Model Architecture Selection

Hyperparameter optimization for the proposed architecture is done using kerastuner. It provides capability to optimize and select different architectures depending on the application considered. The results for hyperparameter optimizations are shown below.

_images/hp_cnn.png

Fig 1: Bayesian 3D CNN Hyperparameter Optimization

_images/hp_unet.png

Fig 1: Bayesian 3D U-Net Optimization*