Upload policy weights, train config and readme

Browse files

Files changed (4) hide show

README.md +62 -0
config.json +120 -0
model.safetensors +3 -0
train_config.json +290 -0

README.md ADDED Viewed

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

+---
+datasets: aposadasn/xarm7_beavrsim_shellgame_labeled_cartesian
+library_name: lerobot
+license: apache-2.0
+model_name: mact_flow
+pipeline_tag: robotics
+tags:
+- robotics
+- lerobot
+- mact_flow
+---
+# Model Card for mact_flow
+<!-- 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 ADDED Viewed

	@@ -0,0 +1,120 @@

+{
+    "type": "mact_flow",
+    "n_obs_steps": 20,
+    "input_features": {
+        "observation.state": {
+            "type": "STATE",
+            "shape": [
+                8
+            ]
+        },
+        "observation.images.overhead": {
+            "type": "VISUAL",
+            "shape": [
+                3,
+                480,
+                640
+            ]
+        },
+        "observation.environment_state": {
+            "type": "ENV",
+            "shape": [
+                13
+            ]
+        }
+    },
+    "output_features": {
+        "action": {
+            "type": "ACTION",
+            "shape": [
+                8
+            ]
+        }
+    },
+    "device": "cuda",
+    "use_amp": false,
+    "use_peft": false,
+    "push_to_hub": true,
+    "repo_id": "arclabmit/xarm7_beavrsim_mact_flow_shell_game_model",
+    "private": null,
+    "tags": null,
+    "license": null,
+    "pretrained_path": null,
+    "n_history_tokens": 20,
+    "chunk_size": 32,
+    "n_action_steps": 1,
+    "observation_stride": 8,
+    "normalization_mapping": {
+        "VISUAL": "MEAN_STD",
+        "STATE": "MEAN_STD",
+        "ACTION": "MIN_MAX"
+    },
+    "vision_backbone": "resnet18",
+    "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
+    "replace_final_stride_with_dilation": false,
+    "dim_model": 512,
+    "n_heads": 8,
+    "dim_feedforward": 3200,
+    "n_dit_layers": 16,
+    "dit_attention_head_dim": 64,
+    "n_cond_self_attn_layers": 2,
+    "num_inference_steps": 4,
+    "num_timestep_buckets": 1000,
+    "noise_beta_alpha": 1.5,
+    "noise_beta_beta": 1.0,
+    "noise_s": 0.999,
+    "do_mask_loss_for_padding": true,
+    "temporal_ensemble_coeff": null,
+    "dropout": 0.1,
+    "optimizer_lr": 0.0001,
+    "optimizer_weight_decay": 0.0001,
+    "optimizer_lr_backbone": 1e-05,
+    "freeze_history_backbone": false,
+    "n_mamba2_layers": 4,
+    "n_spatial_attn_layers": 2,
+    "n_spatial_tokens": 16,
+    "use_optical_flow": false,
+    "max_images_per_chunk": 64,
+    "history_image_size": [
+        224,
+        224
+    ],
+    "spatial_adapter_hidden_dim": 512,
+    "spatial_adapter_dropout": 0.1,
+    "use_vq_mode": true,
+    "n_vq_codes": 8,
+    "vq_dim": null,
+    "vq_commitment_weight": 0.25,
+    "vq_mode_loss_weight": 5.0,
+    "vq_codebook_loss_weight": 1.0,
+    "use_teacher_forcing": true,
+    "use_classifier_inference": true,
+    "teacher_forcing_start_prob": 1.0,
+    "teacher_forcing_end_prob": 0.0,
+    "teacher_forcing_decay_steps": 50000,
+    "use_action_mode_classifier": true,
+    "action_mode_hidden_dim": 128,
+    "action_mode_n_conv_layers": 2,
+    "action_mode_kernel_size": 5,
+    "action_mode_bootstrap_weight": 1.0,
+    "action_mode_pred_weight": 1.0,
+    "action_mode_use_ee": true,
+    "fk_head_hidden_dim": 64,
+    "fk_head_loss_weight": 1.0,
+    "use_point_tracking": true,
+    "n_tracked_points": 3,
+    "tracking_point_dim": 3,
+    "tracking_loss_weight": 1.0,
+    "use_history_mode_classifier": true,
+    "history_mode_loss_weight": 2.0,
+    "use_env_state_as_privileged_supervision": true,
+    "env_state_positions_slice": [
+        0,
+        9
+    ],
+    "env_state_target_id_index": 9,
+    "env_state_ee_pos_slice": [
+        10,
+        13
+    ]
+}

model.safetensors ADDED Viewed

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

+version https://git-lfs.github.com/spec/v1
+oid sha256:5ef6d1b04411a01f0564910f2bdb679213abc3f887234cb72e12c496e07c23e3
+size 457008232

train_config.json ADDED Viewed

	@@ -0,0 +1,290 @@

+{
+    "dataset": {
+        "repo_id": "aposadasn/xarm7_beavrsim_shellgame_labeled_cartesian",
+        "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": "torchcodec",
+        "streaming": false
+    },
+    "env": {
+        "type": "beavr",
+        "task": null,
+        "fps": 30,
+        "features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    8
+                ]
+            },
+            "agent_pos": {
+                "type": "STATE",
+                "shape": [
+                    8
+                ]
+            },
+            "overhead": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            }
+        },
+        "features_map": {
+            "action": "action",
+            "agent_pos": "observation.state",
+            "overhead": "observation.images.overhead"
+        },
+        "max_parallel_tasks": 1,
+        "disable_env_checker": true,
+        "scene": "scene_shell_game",
+        "episode_length": 1000,
+        "seed": null
+    },
+    "policy": {
+        "type": "mact_flow",
+        "n_obs_steps": 20,
+        "input_features": {
+            "observation.state": {
+                "type": "STATE",
+                "shape": [
+                    8
+                ]
+            },
+            "observation.images.overhead": {
+                "type": "VISUAL",
+                "shape": [
+                    3,
+                    480,
+                    640
+                ]
+            },
+            "observation.environment_state": {
+                "type": "ENV",
+                "shape": [
+                    13
+                ]
+            }
+        },
+        "output_features": {
+            "action": {
+                "type": "ACTION",
+                "shape": [
+                    8
+                ]
+            }
+        },
+        "device": "cuda",
+        "use_amp": false,
+        "use_peft": false,
+        "push_to_hub": true,
+        "repo_id": "arclabmit/xarm7_beavrsim_mact_flow_shell_game_model",
+        "private": null,
+        "tags": null,
+        "license": null,
+        "pretrained_path": null,
+        "n_history_tokens": 20,
+        "chunk_size": 32,
+        "n_action_steps": 1,
+        "observation_stride": 8,
+        "normalization_mapping": {
+            "VISUAL": "MEAN_STD",
+            "STATE": "MEAN_STD",
+            "ACTION": "MIN_MAX"
+        },
+        "vision_backbone": "resnet18",
+        "pretrained_backbone_weights": "ResNet18_Weights.IMAGENET1K_V1",
+        "replace_final_stride_with_dilation": false,
+        "dim_model": 512,
+        "n_heads": 8,
+        "dim_feedforward": 3200,
+        "n_dit_layers": 16,
+        "dit_attention_head_dim": 64,
+        "n_cond_self_attn_layers": 2,
+        "num_inference_steps": 4,
+        "num_timestep_buckets": 1000,
+        "noise_beta_alpha": 1.5,
+        "noise_beta_beta": 1.0,
+        "noise_s": 0.999,
+        "do_mask_loss_for_padding": true,
+        "temporal_ensemble_coeff": null,
+        "dropout": 0.1,
+        "optimizer_lr": 0.0001,
+        "optimizer_weight_decay": 0.0001,
+        "optimizer_lr_backbone": 1e-05,
+        "freeze_history_backbone": false,
+        "n_mamba2_layers": 4,
+        "n_spatial_attn_layers": 2,
+        "n_spatial_tokens": 16,
+        "use_optical_flow": false,
+        "max_images_per_chunk": 64,
+        "history_image_size": [
+            224,
+            224
+        ],
+        "spatial_adapter_hidden_dim": 512,
+        "spatial_adapter_dropout": 0.1,
+        "use_vq_mode": true,
+        "n_vq_codes": 8,
+        "vq_dim": null,
+        "vq_commitment_weight": 0.25,
+        "vq_mode_loss_weight": 5.0,
+        "vq_codebook_loss_weight": 1.0,
+        "use_teacher_forcing": true,
+        "use_classifier_inference": true,
+        "teacher_forcing_start_prob": 1.0,
+        "teacher_forcing_end_prob": 0.0,
+        "teacher_forcing_decay_steps": 50000,
+        "use_action_mode_classifier": true,
+        "action_mode_hidden_dim": 128,
+        "action_mode_n_conv_layers": 2,
+        "action_mode_kernel_size": 5,
+        "action_mode_bootstrap_weight": 1.0,
+        "action_mode_pred_weight": 1.0,
+        "action_mode_use_ee": true,
+        "fk_head_hidden_dim": 64,
+        "fk_head_loss_weight": 1.0,
+        "use_point_tracking": true,
+        "n_tracked_points": 3,
+        "tracking_point_dim": 3,
+        "tracking_loss_weight": 1.0,
+        "use_history_mode_classifier": true,
+        "history_mode_loss_weight": 2.0,
+        "use_env_state_as_privileged_supervision": true,
+        "env_state_positions_slice": [
+            0,
+            9
+        ],
+        "env_state_target_id_index": 9,
+        "env_state_ee_pos_slice": [
+            10,
+            13
+        ]
+    },
+    "output_dir": "outputs/train/2026-03-05/12-45-49_xarm7_mact_beavrsim_shell_game",
+    "job_name": "xarm7_mact_beavrsim_shell_game",
+    "resume": false,
+    "seed": 1000,
+    "num_workers": 4,
+    "batch_size": 8,
+    "steps": 100000,
+    "eval_freq": 20000,
+    "log_freq": 200,
+    "tolerance_s": 0.0001,
+    "save_checkpoint": true,
+    "save_freq": 20000,
+    "use_policy_training_preset": true,
+    "optimizer": {
+        "type": "adam",
+        "lr": 0.0001,
+        "weight_decay": 0.0001,
+        "grad_clip_norm": 10.0,
+        "betas": [
+            0.9,
+            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": "lerobot",
+        "entity": null,
+        "notes": null,
+        "run_id": "6a5kerwv",
+        "mode": null
+    },
+    "peft": null,
+    "use_rabc": false,
+    "rabc_progress_path": null,
+    "rabc_kappa": 0.01,
+    "rabc_epsilon": 1e-06,
+    "rabc_head_mode": "sparse",
+    "rename_map": {},
+    "checkpoint_path": null
+}