Table 3 Hyperparameter and values.

From: Brain tumor segmentation using multi-scale attention U-Net with EfficientNetB4 encoder for enhanced MRI analysis

Hyperparameter

Value

Input image size

\(256 \times 256\)

Batch size

4

Number of epochs

100

Learning rate

1e−4

Optimizer

AdamW

Loss function

Dice Loss

Activation function

ReLU, Sigmoid

Early stopping patience

10

Reduce LR factor

0.1

Back to article page