Power grid defect detection method and device based on YOLOv4-tiny algorithm, storage medium and electronic equipment

The embodiment of the invention discloses a power grid defect detection method and device based on a YOLOv4-tiny algorithm, a storage medium and electronic equipment, and belongs to the field of target detection. The method comprises the steps that based on a hot restart stochastic gradient descent (SGDR) algorithm, a sample set is used for training an improved YOLOv4-tiny network structure to obtain a target detection network; wherein in the training process, a mix algorithm is adopted to perform data enhancement on the sample set; the improved YOLOv4-tiny network structure comprises a spatial pyramid pooling SPP layer, and the SPP layer is used for carrying out feature fusion; the to-be-verified power grid image is detected based on the target detection network to obtain a power grid defect detection result, and rapid and accurate detection of power grid defects can be realized. 本申请实施例公开了一种基于YOLOv4-tiny算法的电网缺陷检测方法、装置、存储介质及电子设备，属于目标检测领域，该方法包括：基于热重启随机梯度下降SGDR算法，使用样本集对改进型YOLOv4-tiny网络结构进行训练得到目标检测网络；其中，在训练过程中采用