Upload policy weights, train config and readme

README.md

@@ -0,0 +1,62 @@
+---
+datasets: kelvinzhaozg/digit3a_hardware_box_pickup_dataset_depth
+library_name: lerobot
+license: apache-2.0
+model_name: diffusion
+pipeline_tag: robotics
+tags:
+- diffusion
+- lerobot
+- robotics
+---
+
+# 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

@@ -0,0 +1,86 @@
+{
+    "type": "diffusion",
+    "n_obs_steps": 1,
+    "normalization_mapping": {
+        "VISUAL": "IDENTITY",
+        "STATE": "MIN_MAX",
+        "ACTION": "MIN_MAX"
+    },
+    "input_features": {
+        "observation.images.depth": {
+            "type": "VISUAL",
+            "shape": [
+                1,
+                240,
+                424
+            ]
+        },
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                24
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                21
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "push_to_hub": true,
+    "repo_id": "kelvinzhaozg/diffusion_digit3a_hardware_box_pickup_depth_small",
+    "private": null,
+    "tags": null,
+    "license": null,
+    "horizon": 64,
+    "n_action_steps": 32,
+    "per_feature_normalization_overrides": {
+        "observation.images.depth": "MEAN_STD"
+    },
+    "drop_n_last_frames": 7,
+    "vision_backbone": "resnet18",
+    "crop_shape": null,
+    "crop_is_random": true,
+    "pretrained_backbone_weights": null,
+    "use_group_norm": true,
+    "spatial_softmax_num_keypoints": 32,
+    "use_separate_rgb_encoder_per_camera": false,
+    "use_depth_as_channel": true,
+    "use_depth_only": true,
+    "rgbd_pretrained_backbone_weights": null,
+    "norm_rgb": false,
+    "norm_depth": false,
+    "down_dims": [
+        128,
+        256,
+        512
+    ],
+    "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": "sample",
+    "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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ff681ae54f10ad46c65ced465b49e873a5f34dc9e0be26dddcb1233918d3193
+size 112659356

train_config.json

@@ -0,0 +1,196 @@
+{
+    "dataset": {
+        "repo_id": "kelvinzhaozg/digit3a_hardware_box_pickup_dataset_depth",
+        "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": false,
+        "video_backend": "torchcodec"
+    },
+    "env": null,
+    "policy": {
+        "type": "diffusion",
+        "n_obs_steps": 1,
+        "normalization_mapping": {
+            "VISUAL": "IDENTITY",
+            "STATE": "MIN_MAX",
+            "ACTION": "MIN_MAX"
+        },
+        "input_features": {
+            "observation.images.depth": {
+                "type": "VISUAL",
+                "shape": [
+                    1,
+                    240,
+                    424
+                ]
+            },
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    24
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    21
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "push_to_hub": true,
+        "repo_id": "kelvinzhaozg/diffusion_digit3a_hardware_box_pickup_depth_small",
+        "private": null,
+        "tags": null,
+        "license": null,
+        "horizon": 64,
+        "n_action_steps": 32,
+        "per_feature_normalization_overrides": {
+            "observation.images.depth": "MEAN_STD"
+        },
+        "drop_n_last_frames": 7,
+        "vision_backbone": "resnet18",
+        "crop_shape": null,
+        "crop_is_random": true,
+        "pretrained_backbone_weights": null,
+        "use_group_norm": true,
+        "spatial_softmax_num_keypoints": 32,
+        "use_separate_rgb_encoder_per_camera": false,
+        "use_depth_as_channel": true,
+        "use_depth_only": true,
+        "rgbd_pretrained_backbone_weights": null,
+        "norm_rgb": false,
+        "norm_depth": false,
+        "down_dims": [
+            128,
+            256,
+            512
+        ],
+        "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": "sample",
+        "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/2025-10-16/21-20-30_diffusion",
+    "job_name": "diffusion",
+    "resume": false,
+    "seed": 1000,
+    "num_workers": 4,
+    "batch_size": 8,
+    "steps": 200000,
+    "eval_freq": 20000,
+    "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": true,
+        "project": "digit3a_depth",
+        "entity": null,
+        "notes": null,
+        "run_id": "tizb087q",
+        "mode": null
+    }
+}