论文标题
使用深度学习，对设备友好的番石榴果实和叶子疾病检测
Device-friendly Guava fruit and leaf disease detection using deep learning
论文作者
论文摘要
这项工作使用水果和树叶的图像提出了一个基于学习的植物性诊断系统。已经使用了五个最先进的卷积神经网络（CNN）来实施该系统。迄今为止，模型的精度一直是此类应用程序的重点，并且尚未考虑模型适用于最终用户设备的模型。两种模型量化技术，例如Float16和动态范围量化已应用于五个最新的CNN架构。该研究表明，量化的Googlenet模型达到了0.143 MB的尺寸，精度为97％，这是考虑到尺寸标准的最佳候选模型。高效网络模型的尺寸达到4.2MB，精度为99％，这是考虑性能标准的最佳模型。源代码可在https://github.com/compostieai/guava-disease-detection上找到。
This work presents a deep learning-based plant disease diagnostic system using images of fruits and leaves. Five state-of-the-art convolutional neural networks (CNN) have been employed for implementing the system. Hitherto model accuracy has been the focus for such applications and model optimization has not been accounted for the model to be applicable to end-user devices. Two model quantization techniques such as float16 and dynamic range quantization have been applied to the five state-of-the-art CNN architectures. The study shows that the quantized GoogleNet model achieved the size of 0.143 MB with an accuracy of 97%, which is the best candidate model considering the size criterion. The EfficientNet model achieved the size of 4.2MB with an accuracy of 99%, which is the best model considering the performance criterion. The source codes are available at https://github.com/CompostieAI/Guava-disease-detection.
