Quantitative deployment of weed models based on PaddlePaddle Research on Structural Optimization
In response to the problems of low computing resources and limited storage resources in terminal weeding devices such as drones,which are widely used in agriculture,this article ob-tains a lightweight model by quantitatively deploying and modifying the attention mechanism module of the model.The experimental results show that the inference time of the mobile mod-el is only about 1/10 of that of the server model.The weed classification inference speed de-ployed on Raspberry Pi 3B+is about 6fps,and the quantified weed classification model has a re-duction of over 40％in size,proving the effectiveness of quantification in reducing the model size.MobileNet based on CBAM attention mechanism simultaneously-CBAM weed classifica-tion model compared to MobileNetV3 based on SE Net attention mechanism_The Large model lost 0.3％in accuracy,but the model parameter size decreased by 24.7％,resulting in a more balanced overall performance.This study can provide theoretical basis and technical support for the miniaturization and landing application of weed models.
NETL
NSTL
万方数据
