Table 2 CNN Model Architecture.
From: A deep ensemble learning approach for squamous cell classification in cervical cancer
Operation | Data Dimensions | Weights | Details |
|---|---|---|---|
Input | 64x64x3 | Â | Input Layer |
Conv2D | 64x64x3 \(\rightarrow\) 62x62x16 | 448 | Convolution |
Conv2D | 62x62x16 \(\rightarrow\) 62x62x16 | 448 | Convolution |
Conv2D | 62x62x16 \(\rightarrow\) 60x60x32 | 4640 | Convolution |
Max Pooling | 60x60x32 \(\rightarrow\) 30x30x32 | 0 | Max Pooling |
Conv2D | 30x30x32 \(\rightarrow\) 28x28x64 | 18496 | Convolution |
Max Pooling | 28x28x64 \(\rightarrow\) 14x14x64 | 0 | Max Pooling |
Conv2D | 14x14x646 \(\rightarrow\) 12x12x128 | 73856 | Convolution |
Max Pooling | 12x12x128 \(\rightarrow\) 6x6x128 | 0 | Max Pooling |
Dropout | 6x6x128 \(\rightarrow\) 6x6x128 | 0 | Dropout |
Flatten | 6x6x128 \(\rightarrow\) 4608 | 0 | Flatten |
Dense | 4608 \(\rightarrow\) 64 | 294976 | Dense |
Dropout | 64 \(\rightarrow\) 64 | 0 | Dropout |
Dense | 64 \(\rightarrow\) 5 | 325 | Dense |
