Skip to main content
. 2021 Jun 16;10(7):21. doi: 10.1167/tvst.10.7.21

Figure 3.

Figure 3.

The proposed custom VGG-16 model architecture used for 512 × 512 pixel image classification (created by Hazem Abdelmotaal). Conv2D = convolution layer + ReLU activation; Dense 1, 2 = fully connected layers + ReLU activation; Dense 3 = fully connected layer + Softmax activation.