We use a Convolutional Neural Network (CNN) to identify the relevant features in the thermodynamical phases of a simulated three-dimensional spin-lattice system with ferromagnetic and Dzyaloshinskii-Moriya (DM) interactions. Such features include (anti-)skyrmions, merons, and helical and ferromagnetic states. We use a multi-label classification framework, which is flexible enough to accommodate states that mix different features and phases. We then train the CNN to predict the features of the final state from snapshots of intermediate states of the simulation. The trained model allows identifying the different phases reliably and early in the formation process. Thus, the CNN can significantly speed up the phase diagram calculations by predicting the final phase before the spin-lattice Monte Carlo sampling has converged. We show the prowess of this approach by generating phase diagrams with significantly shorter simulation times.