Table 10 Represents layer details and parameter counts for each EfficientNetB2.
From: Attention-Enhanced CNNs and transformers for accurate monkeypox and skin disease detection
Layer (type) | Output Shape | Param # |
|---|---|---|
input_layer_1 (InputLayer) | (None, 224, 224, 3) | 0 |
efficientnetb2 (Functional) | (None, 7, 7, 1408) | 7,768,569 |
coordinate_attention (CoordAtt) | (None, 7, 7, 1408) | 188,716 |
conv2d_3 (Conv2D) | (None, 7, 7, 512) | 6,488,576 |
global_average_pooling2d_2 | (None, 512) | 0 |
dense (Dense) | (None, 256) | 131,328 |
dense_1 (Dense) | (None, 6) | 1,542 |
Total Parameters | 14,578,731 | |
Trainable Parameters | 6,810,162 | |
Non-Trainable Parameters | 7,768,569 |
