Skip to main content

Table 1 The details of the generative network G

From: Compression artifacts reduction by improved generative adversarial networks

Generative network G

Input: x, size = 64 × 64

[Conv 1]

Conv (3, 3, 64), stride = 2, padding = 1; LeakyReLU;

[Conv 2]

Conv (4, 4, 128), stride = 2, padding = 1; BatchNorm; LeakyReLU;

[Conv 3]

Conv (4, 4, 256), stride = 2, padding = 1; BatchNorm; LeakyReLU;

[Conv 4]

Conv (4, 4, 512), stride = 2, padding = 1; BatchNorm; ReLU;

[DeConv1]

DeConv (4, 4, 256), stride = 2, padding = 1; BatchNorm; ReLU;

[DeConv2]

DeConv (4, 4, 128), stride = 2, padding = 1; BatchNorm; ReLU;

[DeConv3]

DeConv (4, 4, 64), stride = 2, padding = 1; BatchNorm; ReLU;

[DeConv4]

DeConv (4, 4, 3), stride = 2, padding = 1

Output: G(x), size = 64 × 64