Skip to main content
. 2023 May 11;13(10):1696. doi: 10.3390/diagnostics13101696

Figure 2.

Figure 2

Structure of our autoencoder model. It includes three 3 × 3 convolutional layers, each followed by a leaky rectified linear unit (LeakyReLU) and a 2 × 2 max-pooling operation. The decoder path includes three 3 × 3 convolutional layers, followed by a LeakyReLU and an up-sampling operation. NN: number of neurons.