Skip to main content
. Author manuscript; available in PMC: 2020 Jul 13.
Published in final edited form as: IEEE Access. 2019 Jun 12;7:78421–78433. doi: 10.1109/access.2019.2922370

FIGURE 4.

FIGURE 4.

Schema of the proposed CNN-based SE model architecture. The CNN consists 3 components. Input image is first convolved with kernels. The final convolutional layer obtained by stride of 3 is flattened and fed into fully connected layer. Finally, output is fed to the linear layer.