Table 1 Hyperparameter for fusion model.
From: Explainable fusion of EfficientNetB0 and ResNet50 for liver fibrosis staging in ultrasound imaging
Hyperparameter | Value |
|---|---|
Input image size | 224 × 224 × 3 |
Batch size | 64 |
Maximum epochs | 30 |
Optimizer | Adam |
Learning rate | 1 × 10⁻4 |
Loss function | Sparse categorical cross-entropy |
Class weighting | compute_class_weight |
Final classifier | Softmax (5 classes: F0–F4) |
Early stopping | Patience = 5 |
