Scheme of our CNN architecture. Five parallel branches (two for star information, three for gas information) pass through several convolutional and pooling layers independently, further reducing the dimensionality; they then merge for a final sequence of dense and pooling layers, producing an N parameter output. After training the CNN, the 32 neurons of the penultimate layer are used as inputs to train a normalising flow model. The flow model learns a series of transformations to an N-dimensional Gaussian PDF, which are conditioned on the inputs, and outputs a posterior N-dimensional joint PDF. The final output represents the value estimated for the dynamical mass of the galaxy enclosed within N different radii.