Since Electricity Grid Engineering involves a large number of personnel in the construction process, face recognition algorithms can be used to solve the personnel management problem. The recognition devices used in Electricity Grid Engineering are often mobile, embedded, and other lightweight devices with limited hardware performance. Although a large number of existing face recognition algorithms based on deep convolutional neural networks have high recognition accuracy, they are difficult to run in mobile devices or offline environments due to high computational complexity. In order to maintain the accuracy of face recognition while reducing the complexity of face recognition networks, a lightweight face recognition network based on Dynamic Convolution is proposed. Based on MobileNetV2, this paper introduces the Dynamic Convolution operation. It proposes a Dynamic Inverted Residuals Block, which enables the lightweight neural network to combine the feature extraction and learning ability of large neural networks to improve the recognition accuracy of the model. The experiments prove that the proposed model maintains high recognition accuracy while ensuring lightweight.

No abstract

No abstract