Table 2.

Comparison of different networks on 7 Rhinolophus species classifications. Params denote the number of parameters of the model; FLOPs is understood as the amount of computation and can be used to measure the complexity of the model, and the unit of throughput is images. F1 score is the ratio of the product of twice the precision and recall to the sum of precision and recall

	Params	FLOPs	Accuracy	F1 Score
AlexNet	61.10 M	715.54 M	82.26%	82.54%
ViT-B/16	86.56M	17.56G	83.28%	83.82%
ResNet50	25.56 M	4.12G	89.08%	89.52%
MobileNetV2	3.50 M	320.24 M	90.78%	90.92%
VGG16	138.37 M	31.01G	91.13%	91.17%
VGG16-CBAM	31.35 M	20.47G	92.15%	93.09%