Classification of Computed Tomography Images in Different Slice Positions Using Deep Learning

Table 2

Hyperparameters of training models.

	CNN architecture
	AlexNet	GoogLeNet
Training epochs	30
Snapshot interval	10
Validation interval	1
Random seed	None
Batch size of training	128	32
Batch size of validation	32	16
Solver type	Stochastic gradient descent (SGD)
Base learning rate	0.01
Policy	Step down
Step size (%)	33
Gamma	0.1