Upload policy weights, train config and readme

README.md

@@ -0,0 +1,62 @@
+---
+datasets: kelvinzhaozg/t1_stack_cube_isaaclab_dataset
+library_name: lerobot
+license: apache-2.0
+model_name: flow_matching_dit
+pipeline_tag: robotics
+tags:
+- robotics
+- flow_matching_dit
+- lerobot
+---
+
+# Model Card for flow_matching_dit
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+_Model type not recognized — please update this template._
+
+
+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 +1,75 @@
+{
+    "type": "flow_matching_dit",
+    "n_obs_steps": 1,
+    "input_features": {
+        "observation.images.head_rgb": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                240,
+                424
+            ]
+        },
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                21
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                18
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "push_to_hub": true,
+    "repo_id": "kelvinzhaozg/flow_matching_dit_t1_stack_cube_isaaclab",
+    "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",
+    "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": true,
+    "hidden_size": 1536,
+    "num_layers": 12,
+    "num_attention_heads": 12,
+    "attention_dropout": 0.1,
+    "patch_size": 2,
+    "use_adaln_zero": true,
+    "cross_attention_dim": 512,
+    "add_cross_attention": true,
+    "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,
+    "flow_matching_type": "CondOT",
+    "num_integration_steps": 50,
+    "fm_time_embed_dim": 256,
+    "fm_min_period": 0.004,
+    "fm_max_period": 4.0,
+    "ode_solver_method": "midpoint"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dd698eb3206066e4581ca945a2e3caae594f8ba4d22875bc211848e49c11774
+size 2004872544

train_config.json

@@ -0,0 +1,202 @@
+{
+    "dataset": {
+        "repo_id": "kelvinzhaozg/t1_stack_cube_isaaclab_dataset",
+        "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": "flow_matching_dit",
+        "n_obs_steps": 1,
+        "input_features": {
+            "observation.images.head_rgb": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    240,
+                    424
+                ]
+            },
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    21
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    18
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "push_to_hub": true,
+        "repo_id": "kelvinzhaozg/flow_matching_dit_t1_stack_cube_isaaclab",
+        "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",
+        "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": true,
+        "hidden_size": 1536,
+        "num_layers": 12,
+        "num_attention_heads": 12,
+        "attention_dropout": 0.1,
+        "patch_size": 2,
+        "use_adaln_zero": true,
+        "cross_attention_dim": 512,
+        "add_cross_attention": true,
+        "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,
+        "flow_matching_type": "CondOT",
+        "num_integration_steps": 50,
+        "fm_time_embed_dim": 256,
+        "fm_min_period": 0.004,
+        "fm_max_period": 4.0,
+        "ode_solver_method": "midpoint"
+    },
+    "output_dir": "outputs/train/2025-11-04/06-08-30_flow_matching_dit",
+    "job_name": "flow_matching_dit",
+    "resume": false,
+    "seed": 1000,
+    "num_workers": 4,
+    "batch_size": 32,
+    "steps": 250000,
+    "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": "t1_stack_cube_isaac",
+        "entity": null,
+        "notes": null,
+        "run_id": "zihec3zk",
+        "mode": null
+    },
+    "checkpoint_path": null,
+    "rename_map": {}
+}