Skip to main content
. 2024 Sep 12;14:21298. doi: 10.1038/s41598-024-72393-0

Table 2.

U-Net architecture. ‘Conv2D’ denotes a 2D convolutional layer; ‘ConvTransp2d’ denotes 2D transposed convolution; ‘BN’ denotes batch normalization; ‘f” is the number of features in the higher dimensional space, f = 64 for the saturation network, and f = 96 for the pressure buildup network.

Stage Layer type Input channels Output channels Kernel size Stride Concatenation
Contracting path
 1 Conv2d + BN + LeakyReLU f f 3 2
 2 Conv2d + BN + LeakyReLU f f 3 2
 3 Conv2d + BN + LeakyReLU f f 3 1
 4 Conv2d + BN + LeakyReLU f f 3 2
 5 Conv2d + BN + LeakyReLU f f 3 1
Expanding path
 6 ConvTransp2d + LeakyReLU f f 4 2 With stage 3
 7 ConvTransp2d + LeakyReLU 2f f 4 2 With stage 2
 8 ConvTransp2d + LeakyReLU 2f f 4 2 With stage 1
Output layer
 9 Conv2d 2f f 3 1 With input