Table 3.

The network backbone of the AI-100 algorithm.

Layer	Output size	Architecture
Convolution	112 × 112	7 × 7 conv, stride 2
Pooling	56 × 56	3 × 3 max pooling, stride 2
Dense Block (1)	56 × 56
Transition Layer (1)	56 × 56	1 × 1 conv
	28 × 28	2 × 2 average pool, stride 2
Dense Block (2)	28 × 28
Transition Layer (2)	28 × 28	1 × 1 conv
	14 × 14	2 × 2 average pool, stride 2
Dense Block (3)	14 × 14
Transition Layer (3)	14 × 14	1 × 1 conv
	7 × 7	2 × 2 average pool, stride 2
Dense Block (4)	7 × 7
Classification Layer	1 × 1	7 × 7 global average pool
		1000D fully−connected, softmax