Skip to main content
. 2018 Nov 8;8:16520. doi: 10.1038/s41598-018-34525-1

Figure 1.

Figure 1

Structure of the deep generative network CDI NN. CDI NN is implemented using an architecture composed entirely of convolutional, max pooling and upsampling layers. All activations are rectified linear units (ReLU) except for the final convolutional layer which uses sigmoidal activations.