Skip to main content
. Author manuscript; available in PMC: 2020 Jun 1.
Published in final edited form as: Comput Biol Med. 2019 Apr 25;109:85–90. doi: 10.1016/j.compbiomed.2019.04.018

Table 3.

Results of training from scratch. We show the results of four different networks: original GoogleNet, reduced GoogleNet(GoogleNet_R), reduced VGGNet(VGG_R) and CIFAR. We list network input, training AUC and test AUC.

Network Input Training AUC Test AUC
GoogleNet 224×224×3 0.93 0.56
GoogleNet_R 64×64×3 0.94 0.57
VGGNet_R 80×80×3 0.98 0.54
CIFAR 80×80×3 0.75 0.58