Skip to main content
Fig. 1 | Journal of Hematology & Oncology

Fig. 1

From: Constructing an automatic diagnosis and severity-classification model for acromegaly using facial photographs by deep learning

Fig. 1

The architecture of our proposed model. Conv represents the 1 × 1 convolutional layer; the GAP, AvgPool, and FC are the global average pooling layer, the average pooling layer, and the fully connected layer, respectively. In this work, the rate of dropout was set to 0.8, the activation function of the convolution layer is ReLU, and there is no activation function in the fully connected layer

Back to article page