Battery piece silk-screen printing defect detection method based on improved YOLOv5

The invention provides an improved YOLOv5-based battery piece silk-screen printing defect detection method, which comprises the following steps of: generating a new silk-screen printing defect image by using data enhancement to expand the number of data sets to obtain more data samples, then marking silk-screen printing defects, and dividing a training set, a test set and a verification set according to a preset proportion, so that the detection accuracy of the silk-screen printing defects is improved. The training set is input to the input end of the PCDD-YOLOv5 network, and a CBAMC3n module is formed through a C3 module and a CBAM module in the backbone network to realize more efficient feature extraction and fusion of a feature map, so that the model can dynamically adjust the importance of different features, more efficiently and accurately capture key features in the feature map, the target detection precision is improved, and the target detection efficiency is improved. And a small target detection laye