Table 2.

Network architecture modified based on ResNet-50.

Layer Name	Output Size	Network 50-Layer
inputs	$64\times 64\times 3$
conv1	$64\times 64\times 64$	3$\times$3, 64, stride$1$
conv2.x	$32\times 32\times 256$	$\left[\begin{array}{c}1\times 1, 64\\ 3\times 3, 64\\ 1\times 1, 256\end{array}\right]\times 3,$ stride $2$
conv3.x	$16\times 16\times 512$	$\left[\begin{array}{c}1\times 1, 128\\ 3\times 3, 128\\ 1\times 1, 512\end{array}\right]\times 4,$ stride $2$
conv4.x	$8\times 8\times 1024$	$\left[\begin{array}{c}1\times 1, 256\\ 3\times 3, 256\\ 1\times 1, 1024\end{array}\right]\times 6,$ stride $2$
conv5.x	$8\times 8\times 2048$	$\left[\begin{array}{c}1\times 1, 512\\ 3\times 3, 512\\ 1\times 1, 2048\end{array}\right]\times 3,$ stride $1$
concat1	$8\times 8\times 3904$	(conv1, conv2.x, conv3.x, conv4.x, conv5.x)
conv6	$8\times 8\times i$	$1\times 1,i,stride1$
pool5	$1\times i$	reduce mean