Skip to main content

Table 4 Models parameters where N1: No. convolution layers; N2: No. convolution kernels; N3: No. pooling layers; N4: No. Batch normalization; N5: No.fully connected layer: N6: Recognition Time; GAP: Global Average Pooling

From: Towards unbiased skin cancer classification using deep feature fusion

Network

N1

N2

N3

N4

N5

N6

EfficientNet [42]

65

3328992

17 (GAP)

49

1

15 ms

MobilNet [37]

15

4253864

1 (GAP)

27

0

10 ms

Darknet [43]

18

19810176

6 (Max pooling)

18

1

25 ms

Proposed SWNet

33

9368192

1 (GAP)

37

3

20 ms

Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us