Fig. 3From: HAHNet: a convolutional neural network for HER2 status classification of breast cancerThe overall structure of the model. The model takes input images of size \(299 \times 299 \times 3\) and outputs four categories corresponding to the four levels of HER2 expression. The Conv and MaxPool module consists of five convolutional layers and two max pooling layers. The FC module consists of only one fully connected layerBack to article page