A data-driven wall model for turbulent flows over periodic hills is developed using a feedforward neural network and wall-resolved large-eddy simulation data. The employs wall-normal distance, near-wall velocities, pressure gradients as input features, the shear stresses output labels, respectively. In $a$ $p\phantom{\rule{0}{0ex}}r\phantom{\rule{0}{0ex}}i\phantom{\rule{0}{0ex}}o\phantom{\rule{...