Table 2.

Detailed architectures for residual network (ResNet).

Stage of Convolution	ResNet18	ResNet34	ResNet50	ResNet101	ResNet152	ResNet1000
C1	7 × 7, 64, stride 2 3 × 3 max pooling, stride 2
C2	$\left[\begin{array}{c}3\times 3, 64\\ 3\times 3, 64\end{array}\right]\times 2$	$\left[\begin{array}{c}3\times 3, 64\\ 3\times 3, 64\end{array}\right]\times 3$	$\left[\begin{array}{c}1\times 1, 64\\ 3\times 3, 64\\ 1\times 1, 256\end{array}\right]\times 3$	$\left[\begin{array}{c}1\times 1, 64\\ 3\times 3, 64\\ 1\times 1, 256\end{array}\right]\times 3$	$\left[\begin{array}{c}1\times 1, 64\\ 3\times 3, 64\\ 1\times 1, 256\end{array}\right]\times 3$	$\left[\begin{array}{c}1\times 1, 64\\ 3\times 3, 64\\ 1\times 1, 256\end{array}\right]\times 248$
C3	$\left[\begin{array}{c}3\times 3, 128\\ 3\times 3, 128\end{array}\right]\times 2$	$\left[\begin{array}{c}3\times 3, 128\\ 3\times 3, 128\end{array}\right]\times 4$	$\left[\begin{array}{c}1\times 1, 128\\ 3\times 3, 128\\ 1\times 1, 512\end{array}\right]\times 4$	$\left[\begin{array}{c}1\times 1, 128\\ 3\times 3, 128\\ 1\times 1, 512\end{array}\right]\times 4$	$\left[\begin{array}{c}1\times 1, 128\\ 3\times 3, 128\\ 1\times 1, 512\end{array}\right]\times 22$	$\left[\begin{array}{c}1\times 1, 128\\ 3\times 3, 128\\ 1\times 1, 512\end{array}\right]\times 248$
C4	$\left[\begin{array}{c}3\times 3, 256\\ 3\times 3, 256\end{array}\right]\times 2$	$\left[\begin{array}{c}3\times 3, 256\\ 3\times 3, 256\end{array}\right]\times 6$	$\left[\begin{array}{c}1\times 1, 256\\ 3\times 3, 256\\ 1\times 1, 1024\end{array}\right]\times 6$	$\left[\begin{array}{c}1\times 1, 256\\ 3\times 3, 256\\ 1\times 1, 1024\end{array}\right]\times 23$	$\left[\begin{array}{c}1\times 1, 256\\ 3\times 3, 256\\ 1\times 1, 1024\end{array}\right]\times 22$	$\left[\begin{array}{c}1\times 1, 256\\ 3\times 3, 256\\ 1\times 1, 1024\end{array}\right]\times 247$
C5	$\left[\begin{array}{c}3\times 3, 512\\ 3\times 3, 512\end{array}\right]\times 2$	$\left[\begin{array}{c}3\times 3, 512\\ 3\times 3, 512\end{array}\right]\times 3$	$\left[\begin{array}{c}1\times 1, 512\\ 3\times 3, 512\\ 1\times 1, 2048\end{array}\right]\times 3$			$\left[\begin{array}{c}1\times 1, 512\\ 3\times 3, 512\\ 1\times 1, 2048\end{array}\right]\times 247$
	Average pooling, 1000-d FC, softmax

Note: ResNet18-ResNet1000 are residual network with 18–1000 layers of convolution; C1–C5 are convolutional stages 1 to 5 in the ResNet; and FC is fully-connected.