Image Classification of Cassava Leaf Disease Based on Residual Network

摘要

For the low efficiency of the traditional visual inspection and diagnosis method for cassava leaf disease detection by agricultural experts, this paper proposes an image classification method of cassava leaf disease based on residual network (ResNet). Based on the residual network model, the idea of attention mechanism is applied to the network model, which makes the feature extraction area focus on the feature of cassava leaf disease.