Table 4 Comparison of MIFNet performance with different number of widths.

From: A novel benign and malignant classification model for lung nodules based on multi-scale interleaved fusion integrated network

Depth

Params. (M)

Size (MB)

FLOPs (×108)

Acc (%)

10

0.043

0.164

0.142

93.59

22

0.218

0.831

0.722

94.33

28

0.425

1.62

1.405

94.08

34

0.825

3.148

2.721

94.64

40

1.613

6.152

5.303

94.08

46

3.15

12.016

10.418

94.94

Back to article page