Table 1.

ResNet-18 Architecture.

Layer Name	Output Size	ResNet-18
conv1	$112\times 112\times 64$	$7\times 7$, 64, stride 2
conv2_x	$56\times 56\times 64$	$3\times 3$ max pool, stride 2
		$\left[\begin{array}{c}\hfill 3\times 3,64\\ \hfill 3\times 3,64\end{array}\right]$× 2
conv3_x	$28\times 28\times 128$	$\left[\begin{array}{c}\hfill 3\times 3,128\\ \hfill 3\times 3,128\end{array}\right]$× 2
conv4_x	$14\times 14\times 256$	$\left[\begin{array}{c}\hfill 3\times 3,256\\ \hfill 3\times 3,256\end{array}\right]$× 2
conv5_x	$7\times 7\times 512$	$\left[\begin{array}{c}\hfill 3\times 3,512\\ \hfill 3\times 3,512\end{array}\right]$× 2
average pool	$1\times 1\times 512$	$7\times 7$ average pool
fully connected	1000	$512\times 1000$ fully connections
softmax	1000