Skip to main content
. 2023 Sep 27;13:16202. doi: 10.1038/s41598-023-43418-x

Figure 3.

Figure 3

ResNet-18 convolutional neural network consisting of 18 blocks of convolutional layers, average pooling with batch normalization concatenated with a convolutional skip connection, and one fully connected layer. The activation function used is a rectified linear unit. Conv2D, 2D convolution layer; dense, dense (fully connected) layer; merge, merge (sum) layer; norm, batch normalization layer; ReLU rectified linear unit.