Fix normalizer (#57)

* fix normalizer * fix val * update compute stats * delete norm * update readme * minor fix * fix action normalizer * fix * fix * update * update * update * update * update * lint * lint * lint * lint
2025-10-24 17:29:12 +08:00
parent 35399d187a
commit d821b0cb26
14 changed files with 837 additions and 119 deletions
@@ -0,0 +1,124 @@
+# Training Configuration for Wall-X Robotic Multi-Modal Learning
+# This configuration supports multi-modal learning with vision, language, and action data
+
+# Model and paths configuration
+log_name: "opensource_training"
+log_project: "libero"
+model_type: qwen2_5
+use_fast_tokenizer: true
+pretrained_wallx_path: "/path/to/qwen/"
+action_tokenizer_path: "/path/to/fast/"
+qwen_vl_act_config_path: "/path/to/qwen25_config.json"
+
+save_path: "/path/to/save"
+# Torch Profile
+profile: False
+profile_save_path: /path/to/profile/
+profile_wait_iters: 10
+profile_warmup_iters: 5
+profile_active_iters: 2
+
+# Training hyperparameters
+num_warmup_steps: 100
+num_training_steps: 64000000
+learning_rate: 0.00005
+min_lr: 0.00005
+num_epoch: 100
+gradient_accumulation_steps: 1
+batch_size_per_gpu: 8
+padding_side: left
+epoch_save_interval: 1
+
+# Robot configuration - Define degrees of freedom for each component
+dof_config:
+  follow_left_ee_cartesian_pos: 3      # Left end-effector Cartesian position
+  follow_left_ee_rotation: 3           # Left end-effector rotation
+  follow_left_gripper: 1               # Left gripper control
+  follow_right_ee_cartesian_pos: 3     # Right end-effector Cartesian position
+  follow_right_ee_rotation: 3          # Right end-effector rotation
+  follow_right_gripper: 1              # Right gripper control
+  head_actions: 2                      # Head/camera movement
+  height: 1                            # Mobile base height control
+  car_pose: 3                          # Mobile base pose (x, y, theta)
+
+# Agent proprioception configuration (typically matches DOF config)
+agent_pos_config:
+  follow_left_ee_cartesian_pos: 3
+  follow_left_ee_rotation: 3
+  follow_left_gripper: 1
+  follow_right_ee_cartesian_pos: 3
+  follow_right_ee_rotation: 3
+  follow_right_gripper: 1
+  head_actions: 2
+  height: 1
+  car_pose: 3
+
+norm_stats_path: "wall-x/workspace/lerobot_example/libero/libero_norm_stats.json"
+
+enable_customized_robot_config: true
+customized_robot_config:
+  name: "physical-intelligence/libero"
+  customized_dof_config:
+    "panda_action_eef_with_gripper": 7
+
+  customized_agent_pos_config:
+    "panda_state_eef_with_gripper": 8
+
+# Checkpoint resuming configuration
+# resume:
+#   ckpt: "/path/to/ckpt"
+#   load_ckpt_only: false
+
+# Data configuration
+data:
+  use_lerobot: true
+
+  # LeRobot dataset configuration
+  lerobot_config:
+    repo_id: "physical-intelligence/libero"
+    root: null
+    episodes: null
+    image_transforms: null
+    delta_timestamps: null
+    tolerance_s: 1e-4
+    revision: null
+    force_cache_sync: false
+    download_videos: true
+    video_backend: null
+
+  action_horizon: 32
+  train_test_split: 0.95
+
+  # Action keys for observation and prediction
+  obs_action_keys:
+    - follow_left_ee_cartesian_pos
+    - follow_left_ee_rotation
+    - follow_left_gripper
+    - follow_right_ee_cartesian_pos
+    - follow_right_ee_rotation
+    - follow_right_gripper
+    - head_actions
+    - height
+    - car_pose
+
+  predict_action_keys:
+    - follow_left_ee_cartesian_pos
+    - follow_left_ee_rotation
+    - follow_left_gripper
+    - follow_right_ee_cartesian_pos
+    - follow_right_ee_rotation
+    - follow_right_gripper
+    - head_actions
+    - height
+    - car_pose
+
+  # Image resolution configuration for different camera views
+  resolution:
+    face_view: 256
+    left_wrist_view: 256
+    right_wrist_view: 256
+    move1_view: 256
+    move2_view: 256
+    top_view: 256
+    wall_view: 256
+    multi_modal: 256