Table 4.

Detailed configuration of ResNet50, ResNet101, ResNet152, AlexNet, and VGG16. Convolution and pooling layers of ResNet block 2, 3, 4, and 5 were performed with a stride of 2.

Block	Output Size	ResNet50	ResNet101	ResNet152	VGG16	Output Size	AlexNet
1	$112$ × 112	7 × 7, 64, stride 2	7 × 7, 64, stride 2	7 × 7, 64, stride 2	$\left[3\times 3, 64 \right]\times 2$	$55$ × 55	11 × 11, 96, stride 4
2	$56$ × 56	3 × 3 max-pooling, stride 2	3 × 3 max-pooling, stride 2	3 × 3 max-pooling, stride 2	2 × 2 max-pooling, stride 2	$27$ × 27	3 × 3 max-pooling, stride 2
		$\left[ \begin{array}{c}1\times 1, 64\\ 3\times 3, 64\\ 1\times 1, 256\end{array} \right]\times 3$	$\left[ \begin{array}{c}1\times 1, 64\\ 3\times 3, 64\\ 1\times 1, 256\end{array} \right]\times 3$	$\left[ \begin{array}{c}1\times 1, 64\\ 3\times 3, 64\\ 1\times 1, 256\end{array} \right]\times 3$	$\left[ 3\times 3, 128 \right]\times 2$		5 × 5, 256, stride 1
3	$28$ × 28	$\left[ \begin{array}{c}1\times 1, 128\\ 3\times 3, 128\\ 1\times 1, 512\end{array} \right]\times 4$	$\left[ \begin{array}{c}1\times 1, 128\\ 3\times 3, 128\\ 1\times 1, 512\end{array} \right]\times 4$	$\left[ \begin{array}{c}1\times 1, 128\\ 3\times 3, 128\\ 1\times 1, 512\end{array} \right]\times 8$	2 × 2 max-pooling, stride 2	$13$ × 13	3 × 3 max-pooling, stride 2
					$\left[ 3\times 3, 256 \right]\times 3$		$\left[ \begin{array}{c}3\times 3, 384\\ 3\times 3, 384\\ 3\times 3, 256\end{array} \right]$, stride 1
4	$14$ × 14	$\left[ \begin{array}{c}1\times 1, 256\\ 3\times 3, 256\\ 1\times 1, 1024\end{array} \right]\times 6$	$\left[ \begin{array}{c}1\times 1, 256\\ 3\times 3, 256\\ 1\times 1, 1024\end{array} \right]\times 23$	$\left[ \begin{array}{c}1\times 1, 256\\ 3\times 3, 256\\ 1\times 1, 1024\end{array} \right]\times 36$	2 × 2 max-pooling, stride 2	$1$ × 1	3 × 3 max-pooling, stride 2
							average pooling
					$\left[ 3\times 3, 512 \right]\times 3$		[4096 fully connected, $\mathrm{ReLU}] \times 2$
							n-class fully connected, softmax
5	$7$ × 7	$\left[ \begin{array}{c}1\times 1, 512\\ 3\times 3, 512\\ 1\times 1, 2048\end{array} \right]\times 3$	$\left[ \begin{array}{c}1\times 1, 512\\ 3\times 3, 512\\ 1\times 1, 2048\end{array} \right]\times 3$	$\left[ \begin{array}{c}1\times 1, 512\\ 3\times 3, 512\\ 1\times 1, 2048\end{array} \right]\times 3$	$\left[ 3\times 3, 512 \right]\times 3$
6	$1$ × 1	average-pooling			2 × 2 max-pooling, stride 2
					[4096 fully connected, ReLU] $\times 2$
		n-class fully connected, softmax			n-class fully connected, softmax