Skip to main content

Table 6 The results of different K value

From: Automated fundus ultrasound image classification based on siamese convolutional neural networks with multi-attention

K

Accuracy

Precision

Recall

F1

2

0.940

0.941

0.940

0.939

4

0.940

0.941

0.940

0.939

8

0.940

0.941

0.940

0.939

10

0.940

0.941

0.940

0.939

20

0.918

0.920

0.920

0.920

40

0.918

0.920

0.920

0.920

80

0.918

0.920

0.920

0.920

100

0.918

0.920

0.920

0.920

200

0.918

0.920

0.920

0.920