Skip to main content
. Author manuscript; available in PMC: 2021 May 10.
Published in final edited form as: Comput Biol Med. 2020 Jun 24;122:103882. doi: 10.1016/j.compbiomed.2020.103882

Table 4.

VGG16 and ResNet50 Tuned Architecture

VGG16 ResNet50
Output from the final Convolution layer Output from base model
Fully Connected 1: 512, ReLU, Dropout=0.5 Global Average Pooling
Fully Connected 2: 512, ReLU, Dropout=0.5 Dropout =0.5
Fully Connected 3: 1, Sigmoid Fully Connected 1: 1, Sigmoid