Table.2 Detailed network configuration of U-Net, U-Net GAN Generator, and U-Net GAN + SA Generator
From: A method for improving semantic segmentation using thermographic images in infants
Layers | Output size | U-Net | U-Net GAN + SA |
|---|---|---|---|
Input | 320 × 256 × 1 |  |  |
Convolution | 320 × 256 × 16 | 3 × 3, 16 d | 3 × 3, 16 d |
Downscale | 160 × 128 × 32 | 5 × 5, 32 d, CBR 3 × 3, 32 d, CBR | 1 × 1, 32 d 7 × 7, 32 d, SA 1 × 1, 32 d |
Downscale | 80 × 6464 | 5 × 5, 64 d, CBR 3 × 3, 64 d, CBR | 1 × 1, 64 d 7 × 7, 64 d, SA 1 × 1, 64 d |
Downscale | 40 × 32 × 128 | 5 × 5, 128 d, CBR 3 × 3, 128 d, CBR | 1 × 1, 128 d 7 × 7, 128 d, SA 1 × 1, 128 d |
Downscale | 20 × 16 × 256 | 5 × 5, 256 d, CBR 3 × 3, 256 d, CBR | 1 × 1, 256 d 7 × 7, 256 d, SA 1 × 1, 256 d |
Downscale | 10 × 8 × 512 | 5 × 5, 512 d, CBR 3 × 3, 512 d, CBR | 1 × 1, 512 d 7 × 7, 512 d, SA 1 × 1, 512 d |
Upscale | 20 × 16 × 256 | 5 × 5, 256 d, CBR 3 × 3, 256 d, CBR | 1 × 1, 256 d 7 × 7, 256 d, SA 1 × 1, 256 d |
Upscale | 40 × 32 × 128 | 5 × 5, 128 d, CBR 3 × 3, 128 d, CBR | 1 × 1, 128 d 7 × 7, 128 d, SA 1 × 1, 128 d |
Upscale | 80 × 64 × 64 | 5 × 5, 64 d, CBR 3 × 3, 64 d, CBR | 1 × 1, 64 d 7 × 7, 64 d, SA 1 × 1, 64 d |
Upscale | 160 × 128 × 32 | 5 × 5, 32 d, CBR 3 × 3, 32 d, CBR | 1 × 1, 32 d 7 × 7, 32 d, SA 1 × 1, 32 d |
Upscale | 320 × 256 × 16 | 5 × 5, 16 d, CBR 3 × 3, 16 d, CBR | 1 × . 1, 16 d 7 × 7, 16 d, SA 1 × 1, 16 d |
Convolution | 320 × 256 × 1 | 3 × 3, 1 d | 3 × 3, 1 d |