Research Article
Cell Phenotype Classification Based on Joint of Texture Information and Multilayer Feature Extraction in DenseNet
Table 1
The structure details of four used DenseNet versions.
| Layers | Output size | DenseNet-121 | DenseNet-169 | DenseNet-201 | DenseNet-264 |
| Convolution | 112 × 112 | 7 × 7 conv., stride 2 | Pooling | 56 × 56 | 3 × 3 max pool, stride 2 | Dense block (1) | 56 × 56 | 1 × 1 conv 3 × 3 conv | ×6 | 1 × 1 conv 3 × 3 conv | ×6 | 1 × 1 conv 3 × 3 conv | ×6 | 1 × 1 conv 3 × 3 conv | x6 |
| Transition layer (1) | 56 × 56 | 1 × 1 conv | 28 × 28 | 2 × 2 average pool, stride 2 | Dense block (2) | 28 × 28 | 1 × 1 conv 3 × 3 conv | ×12 | 1 × 1 conv 3 × 3 conv | ×12 | 1 × 1 conv 3 × 3 conv | ×12 | 1 × 1 conv 3 × 3 conv | ×12 |
| Transition layer (2) | 28 × 28 | 1 × 1 conv | 14 × 14 | 2 × 2 average pool, stride 2 | Dense block (3) | 14 × 14 | 1 × 1 conv 3 × 3 conv | ×24 | 1 × 1 conv 3 × 3 conv | ×32 | 1 × 1 conv 3 × 3 conv | ×48 | 1 × 1 conv 3 × 3 conv | ×64 |
| Transition layer (3) | 14 × 14 | 1 × 1 conv | 7 × 7 | 2 × 2 average pool, stride 2 | Dense block (4) | 7 × 7 | 1 × 1 conv 3 × 3 conv | ×16 | 1 × 1 conv 3 × 3 conv | ×32 | 1 × 1 conv 3 × 3 conv | ×32 | 1 × 1 conv 3 × 3 conv | ×48 |
| Classification layer | 1 × 1 | 7 × 7 global average pool | | 1000D fully connected, softmax |
|
|