Deep Learning-Aided Automated Pneumonia Detection and Classification Using CXR Scans

Table 4

Training properties.

S. no.	Training parameters	CNN	Xception	VGG19	VGG16
1.	Learning rate	0.001	0.001	0.001	0.001
2.	Batch size	64	64	64	64
3.	Brightness range	[0.25, 1]	[0.25, 1]	[0.25, 1]	[0.25, 1]
4.	Height and width shift range	0.1	0.1	0.1	0.1
5.	Rotation range	10	10	10	10
6.	Share range	0.2	0.2	0.2	0.2
7.	Zoom range	[0.8, 1.2]	[0.8, 1.2]	[0.8, 1.2]	[0.8, 1.2]
5.	Input shape	[224, 224, 3]	[224, 224, 3]	[224, 224, 3]	[224, 224, 3]
6.	Loss function	Categorical cross-entropy	Categorical cross-entropy	Categorical cross-entropy	Categorical cross-entropy
7.	Rescale	1/225	1/225	1/225	1/225
8.	Epoch	15	15	15	15
9.	Training set	80%, 70%, and 60%	80%, 70%, and 60%	80%, 70%, and 60%	80%, 70%, and 60%