Comparative Analysis of Skin Cancer (Benign vs. Malignant) Detection Using Convolutional Neural Networks

Table 7

Layers and parameters of sequential model 2.

Type of layers	Outcome structure	Number of parameters
Conv-1 (2d)	(Nil, 222 × 222 × 20)	560
Pooling-1 (max)	(Nil, 111 × 111 × 20)	Null
Layer dropout-1	(Nil, 111 × 111 × 20)	Null
Conv-2 (2d)	(Nil, 109 × 109 × 20)	3620
Pooling-2 (max)	(Nil, 54 × 54 × 20)	Null
Layer dropout-2	(Nil, 54 × 54 × 20)	Null
Conv-3 (2d)	(Nil, 52 × 52 × 20)	3620
Pooling-3 (max)	(Nil, 26 × 26 × 20)	Null
Layer dropout-3	(Nil, 26 × 26 × 20)	Null
Layer flatten-1	(Nil, 13520)	Null
Layer dense-1	(Nil, 128)	1730688
Layer dense-2	(Nil, 128)	16512
Layer dense-3	(Nil, 1)	129
Total number of parameters: 1,755,129;
number of trainable parameters: 1,755,129;
number of nontrainable parameters: null