交通标志辅助识别技术在自动驾驶体系中越发重要，由于不同的硬件设备承载力不同，使模型更轻量化的同时保持性能不变或更好成为当下各单位和企业的研究方向之一。为了使模型更轻量化的同时提升模型识别效果和检测速度，提出一种基于SWimAM（a simple, parameter-free attention module add weight part for convolutional neural networks）设计YOLOv5（you only look once version 5）的轻量化交通标志检测方法。该方法基于SimAM机制加入可迭代学习权重改变内部权重的计算方式提出SWimAM模块，并将YOLOv5的backbone结构中的C3层替换成该模块，将head部分融合SE（squeeze-and-excitation networks）注意力机制的同时把损失函数替换为SIoU（soft intersection over union）强化了模型的检测精度减少了梯度的不稳定性。提出一种滤波拼接的数据增强方法扩充了TT100K交通标志数据集，解决了部分标签不均匀的问题。改进的YOLOv5s网络的在TT100K上识别平均精度提升2.5%、检测速度提升7.33%、计算复杂度下降3.07%、参数量下降9.27%。在中国交通标志检测数据集CCTSDB中和德国交通GTSDB数据集中平均精度分别达到94.9%和94.7%，验证了该模型具有良好的泛化性。

Traffic sign assisted recognition technology is becoming more and more important in the automatic driving system. Due to the different bearing capacity of different hardware equipment, it has become one of the research directions of various units and enterprises to make the model lighter while the performance is unchanged or better. In order to make the model lighter and improve the model recognition effect and detection speed, a lightweight traffic sign detection method based on SWimAM (a simple, parameter-free attention module add weight part for convolutional neural networks) designed YOLOv5 (you only look once version 5) was proposed. This method added iterable learning weights based on SimAM mechanism and changes the calculation method of internal weights. SWimAM module was proposed and C3 layer of YOLOv5 backbone structure was replaced with this module. The head part was fused with SE (squeeze-and-excitation networks) attention mechanism and the loss function was replaced by SIoU (soft intersection over union) to enhance the detection accuracy of the model and reduce the instability of the gradient. A data enhancement method of filtering Mosaic images was proposed to solve the non-uniformity of partial labels. On the final TT100K traffic sign data set, the recognition mean average precision of the improved YOLOv5s network increase by 2.5%, calculation speed increased by 7.33%, computational complexity decreased by 3.07%, and the number of references decreased by 9.27%. The mean average precision of Chinese traffic sign detection data set CCTSDB and German traffic sign detection data set GTSDB reached 94.9% and 94.7%, respectively, which verified that the model has good generalization.