Table 8.
Architecture of hybrid (CNN+RNN) model.
| Layer (Type) | Output Shape | Parameters |
|---|---|---|
| conv2d (Conv2D) | (None, 62, 62, 32) | 896 |
| max_pooling2d (MaxPooling2D) | (None, 31, 31, 32) | 0 |
| conv2d_1 (Conv2D) | (None, 29, 29, 64) | 18,496 |
| max_pooling2d_1 (MaxPooling2D) | (None, 14, 14, 64) | 0 |
| conv2d_2 (Conv2D) | (None, 12, 12, 128) | 73,856 |
| max_pooling2d_2 (MaxPooling2D) | (None, 6, 6, 128) | 0 |
| conv2d_3 (Conv2D) | (None, 5, 5, 256) | 131,328 |
| max_pooling2d_3 (MaxPooling2D) | (None, 5, 5, 256) | 0 |
| conv2d_4 (Conv2D) | (None, 4, 4, 512) | 524,800 |
| max_pooling2d_4 (MaxPooling2D) | (None, 4, 4, 512) | 0 |
| flatten (Flatten) | (None, 8192) | 0 |
| reshape (Reshape) | (None, 1, 8192) | 0 |
| lstm (LSTM) | (None, 128) | 4,260,352 |
| dense (Dense) | (None, 1) | 129 |