lerobot_train_model_SmolVLAmulti_gpu_wandb.sh
Robotaxi-OperatingSystem-Hardware-Interfaces/fmc3-robotics-main/projects/lerobot/demo_scripts/lerobot_train_model_SmolVLAmulti_gpu_wandb.sh
accelerate launch \
--multi_gpu \
--num_processes=1 \
$(which lerobot-train) \
--dataset.repo_id=${HF_USER}/my_eval_smolvla_single_cam \
--policy.path=lerobot/smolvla_base \
--policy.repo_id=${HF_USER}/lerobot_pick_and_place_smolvla \
--output_dir=outputs/train/act_multi_gpu/lerobot_model \
--job_name=pick_and_place_bottle_from_A_to_B \
--policy.device=cuda \
--batch_size=8 \
--steps=50000 \
--optimizer.lr=2e-4 \
--wandb.enable=true
関連記事
alloc.c
alloc.c — c source code from the Robotaxi-OperatingSystem-Hardware-Interfaces learning materials (Robotaxi-OperatingSystem-Hardware-Interfaces/class001_bundle/alloc.c).
記事を読む →hello.c
hello.c — c source code from the Robotaxi-OperatingSystem-Hardware-Interfaces learning materials (Robotaxi-OperatingSystem-Hardware-Interfaces/class001_bundle/hello.c).
記事を読む →mlock_demo.c
mlock_demo.c — c source code from the Robotaxi-OperatingSystem-Hardware-Interfaces learning materials (Robotaxi-OperatingSystem-Hardware-Interfaces/class001_bundle/mlock_demo.c).
記事を読む →debug_perf.py
debug_perf.py — python source code from the Robotaxi-OperatingSystem-Hardware-Interfaces learning materials (Robotaxi-OperatingSystem-Hardware-Interfaces/fmc3-robotics-main/projects/RoboBrain2.0/debug_perf.py).
記事を読む →inference.py
inference.py — python source code from the Robotaxi-OperatingSystem-Hardware-Interfaces learning materials (Robotaxi-OperatingSystem-Hardware-Interfaces/fmc3-robotics-main/projects/RoboBrain2.0/inference.py).
記事を読む →startup.sh
startup.sh — bash source code from the Robotaxi-OperatingSystem-Hardware-Interfaces learning materials (Robotaxi-OperatingSystem-Hardware-Interfaces/fmc3-robotics-main/projects/RoboBrain2.0/startup.sh).
記事を読む →