Figure 2
From: Prediction of steady flows passing fixed cylinders using deep learning
Schematic representation of the architecture of the deep-learning model. The input is a smoothed profile function \(\phi\), and the outputs are the x- and y-components of the flow velocity (i.e., u and v). The filter size \(f_{i}\) and keep probability \(k_{i}\) of ith residual block are shown.
