10 July 2022 : Clinical Research
Automatic Identification of Depression Using Facial Images with Deep Convolutional Neural Network
Xinru Kong1CE, Yan Yao1BC, Cuiying Wang1BC, Yuangeng Wang1BF, Jing Teng2DG, Xianghua Qi2AG*DOI: 10.12659/MSM.936409
Med Sci Monit 2022; 28:e936409
Figure 3 (A–E) Training loss vs validation loss of FCN, VGG11, VGG19, ResNet50, and Inception-V3. VGG11, ResNet50 network, and Inception-V3 models had serious oscillation and achieved good results in speed and accuracy. At the same time, the loss function curves of the VGG11 and FCN models decreased rapidly and the model oscillation was small.