Skip to main content

Table 1 Structure of GoogLeNet network

From: Ancient mural classification methods based on a multichannel separable network

Layer type

Patch size/stride

Output size

Convolutional

7 × 7/2

112 × 112 × 64

Max pooling

3 × 3/2

56 × 56 × 64

Convolutional

3 × 3/1

56 × 56 × 192

Max pooling

3 × 3/2

28 × 28 × 192

Inception (3a)

 

28 × 28 × 256

Inception (3b)

 

28 × 28 × 480

Max pooling

3 × 3/2

14 × 14 × 480

Inception (4a)

 

14 × 14 × 512

Inception (4b)

 

14 × 14 × 512

Inception (4c)

 

14 × 14 × 512

Inception (4d)

 

14 × 14 × 528

Inception (4e)

 

14 × 14 × 832

Max pooling

3 × 3/2

7 × 7 × 832

Inception (5a)

 

7 × 7 × 832

Inception (5b)

 

7 × 7 × 1024

Avg pooling

7 × 7/2

1 × 1 × 1024

Dropout (40%)

 

1 × 1 × 1024

Softmax with loss