Research Article
[Retracted] Analysis of Feature Extraction and Anti-Interference of Face Image under Deep Reconstruction Network Algorithm
Table 1
Basic parameters of ResNet-Inception network structure.
| | Structure | Parameter | Output image size |
| | Conv-1 | 3 3 | 147 147 32 | | Conv-2 | 3 3 | 145 145 32 | | Conv-3 | 3 3 | 145 145 64 | | Pool-1 | — | 73 73 64 | | Conv-4 | 1 1 | 73 73 80 | | Conv-5 | 3 3 | 70 70 190 | | Conv-6 | 3 3 | 33 33 256 | | ResNet-Inception-1 | 5 | 33 33 256 | | Reduction-1 | — | 16 16 512 | | ResNet-Inception-2 | 10 | 16 16 512 | | Reduction-2 | — | 8 8 1024 | | ResNet-Inception-3 | 5 | 8 8 1024 | | Pool-2 | — | 1792 | | Dropout | x | 1792 |
|
|
