[Retracted] Research on Face Recognition Classification Based on Improved GoogleNet

Table1

GoogleLenet network architecture.

Type	Size/stride	Output	Depth	Pooling
Conv	7 × 7/2	112 × 112 × 64	1
Max pool	3 × 3/2	56 × 56 × 64	0
Conv	3 × 3/1	56 × 56 × 192	2
Max pool	3 × 3/2	28 × 28 × 192	0
Inception (3a)		28 × 28 × 256	2	32
Inception (3b)		28 × 28 × 480	2	64
Max pool	3 × 3/2	14 × 14 × 480	0
Inception (4a)		14 × 14 × 512	2	64
Inception (4b)		14 × 14 × 512	2	64
Inception (4c)		14 × 14 × 512	2	64
Inception (4d)		14 × 14 × 528	2	64
Inception (4e)		14 × 14 × 832	2	128
Max pool	3 × 3/2	7 × 7 × 832	0
Inception (5a)		7 × 7 × 832	2	128
Inception (5b)		7 × 7 × 1024	2	128
Avg pool	7 × 7/1	1 × 1 × 1024	0
Dropout 40%		1 × 1 × 1024	0
Fc		1 × 1 × 1000	1
Softmax		1 × 1 × 1000	0