PCB defect detection

This project contains two datasets: DeepPCB and PKU-Market-PCB (A-Version), which are used to validate the detection performance and generalization ability of the model proposed in the paper <i>“A Lightweight PCB Defect Detection Method Based on Group Convolution and Adaptive Pruning”</i>. The two YAML files are dataset configuration files used in the project, and their specific usage is described in the project documentation.

本项目包含DeepPCB与PKU-Market-PCB（A版本）两个数据集，用于验证论文《基于分组卷积与自适应剪枝的轻量级印刷电路板缺陷检测方法》中提出的模型的检测性能与泛化能力。本项目所用的两个YAML文件均为数据集配置文件，其具体使用方法详见项目文档。