Table 1 Optimized hyperparameters for CNN models.
From: Enhancing lane detection in autonomous vehicles with multi-armed bandit ensemble learning
Hyperparameter | ENet | PINet | ResNet-50 | ResNet-101 | SqueezeNet | VGG16Net |
|---|---|---|---|---|---|---|
Learning Rate | 0.001 | 0.0005 | 0.0001 | 0.0001 | 0.001 | 0.0005 |
Batch Size | 16 | 32 | 64 | 32 | 16 | 32 |
Optimizer | Adam | AdamW | SGD | SGD | Adam | AdamW |
Dropout Rate | 0.3 | 0.4 | 0.5 | 0.4 | 0.3 | 0.5 |
Weight Initialization | Xavier | Kaiming | Kaiming | Xavier | Xavier | He Normal |
Data Augmentation | Yes | Yes | Yes | Yes | Yes | Yes |
Regularization (L2) | 0.0001 | 0.0005 | 0.001 | 0.0001 | 0.0001 | 0.0005 |
