Application of Optimized Convolution Neural Network Model in Mural Segmentation

Table 1

Structure of MobileNetV2 network.

Input	Operator	t	c	n	s
224^2 × 3	conv2d	—	32	1	2
112^2 × 32	Bottleneck	1	16	1	1
112^2 × 16	Bottleneck	6	24	2	2
56^2 × 24	Bottleneck	6	32	3	2
28^2 × 32	Bottleneck	6	64	4	2
14^2 × 64	Bottleneck	6	96	3	1
14^2 × 96	Bottleneck	6	160	3	2
7^2 × 160	Bottleneck	6	320	1	1
7^2 × 320	conv2d 1 × 1	—	1280	1	1
7^2 × 1280	Avgpool 7 × 7	—	—	1	—
1 × 1 × 1280	conv2d 1 × 1	—	k	—