Init
This commit is contained in:
Starrick
@@ -0,0 +1,67 @@
|
||||
# Training Configuration Guide
|
||||
|
||||
This document explains the key configuration parameters that can be modified for Wall-X training.
|
||||
|
||||
## Quick Start Checklist
|
||||
1. **Update run.sh**: Set `code_dir` and `config_path` to your actual paths
|
||||
2. **Configure GPUs**: Set `CUDA_VISIBLE_DEVICES` for your available GPUs
|
||||
3. **Update config paths**: Replace all `/path/to/` placeholders in config.yml with actual paths
|
||||
4. **Configure robot**: Set `dof_config` and `agent_pos_config` for your robot
|
||||
5. **Set dataset**: Choose appropriate `repo_id` for your dataset
|
||||
6. **Adjust batch size**: Set `batch_size_per_gpu` based on GPU memory
|
||||
7. **Run training**: Execute `bash ./workspace/lerobot_example/run.sh`
|
||||
|
||||
## Required Paths (Must Modify)
|
||||
```yaml
|
||||
processor_path: "/path/to/model/" # Path to model processor
|
||||
pretrained_qwen_vl_path: "/path/to/qwen_vl_model/" # Path to pretrained Qwen VL model
|
||||
qwen_vl_act_config_path: "/path/to/config.json" # Path to model config file
|
||||
action_tokenizer_path: "/path/to/fast/" # Path to action tokenizer
|
||||
save_path: "/path/to/workspace/" # Path to save training outputs
|
||||
```
|
||||
|
||||
## Training Parameters (Commonly Modified)
|
||||
|
||||
### Learning Rate Settings
|
||||
- `learning_rate`: Initial learning rate (default: 0.00009)
|
||||
- `min_lr`: Minimum learning rate for scheduler (default: 0.00005)
|
||||
- `num_warmup_steps`: Number of warmup steps (default: 100)
|
||||
|
||||
### Batch Size and Memory
|
||||
- `batch_size_per_gpu`: Batch size per GPU - adjust based on GPU memory
|
||||
- `gradient_accumulation_steps`: Gradient accumulation steps
|
||||
- `num_training_steps`: Total training steps
|
||||
- `num_epoch`: Number of training epochs
|
||||
|
||||
## Robot Configuration (Modify for Your Robot)
|
||||
|
||||
### DOF Configuration
|
||||
Modify `dof_config` to match your robot's action space:
|
||||
- Add/remove action keys based on your robot's capabilities
|
||||
- Ensure DOF numbers match your robot's action dimensions
|
||||
|
||||
### Agent Position Configuration
|
||||
Keep `agent_pos_config` consistent with `dof_config`.
|
||||
|
||||
### Action Keys
|
||||
- `obs_action_keys`: Actions used as observation context
|
||||
- `predict_action_keys`: Actions to predict/control
|
||||
|
||||
## Data Configuration
|
||||
|
||||
### Dataset
|
||||
- `repo_id`: LeRobot dataset identifier
|
||||
- `train_test_split`: Training/validation split ratio (default: 0.95)
|
||||
- `action_horizon`: Number of future actions to predict (default: 32)
|
||||
|
||||
### Image Settings
|
||||
- `resolution`: Image resolution for different camera views
|
||||
- `download_videos`: Whether to download video files (true/false)
|
||||
|
||||
## Resume Training (Optional)
|
||||
- `resume.ckpt`: Path to checkpoint for resuming training
|
||||
- `resume.load_ckpt_only`: Only load model weights, not optimizer state
|
||||
|
||||
## Performance Settings (Optional)
|
||||
- `profile`: Enable PyTorch profiling (true/false)
|
||||
- `padding_side`: Token padding side (left/right)
|
||||
@@ -0,0 +1,112 @@
|
||||
# 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: "robotic_training"
|
||||
log_project: "vla_training"
|
||||
model_type: qwen2_5
|
||||
processor_path: "/path/to/model/"
|
||||
pretrained_qwen_vl_path: "/path/to/qwen_vl_model/"
|
||||
qwen_vl_act_config_path: "/path/to/config.json"
|
||||
action_tokenizer_path: "/path/to/fast/"
|
||||
save_path: "/path/to/workspace/"
|
||||
|
||||
# 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: 0.00009
|
||||
min_lr: 0.00005
|
||||
num_epoch: 100
|
||||
gradient_accumulation_steps: 32
|
||||
batch_size_per_gpu: 8
|
||||
padding_side: left
|
||||
|
||||
# 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
|
||||
|
||||
# Checkpoint resuming configuration
|
||||
resume:
|
||||
ckpt: "/path/to/resume_model/"
|
||||
load_ckpt_only: true
|
||||
|
||||
# Data configuration
|
||||
data:
|
||||
use_lerobot: true
|
||||
|
||||
# LeRobot dataset configuration
|
||||
lerobot_config:
|
||||
repo_id: "lerobot/aloha_mobile_cabinet"
|
||||
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
|
||||
@@ -0,0 +1,24 @@
|
||||
#!/bin/bash
|
||||
# export CUDA_VISIBLE_DEVICES=4,5,6,7
|
||||
export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
|
||||
NUM_GPUS=$(echo $CUDA_VISIBLE_DEVICES | tr ',' '\n' | wc -l)
|
||||
|
||||
# print current time
|
||||
echo "[current time: $(date +'%Y-%m-%d %H:%M:%S')]"
|
||||
|
||||
code_dir="/path/to/wall-x"
|
||||
config_path="/path/to/wall-x/workspace/lerobot_example"
|
||||
|
||||
# Use a fixed port instead of a random one
|
||||
export PORT=$((21000 + $RANDOM % 30000))
|
||||
|
||||
MASTER_PORT=10239 # use 5 digits ports
|
||||
|
||||
export LAUNCHER="accelerate launch --num_processes=$NUM_GPUS --main_process_port=$PORT"
|
||||
|
||||
export SCRIPT="${code_dir}/train_qact.py"
|
||||
export SCRIPT_ARGS="--config ${config_path}/config_qact.yml --seed $MASTER_PORT"
|
||||
|
||||
echo "Running command: $LAUNCHER $SCRIPT $SCRIPT_ARGS"
|
||||
|
||||
$LAUNCHER $SCRIPT $SCRIPT_ARGS
|
||||
Reference in New Issue
Block a user