Instructions to use Yunrufeng000/act_so100_4colors_540p with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use Yunrufeng000/act_so100_4colors_540p with LeRobot:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
|
Download README.md from Yunrufeng000/act_so100_4colors_540p: direct link, hf CLI and curl.
- Browser
- Download file 1.51 kB
-
https://huggingface.co/Yunrufeng000/act_so100_4colors_540p/resolve/main/README.md
- Command line
-
hf download hf://Yunrufeng000/act_so100_4colors_540p/README.md
-
curl -L -o README.md https://huggingface.co/Yunrufeng000/act_so100_4colors_540p/resolve/main/README.md
1.51 kB
metadata
license: apache-2.0
library_name: lerobot
pipeline_tag: robotics
tags:
- lerobot
- act
- so100
- so-arm100
- robotics
ACT · SO-100 · 四色抓取 (540×960)
基于 LeRobot 训练的 ACT 策略,用于 SO-100 (so_follower) 6 自由度机械臂的彩色物块抓取任务。
⚠️ 部署关键:输入分辨率
原始采集数据是 1920×1080,但本模型训练时把图像 **resize 到 540×960 (H×W)**。 推理时必须把相机画面同样 resize 到 540×960,否则会很慢且效果异常。
训练信息
| 项目 | 值 |
|---|---|
| 策略 | ACT (vision: ResNet18, chunk_size=100) |
| 机型 | SO-100 / so_follower,6 关节 |
| 相机 | 单路前置 (observation.images.front) |
| 输入分辨率 | 540×960 (从 1080p 缩放) |
| 训练步数 | 300,000 |
| Batch size | 8 |
| 最终 loss | 0.046 |
| 训练轮数 | ~82 epoch |
| fps | 30 |
| 硬件 | RTX 5080 (CUDA 12.8, torch 2.11) |
训练数据
合并自 8 个数据集(4 种颜色 × 2 轮采集),共 77 episode / 29250 帧 / 4 个任务:
Yunrufeng000/test_blue,test_blue1Yunrufeng000/test_green,test_green1Yunrufeng000/test_red,test_red1Yunrufeng000/test_yellow,test_yellow1
使用
from lerobot.policies.act.modeling_act import ACTPolicy
policy = ACTPolicy.from_pretrained("Yunrufeng000/act_so100_4colors_540p")
# 推理前记得把相机画面 resize 到 (540, 960)