        ],
+        "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,
+        "training_noise_sampling": "uniform",
+        "use_flow_matching": true,
+        "num_inference_steps": null,
+        "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/wedgit_stack_single_diffusion2",
+    "job_name": "diffusion2",
+    "resume": false,
+    "seed": 1000,
+    "num_workers": 4,
+    "batch_size": 8,
+    "steps": 200000,
+    "eval_freq": 20000,
+    "validation_freq": 400,
+    "log_freq": 200,
+    "save_checkpoint": true,
+    "save_freq": 20000,
+    "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": "wedgit_stack_single",
+        "entity": null,
+        "notes": null,
+        "run_id": null,
+        "mode": null
+    }
+}