Skip to main content
. 2024 Mar 8;14:5753. doi: 10.1038/s41598-024-56323-8

Table 2.

Layered architecture of applied deep learning models.

Models Convolutional layer Pooling layer Dense Layer Other architectural features Parameters
VGG19 16 5 3 None 143 M
Inception V3 48 8 3 Batch normalization 23 M
EfficientNetB3 9 7 2 Squeeze-and-excitation 6.8 M
ResNet152V2 152 39 3 Residual connections 60.2 M
ResNet50V2 50 13 3 Residual connections 25.6 M
MobileNetV2 18 6 2 Inverted residual connections 3.5 M
Xception 36 11 3 Depthwise separable convolutions 22.9 M
Densenet169 169 5 3 Dense connections 14.3 M
EfficientNetB0 5 4 2 Squeeze-and-excitation 5.3 M
InceptionResNetV2 164 41 3 Batch normalization 55 M