Table 2 Architecture of the proposed convolutional neural network
Block type | Ingredients | Size of feature maps |
|---|---|---|
Input | – | 256 × 256 ×1 |
Down layer (D1) | conv+res + drop+conv+batchnorm+max | 128 ×128 × 64 |
Down layer (D2) | conv+res + drop+conv+batchnorm+max | 64 ×64 × 128 |
Down layer (D3) | conv+res + drop+conv+batchnorm+max | 32 ×32× 256 |
Down layer (D4) | conv+res + drop+conv+batchnorm+max | 16 ×16 × 512 |
Bridge layer (B) | conv+res + conv | 16 ×16 × 1024 |
Upscaling layer (U1) | deconv+merge+conv+res + conv | 32 × 32 × 512 |
Upscaling layer (U2) | deconv+merge+conv+res + conv | 64 × 64 × 256 |
Upscaling layer (U3) | deconv+merge+conv+res + conv | 128 × 128 × 128 |
Upscaling layer (U4) | deconv+merge+conv+res + conv | 256 × 256 × 64 |
Output | conv | 256 × 256 ×1 |