Figure 3 | Scientific Reports

Figure 3

From: Accuracy of deep learning, a machine-learning technology, using ultra–wide-field fundus ophthalmoscopy for detecting rhegmatogenous retinal detachment

Figure 3

Overall architecture of the model. The data set for the retinal fundus images (96 × 96 pixels) is labelled as Input. Each of the convolutional layers (Conv1–3) is followed by an activation function (ReLU) layer, pooling layers (MP1–3) and two fully connected layers (FC1, FC2). The final output layer performs binary classification by using a softmax function.

Back to article page