network layer

Number of output channels

Structural parameters

quantity of participants

Conv1

112 × 112

7 × 7.64, stride2

9536

Maxplool

56 × 56

3 × 3 maxpool, stride2

0

Conv2

56 × 56

$\left[\begin{array}{c}1\times 1.64\\ 3\times 3.64\\ 1\times 1.256\end{array}\right]\times 3$

215,808

Conv3

28 × 28

$\left[\begin{array}{c}1\times 1.128\\ 3\times 3.128\\ 1\times 1.512\end{array}\right]\times 4$

1,219,584

Conv4

14 × 14

$\left[\begin{array}{c}1\times 1.256\\ 3\times 3.256\\ 1\times 1.1024\end{array}\right]\times 6$

7,098,368

Downsample

7 × 7

2 × 2.512, stride2

2,097,664

Conv5

7 × 7

$\left[\begin{array}{c}1\times 1.2048\\ 7\times 7.2048\\ 1\times 1.512\end{array}\right]\times 3$

8,185,728

Avapool

7 × 7

7 × 7 average pool, 512

0

FC

5

1 × 1.512

2565

Total model parameters

18,829,253