Table 5. Classification models with Fine-tuned Layers.

Parameters	1-layer unfreeze			2-layers unfreeze
	VGG16	MobileNetV2	ResNet50	VGG16	MobileNetV2	ResNet50
Execution time (Seconds)	3,742	1,337	3,012	4,020	1,398	3,128
Training accuracy (%)	99.8	99.6	100	100	99.8	100
Validation accuracy (%)	97.9	96.6	99.9	99.1	96.1	99.8
Testing accuracy (%)	96.12	91.49	98.08	97.09	92.25	97.56
Precision	0.97	0.92	0.98	0.97	0.93	0.98
Recall	0.96	0.92	0.98	0.97	0.93	0.98
F1-Score	0.96	0.91	0.98	0.97	0.92	0.98