描述: 这是一个深度学习项目,利用 HRNet 和 FPN 架构进行钢材表面缺陷检测。本项目针对噪声较大的比赛数据进行了优化,包括椒盐噪声模拟和拼接数据处理,采用自定义增强技术、高级损失函数及多尺度特征融合。仓库包含训练脚本、模型定义和评估指标。
☆16Nov 17, 2024Updated last year
Alternatives and similar repositories for steel-defect-detection
Users that are interested in steel-defect-detection are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting: