Upload policy weights, train config and readme

Browse files

Files changed (4) hide show

README.md +62 -0
config.json +99 -0
model.safetensors +3 -0
train_config.json +213 -0

README.md ADDED Viewed

	@@ -0,0 +1,62 @@

+---
+datasets: ramen-noodels/prepared_blue_round_button_small_audio
+library_name: lerobot
+license: apache-2.0
+model_name: diffusion
+pipeline_tag: robotics
+tags:
+- robotics
+- lerobot
+- diffusion
+---
+# Model Card for diffusion
+<!-- Provide a quick summary of what the model is/does. -->
+[Diffusion Policy](https://huggingface.co/papers/2303.04137) treats visuomotor control as a generative diffusion process, producing smooth, multi-step action trajectories that excel at contact-rich manipulation.
+This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).
+See the full documentation at [LeRobot Docs](https://huggingface.co/docs/lerobot/index).
+---
+## How to Get Started with the Model
+For a complete walkthrough, see the [training guide](https://huggingface.co/docs/lerobot/il_robots#train-a-policy).
+Below is the short version on how to train and run inference/eval:
+### Train from scratch
+```bash
+lerobot-train \
+  --dataset.repo_id=${HF_USER}/<dataset> \
+  --policy.type=act \
+  --output_dir=outputs/train/<desired_policy_repo_id> \
+  --job_name=lerobot_training \
+  --policy.device=cuda \
+  --policy.repo_id=${HF_USER}/<desired_policy_repo_id>
+  --wandb.enable=true
+```
+_Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`._
+### Evaluate the policy/run inference
+```bash
+lerobot-record \
+  --robot.type=so100_follower \
+  --dataset.repo_id=<hf_user>/eval_<dataset> \
+  --policy.path=<hf_user>/<desired_policy_repo_id> \
+  --episodes=10
+```
+Prefix the dataset repo with **eval\_** and supply `--policy.path` pointing to a local or hub checkpoint.
+---
+## Model Details
+- **License:** apache-2.0

config.json ADDED Viewed

	@@ -0,0 +1,99 @@

+{
+    "type": "diffusion",
+    "n_obs_steps": 2,
+    "input_features": {
+        "observation.images.wrist_image": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                240,
+                320
+            ]
+        },
+        "observation.audio.spectogram_values": {
+            "type": "AUDIO",
+            "shape": [
+                3,
+                298,
+                128
+            ]
+        },
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                1
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                9
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "push_to_hub": true,
+    "repo_id": "ramen-noodels/blue_round_button_small_audio_button",
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": null,
+    "horizon": 16,
+    "n_action_steps": 1,
+    "normalization_mapping": {
+        "VISUAL": "MEAN_STD",
+        "STATE": "MIN_MAX",
+        "ACTION": "MIN_MAX",
+        "AUDIO": "IDENTITY"
+    },
+    "drop_n_last_frames": 7,
+    "vision_backbone": "resnet18",
+    "crop_shape": [
+        216,
+        288
+    ],
+    "crop_is_random": true,
+    "pretrained_backbone_weights": null,
+    "use_group_norm": true,
+    "spatial_softmax_num_keypoints": 32,
+    "use_separate_rgb_encoder_per_camera": true,
+    "audio_backbone": "ramen-noodels/blue_round_button_small_click_detector",
+    "audio_norm_mean": 0.6490834819975885,
+    "audio_norm_std": 0.061071827558345816,
+    "audio_feature_type": "embedding",
+    "time_dimension": 298,
+    "freeze_audio_encoder": false,
+    "add_intermediate_audio_layer": true,
+    "pretrained_audio_weights": true,
+    "down_dims": [
+        512,
+        1024,
+        2048
+    ],
+    "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": 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
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:9eb5c1f5617ed6537f165fe080e2ca5724b62b17018661d66f219c1b7c91b5cc
+size 1407734276

train_config.json ADDED Viewed

	@@ -0,0 +1,213 @@

+{
+    "dataset": {
+        "repo_id": "ramen-noodels/prepared_blue_round_button_small_audio",
+        "root": null,
+        "episodes": null,
+        "image_transforms": {
+            "enable": true,
+            "max_num_transforms": 3,
+            "random_order": true,
+            "tfs": {
+                "brightness": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "brightness": [
+                            0.5,
+                            1.5
+                        ]
+                    }
+                },
+                "contrast": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "contrast": [
+                            0.5,
+                            1.5
+                        ]
+                    }
+                },
+                "saturation": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "saturation": [
+                            0.5,
+                            1.5
+                        ]
+                    }
+                },
+                "hue": {
+                    "weight": 1.0,
+                    "type": "ColorJitter",
+                    "kwargs": {
+                        "hue": [
+                            -0.1,
+                            0.1
+                        ]
+                    }
+                },
+                "sharpness": {
+                    "weight": 1.0,
+                    "type": "SharpnessJitter",
+                    "kwargs": {
+                        "sharpness": [
+                            0.5,
+                            1.5
+                        ]
+                    }
+                }
+            }
+        },
+        "revision": null,
+        "use_imagenet_stats": false,
+        "video_backend": "torchcodec",
+        "streaming": false
+    },
+    "env": null,
+    "policy": {
+        "type": "diffusion",
+        "n_obs_steps": 2,
+        "input_features": {
+            "observation.images.wrist_image": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    240,
+                    320
+                ]
+            },
+            "observation.audio.spectogram_values": {
+                "type": "AUDIO",
+                "shape": [
+                    3,
+                    298,
+                    128
+                ]
+            },
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    1
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    9
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "push_to_hub": true,
+        "repo_id": "ramen-noodels/blue_round_button_small_audio_button",
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": null,
+        "horizon": 16,
+        "n_action_steps": 1,
+        "normalization_mapping": {
+            "VISUAL": "MEAN_STD",
+            "STATE": "MIN_MAX",
+            "ACTION": "MIN_MAX",
+            "AUDIO": "IDENTITY"
+        },
+        "drop_n_last_frames": 7,
+        "vision_backbone": "resnet18",
+        "crop_shape": [
+            216,
+            288
+        ],
+        "crop_is_random": true,
+        "pretrained_backbone_weights": null,
+        "use_group_norm": true,
+        "spatial_softmax_num_keypoints": 32,
+        "use_separate_rgb_encoder_per_camera": true,
+        "audio_backbone": "ramen-noodels/blue_round_button_small_click_detector",
+        "audio_norm_mean": 0.6490834819975885,
+        "audio_norm_std": 0.061071827558345816,
+        "audio_feature_type": "embedding",
+        "time_dimension": 298,
+        "freeze_audio_encoder": false,
+        "add_intermediate_audio_layer": true,
+        "pretrained_audio_weights": true,
+        "down_dims": [
+            512,
+            1024,
+            2048
+        ],
+        "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": 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/2026-05-16/20-06-29_blue_round_button_small_audio_button",
+    "job_name": "blue_round_button_small_audio_button",
+    "resume": false,
+    "seed": 2025,
+    "num_workers": 8,
+    "batch_size": 32,
+    "steps": 100000,
+    "eval_freq": 0,
+    "log_freq": 200,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 50000,
+    "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": true,
+        "project": "imitation_button",
+        "entity": "rtalwar",
+        "notes": null,
+        "run_id": "7k57fy2k",
+        "mode": null
+    },
+    "checkpoint_path": null,
+    "rename_map": {}
+}