A Design of Model Compression Method Based on YOLOv5

Abstract

In response to the requirements for detection accuracy and speed in security detection technology in current smart city construction, a model compression method based on YOLOv5s is proposed, aiming to lighten the original model and detect the opening and closing states of car windows. Firstly, a structured pruning method based on channel weights is employed to perform channel pruning. Then, a fine-tuning training method based on logical distillation is adopted to restore the network detection accuracy. Experimental results on the car window dataset show that compared with the original algorithm, the improved algorithm only loses 0.3% in detection accuracy while reducing the number of parameters and computations to 41.5% and 44.3% of the original model, respectively. This significantly reduces the model complexity and achieves model lightweighting.