Table 2.

The hyper-parameters of the best-trained models (e.g., ResNet34 and HRNet) used in the proposed COVID-CheXNet system

ResNet34 model		HRNet model
Hyper-parameters	Values	Hyper-parameters	Values
Optimizer	Adam	Optimizer	SGD
Momentum	0.95	Momentum	0.9
Weight decay	0.0005	Weight decay	0.0005
Batch size	100	Batch size	100
Dropout	0.5	Dropout	0.5
Learning rate	0.01	Learning rate	0.01
Factor	0.7	Factor	0.9
Patience	5	Patience	5
Total no. of epochs	10	Total no. of epochs	20