The DNN-ROM code can be used for construction of reduced order models, ROMs, of fluid flows. The code employs a combination of flow modal decomposition and regression analysis. Spectral proper orthogonal decomposition, SPOD, is applied to reduce the dimensionality of the model and, at the same time, filter the POD temporal modes. The regression step is performed by a deep feedforward neural network, DNN, and the current framework is implemented in a context similar to the sparse identification of non-linear dynamics algorithm, SINDy. Test cases such as the compressible flow past a cylinder and the turbulent flow computed by a large eddy simulation of a plunging airfoil under dynamic stall are provided. The current reduced order model framework is able to capture the dynamics of the leading edge stall vortex and the subsequent trailing edge vortex. For the examples provided, the numerical framework allows the prediction of the flowfield beyond the training window using larger time increments than those employed by the full order model. The current DNN approach is also able to learn transient features of the flow and presents accurate and stable long-term predictions.