Table 3.
Performance comparison of the hyperparameter tuned models.
| Batch Size | Learning Rate | Epoch | Dropout Regularization | Optimizer | Test Accuracy | Val Accuracy | |
|---|---|---|---|---|---|---|---|
| Resnet-50 | 32 | 0.001 | 10 | 0.5 | ADAM | 97.71 % | 96.95 % |
| VGG-16 | 4 | 98.96 | 98.27 % | ||||
| VGG-19 | 5 | 99 % | 98.58 % | ||||
| MobileNetV2 | 9 | 96.99 % | 94 % | ||||
| AlexNet | 17 | 34.36 % | 34 % | ||||
| AlexNet | 3 | 0.001 | 17 | 99.13 % | 98.34 % |