北京大学学报（自然科学版）2025，Vol.61Issue(5)：884-890,7.DOI:10.13209/j.0479-8023.2025.077
一种基于双级剪枝和训练后量化的火灾检测轻量化模型设计方法
A Lightweight Model Design Method for Fire Detection via Dual Level Pruning and Post-Training Quantization
徐鹏涛 1王刚 1张连杰 1王越 2黄华1
作者信息
- 1. 西安中核核仪器股份有限公司,西安 710061
- 2. 北京大学软件与微电子学院,北京 102600
- 折叠
摘要
Abstract
A lightweight fire detection model is designed to meet the urgent demand for efficient and lightweight models in the field of fire detection.The model is built based on the SSD object detection algorithm,and pruning and quantization methods are used to achieve lightweighting of the detection model in order to reduce model size,improve model speed,and meet the deployment requirements in practical scenarios.In order to achieve effective pruning of the model network at both channel and layer levels,a dual pruning method based on fusible residual convolution blocks is proposed.In order to effectively improve the performance of the quantization model,an adaptive method is introduced to quantize the model,which realizes a post-training quantization method based on adaptive outlier removal.The experimental results show that the proposed pruning method and quantization method exhibit significant advantages compared with the original method,and can significantly reduce the model size with almost no impact on performance.The final lightweight fire detection model also has excellent performance.关键词
火灾检测/SSD目标检测/模型轻量化/剪枝/量化Key words
fire detection/SSD object detection/model lightweighting/pruning/quantization引用本文复制引用
徐鹏涛,王刚,张连杰,王越,黄华..一种基于双级剪枝和训练后量化的火灾检测轻量化模型设计方法[J].北京大学学报（自然科学版）,2025,61(5):884-890,7.
