Fig. 6From: Recognition of eye diseases based on deep neural networks for transfer learning and improved D-S evidence theoryConfusion matrices. The top left, top right and bottom figures are the confusion matrices of ResNet50, ResNet101, and the fusion model, respectively. The test accuracy of the fused model is 92.37%, which is an improvement of 0.46% on ResNet50 and 2.3% on ResNet101Back to article page