A Lightweight Deep Learning Model for Identifying Weeds in Corn and Soybean Using Quantization
Open Access
- 2 November 2023
- conference paper
- Published by MDPI AG in Engineering Proceedings
- Vol. 56 (1) , 318
Abstract
Deep learning models are applied in precision agriculture for site-specific weed management by identifying weeds in farmlands. Unfortunately, because deep learning models are usually large, they are rarely adopted in resource-constrained devices (like edge devices) used in precision agriculture. In this study, we propose a lightweight deep learning model for detecting weeds in corn and soybean plants. We used transfer learning to train an InceptionnetV3 model for the task. The dataset used consists of a total of 13,177 samples of corn, soybean, and weeds. The InceptionV3 model, whose size is 183.34 MB, achieved a classification accuracy of 97%. We then applied the quantization technique to reduce the size of the model. The quantized model was reduced to a size of 23.38 MB, achieving an accuracy of 87%. The results show that quantization can reduce the size of a deep learning model while maintaining a reasonable amount of performance.Keywords
This publication has 7 references indexed in Scilit:
- Weed recognition using deep learning techniques on class-imbalanced imageryCrop & Pasture Science, 2022
- Towards Model Compression for Deep Learning Based Speech EnhancementIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021
- IMPLEMENTASI DEEP LEARNING MENGGUNAKAN CNN UNTUK SISTEM PENGENALAN WAJAHFaktor Exacta, 2021
- Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference2018
- Weed control under conservation agriculture in dryland smallholder farming systems of southern Africa. A reviewAgronomy for Sustainable Development, 2017
- Fixed point optimization of deep convolutional neural networks for object recognition2015
- PCA-SVM based CAD System for Focal Liver Lesions using B-Mode Ultrasound ImagesDefence Science Journal, 2013