Skip to main content

Table 2 Residual-Network Architecture: Input Dimension & Number of Kernels

From: Atrial fibrillation classification based on convolutional neural networks

Layer/Model

Residual 1–1

Residual 1–2

Residual 1–3

Residual 1–4

Residual 1–5

Residual 1–6

Convolution

(1, 1000, 64)a

(1, 1000, 32)

(1, 1000, 16)

(1, 1000, 8)

(1, 1000, 4)

(1, 1000, 2)

Pooling

(1, 500, 64)

(1, 500, 32)

(1, 500, 16)

(1, 500, 8)

(1, 500, 4)

(1, 500, 2)

Residual Block

(1, 500, 64)

(1, 500, 32)

(1, 500, 16)

(1, 500, 8)

(1, 500, 4)

(1, 500, 2)

Residual Block

(1, 500, 64)

(1, 500, 32)

(1, 500, 16)

(1, 500, 8)

(1, 500, 4)

(1, 500, 2)

Residual Block

(1, 250, 128)

(1, 250, 64)

(1, 250, 32)

(1, 250, 16)

(1, 250, 8)

(1, 250, 4)

Residual Block

(1, 250, 128)

(1, 250, 64)

(1, 250, 32)

(1, 250, 16)

(1, 250, 8)

(1, 250, 4)

Residual Block

(1, 125, 256)

(1, 125, 128)

(1, 125, 64)

(1, 125, 32)

(1, 125, 16)

(1, 125, 8)

Residual Block

(1, 125, 256)

(1, 125, 128)

(1, 125, 64)

(1, 125, 32)

(1, 125, 16)

(1, 125, 8)

Residual Block

(1, 63, 512)

(1, 63, 256)

(1, 63, 128)

(1, 63, 64)

(1, 63, 32)

(1, 63, 16)

Residual Block

(1, 63, 512)

(1, 63, 256)

(1, 63, 128)

(1, 63, 64)

(1, 63, 32)

(1, 63, 16)

Pooling

(1, 1, 512)

(1, 1, 256)

(1, 1, 128)

(1, 1, 64)

(1, 1, 32)

(1, 1, 16)

Output

(2)

(2)

(2)

(2)

(2)

(2)

Layer/Model

Residual 2–1

Residual 2–2

Residual 2–3

Residual 2–4

Residual 2–5

Residual 2–6

Convolution

(1, 1000, 64)

(1, 1000, 32)

(1, 1000, 16)

(1, 1000, 8)

(1, 1000, 4)

(1, 1000, 2)

Pooling

(1, 500, 64)

(1, 500, 32)

(1, 500, 16)

(1, 500, 8)

(1, 500, 4)

(1, 500, 2)

Residual Block

(1, 500, 64)

(1, 500, 32)

(1, 500, 16)

(1, 500, 8)

(1, 500, 4)

(1, 500, 2)

Residual Block

(1, 500, 64)

(1, 500, 32)

(1, 500, 16)

(1, 500, 8)

(1, 500, 4)

(1, 500, 2)

Residual Block

(1, 250, 128)

(1, 250, 64)

(1, 250, 32)

(1, 250, 16)

(1, 250, 8)

(1, 250, 4)

Residual Block

(1, 250, 128)

(1, 250, 64)

(1, 250, 32)

(1, 250, 16)

(1, 250, 8)

(1, 250, 4)

Residual Block

(1, 125, 256)

(1, 125, 128)

(1, 125, 64)

(1, 125, 32)

(1, 125, 16)

(1, 125, 8)

Residual Block

(1, 125, 256)

(1, 125, 128)

(1, 125, 64)

(1, 125, 32)

(1, 125, 16)

(1, 125, 8)

Pooling

(1, 1, 256)

(1, 1, 128)

(1, 1, 64)

(1, 1, 32)

(1, 1, 16)

(1, 1, 8)

Output

(2)

(2)

(2)

(2)

(2)

(2)

Layer/Model

Residual 3–1

Residual 3–2

Residual 3–3

Residual 3–4

Residual 3–5

Residual 3–6

Convolution

(1, 1000, 64)

(1, 1000, 32)

(1, 1000, 16)

(1, 1000, 8)

(1, 1000, 4)

(1, 1000, 2)

Pooling

(1, 500, 64)

(1, 500, 32)

(1, 500, 16)

(1, 500, 8)

(1, 500, 4)

(1, 500, 2)

Residual Block

(1, 500, 64)

(1, 500, 32)

(1, 500, 16)

(1, 500, 8)

(1, 500, 4)

(1, 500, 2)

Residual Block

(1, 500, 64)

(1, 500, 32)

(1, 500, 16)

(1, 500, 8)

(1, 500, 4)

(1, 500, 2)

Residual Block

(1, 250, 128)

(1, 250, 64)

(1, 250, 32)

(1, 250, 16)

(1, 250, 8)

(1, 250, 4)

Residual Block

(1, 250, 128)

(1, 250, 64)

(1, 250, 32)

(1, 250, 16)

(1, 250, 8)

(1, 250, 4)

Pooling

(1, 1, 128)

(1, 1, 64)

(1, 1, 32)

(1, 1, 16)

(1, 1, 8)

(1, 1, 4)

Output

(2)

(2)

(2)

(2)

(2)

(2)

Layer/Model

Residual 4–1

Residual 4–2

Residual 4–3

Residual 4–4

Residual 4–5

Residual 4–6

Convolution

(1, 1000, 64)

(1, 1000, 32)

(1, 1000, 16)

(1, 1000, 8)

(1, 1000, 4)

(1, 1000, 2)

Pooling

(1, 500, 64)

(1, 500, 32)

(1, 500, 16)

(1, 500, 8)

(1, 500, 4)

(1, 500, 2)

Residual Block

(1, 500, 64)

(1, 500, 32)

(1, 500, 16)

(1, 500, 8)

(1, 500, 4)

(1, 500, 2)

Residual Block

(1, 500, 64)

(1, 500, 32)

(1, 500, 16)

(1, 500, 8)

(1, 500, 4)

(1, 500, 2)

Pooling

(1, 1, 64)

(1, 1, 32)

(1, 1, 16)

(1, 1, 8)

(1, 1, 4)

(1, 1, 2)

Output

(2)

(2)

(2)

(2)

(2)

(2)

  1. a(1, 1000, 64), Input Dimension 1, Input Dimension 2, Number of Kernels