Research on Classification of COVID-19 Chest X-Ray Image Modal Feature Fusion Based on Deep Learning

Table 3

Summary of the pretrained convolutional neural network architecture used in this study.

Pretrained model		Input size	Layers	Size (MB)	Parameters (M)
ResNet50		224 × 224	50	98	23.52
ResNet152		224 × 224	152	232	60.42
Xception		299 × 299	126	88	22.91
InceptionResNetV2		299 × 299	572	215	55.87
Model 1	ResNet50	224 × 224	50	98	23.52
	Xception	299 × 299	126	88	22.91
	InceptionV3	224 × 224	159	92	23.85
Model 2	DesenNet201	224 × 224	201	80	20.24
	VGG19	224 × 224	19	549	143.67
	Xception	299 × 299	126	88	22.91
	ResNet152	224 × 224	152	232	60.42
	InceptionResNetV2	299 × 299	572	215	55.87