Training strategies and evaluation indicators of the classification framework
The training strategies and hyper-parameters of the classification framework were as follows. We adopted a knowledge distillation method (Fig. 7) to train the CNNCF as a student network with one stage I block and one stage II block, each of which contained two ResBlock-A. Four teacher networks (the hyper-parameters are provided in Supplementary Table 21) with the proposed blocks were trained on the train-val part of each sub-data set using a 5-fold cross-validation method. All networks were initialized using the Xavier initialization method. The initial learning rate was 0.01, and the optimization function was the SGD. The CNNCF was trained using the image data and the label, as well as the fused output of the teacher networks. The comparison of RT-PCR test results using throat specimen and the CNNCF results were provided in Supplementary Table 22. Supplementary Fig. 20 shows the details of the knowledge distillation method. The definitions and details of the five evaluation indicators used in this study were given in Supplementary Note 2.
Fig. 7 Knowledge distillation consisting of multiple teacher networks and a target student network.
The knowledge is transferred from the teacher networks to the student network using a loss function.