Research Article
Highly Robust Synthetic Aperture Radar Target Recognition Method Based on Simulation Data Training
Table 3
Architectures of ResNets. Downsampling is performed by the first conv layer in each stage, with a stride of 2.
| Layer name | ResNet-18 | ResNet-34 | ResNet-50 | ResNet-101 | ResNet-152 |
| Stage 0 | 7 × 7, 64, stride 2 |
| Stage 1 | Max pool, 3 × 3, stride 2 | | | | | |
| Stage 2 | | | | | |
| Stage 3 | | | | | |
| Stage 4 | | | | | |
| Classification | Global average pool | 3-d FC, softmax |
|
|