Upload policy weights, train config and readme

README.md

@@ -0,0 +1,62 @@
+---
+datasets: LSY-lab/stack_vision_only_v2
+library_name: lerobot
+license: apache-2.0
+model_name: ditflow
+pipeline_tag: robotics
+tags:
+- ditflow
+- robotics
+- lerobot
+---
+
+# Model Card for ditflow
+
+<!-- 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
+python -m lerobot.scripts.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
+python -m 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 +1,91 @@
+{
+    "type": "ditflow",
+    "n_obs_steps": 2,
+    "normalization_mapping": {
+        "VISUAL": "MEAN_STD",
+        "STATE": "MIN_MAX",
+        "ACTION": "MIN_MAX"
+    },
+    "input_features": {
+        "observation.images.primary": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                256,
+                256
+            ]
+        },
+        "observation.images.wrist": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                256,
+                256
+            ]
+        },
+        "observation.state.gripper": {
+            "type": "STATE",
+            "shape": [
+                1
+            ]
+        },
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                1
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                7
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "push_to_hub": true,
+    "repo_id": "danielsanjosepro/ditflow_stack_vision_only_v2",
+    "private": null,
+    "tags": null,
+    "license": null,
+    "horizon": 16,
+    "n_action_steps": 8,
+    "use_proprioceptive": false,
+    "drop_n_last_frames": 7,
+    "vision_backbone": "resnet18",
+    "crop_shape": [
+        224,
+        224
+    ],
+    "crop_is_random": true,
+    "pretrained_backbone_weights": null,
+    "use_group_norm": true,
+    "spatial_softmax_num_keypoints": 32,
+    "use_separate_rgb_encoder_per_camera": true,
+    "frequency_embedding_dim": 256,
+    "hidden_dim": 512,
+    "num_blocks": 6,
+    "num_heads": 16,
+    "dropout": 0.1,
+    "dim_feedforward": 4096,
+    "activation": "gelu",
+    "training_noise_sampling": "uniform",
+    "clip_sample": true,
+    "clip_sample_range": 1.0,
+    "num_inference_steps": 100,
+    "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,
+    "features_to_exclude": [],
+    "features_to_include": null
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd218aee0c76ddc68a9aede818d9608e7bb90e96d32f8a817a304da1137c5f9e
+size 257746460

train_config.json

@@ -0,0 +1,201 @@
+{
+    "dataset": {
+        "repo_id": "LSY-lab/stack_vision_only_v2",
+        "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": "ditflow",
+        "n_obs_steps": 2,
+        "normalization_mapping": {
+            "VISUAL": "MEAN_STD",
+            "STATE": "MIN_MAX",
+            "ACTION": "MIN_MAX"
+        },
+        "input_features": {
+            "observation.images.primary": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    256,
+                    256
+                ]
+            },
+            "observation.images.wrist": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    256,
+                    256
+                ]
+            },
+            "observation.state.gripper": {
+                "type": "STATE",
+                "shape": [
+                    1
+                ]
+            },
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    1
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    7
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "push_to_hub": true,
+        "repo_id": "danielsanjosepro/ditflow_stack_vision_only_v2",
+        "private": null,
+        "tags": null,
+        "license": null,
+        "horizon": 16,
+        "n_action_steps": 8,
+        "use_proprioceptive": false,
+        "drop_n_last_frames": 7,
+        "vision_backbone": "resnet18",
+        "crop_shape": [
+            224,
+            224
+        ],
+        "crop_is_random": true,
+        "pretrained_backbone_weights": null,
+        "use_group_norm": true,
+        "spatial_softmax_num_keypoints": 32,
+        "use_separate_rgb_encoder_per_camera": true,
+        "frequency_embedding_dim": 256,
+        "hidden_dim": 512,
+        "num_blocks": 6,
+        "num_heads": 16,
+        "dropout": 0.1,
+        "dim_feedforward": 4096,
+        "activation": "gelu",
+        "training_noise_sampling": "uniform",
+        "clip_sample": true,
+        "clip_sample_range": 1.0,
+        "num_inference_steps": 100,
+        "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,
+        "features_to_exclude": [],
+        "features_to_include": null
+    },
+    "output_dir": "outputs/train/2025-12-14/10-20-23_config/train_ditflow_stack_vision_only.json",
+    "job_name": "config/train_ditflow_stack_vision_only.json",
+    "resume": false,
+    "seed": 1000,
+    "num_workers": 4,
+    "batch_size": 128,
+    "steps": 20000,
+    "eval_freq": 2000,
+    "log_freq": 100,
+    "save_checkpoint": true,
+    "save_freq": 2000,
+    "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": "policies",
+        "entity": null,
+        "notes": null,
+        "run_id": "q0urrjfp",
+        "mode": null
+    }
+}