Instructions to use naochanman/smolvla_epi101_2cam with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use naochanman/smolvla_epi101_2cam with LeRobot:
# See https://github.com/huggingface/lerobot?tab=readme-ov-file#installation for more details git clone https://github.com/huggingface/lerobot.git cd lerobot pip install -e .[smolvla]
# Launch finetuning on your dataset python lerobot/scripts/train.py \ --policy.path=naochanman/smolvla_epi101_2cam \ --dataset.repo_id=lerobot/svla_so101_pickplace \ --batch_size=64 \ --steps=20000 \ --output_dir=outputs/train/my_smolvla \ --job_name=my_smolvla_training \ --policy.device=cuda \ --wandb.enable=true
# Run the policy using the record function python -m lerobot.record \ --robot.type=so101_follower \ --robot.port=/dev/ttyACM0 \ # <- Use your port --robot.id=my_blue_follower_arm \ # <- Use your robot id --robot.cameras="{ front: {type: opencv, index_or_path: 8, width: 640, height: 480, fps: 30}}" \ # <- Use your cameras --dataset.single_task="Grasp a lego block and put it in the bin." \ # <- Use the same task description you used in your dataset recording --dataset.repo_id=HF_USER/dataset_name \ # <- This will be the dataset name on HF Hub --dataset.episode_time_s=50 \ --dataset.num_episodes=10 \ --policy.path=naochanman/smolvla_epi101_2cam - Notebooks
- Google Colab
- Kaggle
smolvla_epi101_2cam
English
SmolVLA finetuned on SO101 pick and place with 2 cameras (101 episodes).
Training
- Base model:
lerobot/smolvla_base - Dataset:
naochanman/so101_pick_fixed_2cam_100ep - Steps: 20000
- Batch size: 8
- Image augmentation: enabled
rename_mapapplied to swap camera labels
Note
Dataset so101_pick_fixed_2cam_100ep has camera labels (top/wrist) swapped.
Training used rename_map to correct this, so inference should use correct camera assignments:
top= top camerawrist= wrist camera
日本語
SO101 ピック&プレースタスクを2カメラ(top + wrist)で学習した SmolVLA モデル(101エピソード)。
トレーニング設定
- ベースモデル:
lerobot/smolvla_base - データセット:
naochanman/so101_pick_fixed_2cam_100ep - ステップ数: 20000
- バッチサイズ: 8
- 画像オーグメンテーション: 有効
rename_mapでカメララベルをスワップして学習
注意事項
データセット so101_pick_fixed_2cam_100ep はカメララベル(top/wrist)が逆に記録されています。
トレーニング時に rename_map で修正済みのため、推論時は正しいカメラ割り当てで使用してください:
top= 上方カメラwrist= 手首カメラ
- Downloads last month
- 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support