Table 3.

The dimensions of the various layers of DenseNet-201 CNN.

Layer Label	Input Layer Dimension	Output Dimension
Input Layer		224 × 224 × 3
Convolution	112 × 112	Filter size = 7 × 7 Stride = 2 Padding = 3
pooling	56 × 56	Maximum Pooling = 3 × 3 Stride = 2
Dense Block 1	56 × 56	$\left[\begin{array}{cc}1& \times 1\\ 3& \times 3\end{array}\right]\times 6$
Transition Layer 1	56 × 56	1 × 1 convolution
	28 × 28	2 × 2 average pooling, stride =2
Dense Block 2	28 × 28	$\left[\begin{array}{cc}1& \times 1\\ 3& \times 3\end{array}\right]\times 12$
Transition Layer 2	28 × 28	1 × 1 convolution
	14 × 14	2 × 2 average pooling, stride =2
Dense Block 3	14 × 14	$\left[\begin{array}{cc}1& \times 1\\ 3& \times 3\end{array}\right]\times 48$
Transition Layer 3	14 × 14	1 × 1 convolution
	7 × 7	2 × 2 average pooling, stride =2
Dense Block 4	7 × 7	$\left[\begin{array}{cc}1& \times 1\\ 3& \times 3\end{array}\right]\times 32$
Pooling		Average Pooling= 7 × 7 Stride = 7
		1 × 1
FC Layer		1000