Instructions to use tonghuiwang123/so100-smolvla-s2000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use tonghuiwang123/so100-smolvla-s2000 with LeRobot:
- Notebooks
- Google Colab
- Kaggle
so100-smolvla-s2000
LeRobot policy for SO-ARM100 / SO100, task: Grab the white cube to the white cup
Trained on tonghuiwang123/test10 (2 cameras @1280x720, 30fps).
相机对照(顺序不能错,错了不报错但表现会莫名变差)
| 物理位置 | 设备 | 本模型要求的 key |
|---|---|---|
| 顶部 (top-down) | /dev/video2 |
camera1 |
| 腕部 (wrist) | /dev/video4 |
camera2 |
建议把
/dev/videoN换成/dev/v4l/by-id/...的稳定路径, 因为 videoN 编号在重插 USB / 重启后会漂移。
真机部署
lerobot-record \
--robot.type=so100_follower --robot.port=/dev/ttyACM0 \
--robot.id=my_awesome_follower_arm \
--robot.cameras="{
camera1: {type: opencv, index_or_path: /dev/video2, width: 1280, height: 720, fps: 30},
camera2: {type: opencv, index_or_path: /dev/video4, width: 1280, height: 720, fps: 30},
}" \
--dataset.repo_id=tonghuiwang123/eval_so100-smolvla-s2000 \
--dataset.single_task="Grab the white cube to the white cup" \
--policy.path=tonghuiwang123/so100-smolvla-s2000
分辨率必须 1280x720,与训练数据一致。
推理开销
| 模型族 | 显存 | 单次推理 |
|---|---|---|
| ACT | 0.70 GB | ~56 ms (720p x2) |
| SmolVLA | 1.03 GB | - |
| Pi0 | 9.43 GB | - |
| Pi0.5 | 9.90 GB | - |
ACT 注意:默认 n_action_steps=100 会开环执行 3.3 秒,期间腕部相机画面全部被丢弃。
若出现「朝目标动但抓不准」,优先调小到 15(约 0.5 秒闭环一次),无需重训。
- Downloads last month
- 3