Table 2.
Model parameters setting for experimentation.
Parameters [31] | vgg16 | vgg19 | EfficiebtnetB0 | ResNet50 | Hybrid Deep Learning Models |
---|---|---|---|---|---|
Image size | 150 × 150 × 3 | 150 × 150 × 3 | 150 × 150 × 3 | 150 × 150 × 3 | 150 × 150 × 3 |
Batch size | 64 | 64 | 64 | 64 | 64 |
Optimizer | Adam | Adam | Adam | Adam | Adam |
Learning rate | 3e-4 | 3e-4 | 3e-4 | 3e-4 | 3e-4 |
epochs | 25 | 25 | 25 | 25 | 25 |
1st Dense layer Activation Function(1000) | Relu activation | Relu activation | Relu activation | Relu activation | Relu activation |
2nd and 3rd Dense layer Activation Function(500,150) | Sigmoid activation | Sigmoid activation | Sigmoid activation | Sigmoid activation | Sigmoid activation |
Dropout | 0.5 | 0.5 | 0.5 | 0.5 | 0.5 |
Output Layer(2) | Categorical/Softmax | Categorical/Softmax | Categorical/Softmax | Categorical/Softmax | Categorical/Softmax |
Activation/Loss Function | Cross Entropy | Cross Entropy | Cross Entropy | Cross Entropy | Cross Entropy |