Modelpublic

tonghuiwang123/so100-diffusion-new60-ft

sourceHugging Faceupdated 23d agoView on Hugging Face

0likes25downloads

Model Card

so100-diffusion-new60-ft · step 30000

DIFFUSION policy for SO-ARM100 / SO100 — Grab the white cube to the white cup

—数据: tonghuiwang123/40 60 episodes / 13454 frames / 2×1280x720 @30fps
—Checkpoint: step 30000 ≈ 142.7 epoch（有效 batch 64）
—两阶段：起点为旧60集(旧相机)训练的 Diffusion Policy 权重；resizeshape=[180,320] cropratio=0.95

相机命名（各算法族不同，顺序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`	`front`
腕部 (wrist)	`/dev/video4`	`side`

部署

bash

lerobot-record \
  --robot.type=so100_follower --robot.port=/dev/ttyACM0 \
  --robot.id=my_awesome_follower_arm \
  --robot.cameras="{
                     front: {type: opencv, index_or_path: /dev/video2, width: 1280, height: 720, fps: 30},
                     side: {type: opencv, index_or_path: /dev/video4, width: 1280, height: 720, fps: 30},
                    }" \
  --dataset.repo_id=tonghuiwang123/eval_so100-diffusion-new60-ft \
  --dataset.single_task="Grab the white cube to the white cup" \
  --policy.path=tonghuiwang123/so100-diffusion-new60-ft

分辨率必须 1280x720。推理显存约 1.1 GB。中间 checkpoint 用 --policy.pretrained_revision=ckpt-XXXXXX。