Wen Xiaojie, Zeng Minghao, Chen Jing, Maimaiti Muzaipaer, Liu Qi
Key Laboratory of the Pest Monitoring and Safety Control of Crops and Forests of the Xinjiang Uygur Autonomous Region, College of Agronomy, Xinjiang Agricultural University, Urumqi 830052, China.
Key Laboratory of Prevention and Control of Invasive Alien Species in Agriculture & Forestry of the North-Western Desert Oasis, Ministry of Agriculture and Rural Affairs, Urumqi 830052, China.
Life (Basel). 2023 Oct 26;13(11):2125. doi: 10.3390/life13112125.
Wheat leaf diseases are considered to be the foremost threat to wheat yield. In the realm of crop disease detection, convolutional neural networks (CNNs) have emerged as important tools. The training strategy and the initial learning rate are key factors that impact the performance and training speed of the model in CNNs. This study employed six training strategies, including Adam, SGD, Adam + StepLR, SGD + StepLR, Warm-up + Cosine annealing + SGD, Warm-up + Cosine, and annealing + Adam, with three initial learning rates (0.05, 0.01, and 0.001). Using the wheat stripe rust, wheat powdery mildew, and healthy wheat datasets, five lightweight CNN models, namely MobileNetV3, ShuffleNetV2, GhostNet, MnasNet, and EfficientNetV2, were evaluated. The results showed that upon combining the SGD + StepLR with the initial learning rate of 0.001, the MnasNet obtained the highest recognition accuracy of 98.65%. The accuracy increased by 1.1% as compared to that obtained with the training strategy with a fixed learning rate, and the size of the parameters was only 19.09 M. The above results indicated that the MnasNet was appropriate for porting to the mobile terminal and efficient for automatically identifying wheat leaf diseases.
小麦叶部病害被认为是对小麦产量的首要威胁。在作物病害检测领域，卷积神经网络（CNN）已成为重要工具。训练策略和初始学习率是影响CNN模型性能和训练速度的关键因素。本研究采用了六种训练策略，包括Adam、SGD、Adam + StepLR、SGD + StepLR、Warm-up + Cosine退火 + SGD、Warm-up + Cosine退火 + Adam，并设置了三个初始学习率（0.05、0.01和0.001）。使用小麦条锈病、小麦白粉病和健康小麦数据集，对五个轻量级CNN模型，即MobileNetV3、ShuffleNetV2、GhostNet、MnasNet和EfficientNetV2进行了评估。结果表明，将SGD + StepLR与初始学习率0.001相结合时，MnasNet获得了最高识别准确率98.65%。与固定学习率的训练策略相比，准确率提高了1.1%，参数大小仅为19.09 M。上述结果表明，MnasNet适合移植到移动终端，且在自动识别小麦叶部病害方面效率较高。
