pihnn.graphics.plot_sol#

pihnn.graphics.plot_sol(triangulation, model, model_true=None, format='png', dir='results/', figsize=None, split=False, **kwargs)#

Plot of the solution from the training of the network. This can be graphically compared with a reference solution (either numerical or analytical). The function behaves differently for each problem:

  • For the Laplace and biharmonic problems, it shows the PDE solutions.

  • For linear elasticity, it plots the stresses.

Parameters:

  • triangulation (matplotlib.tri.Triangulation) – 2D mesh used for the contour plot.

  • model (pihnn.nn.PIHNN/pihnn.nn.DD_PIHNN) – Neural network model.

  • model_true (callable / None) – Reference solution. It must be a scalar function for Laplace and biharmonic problems whereas it must return the 3 components of the stress tensor when solving the linear elasticity problem. Instead, leave it to None if no comparison is desired.

  • format (str) – Format of the save figure.

  • dir (str) – Directory where to save the figure.

  • figsize (tuple of float) – Size of the matplotlib.pyplot.figure. If None, no figure is created.

  • split (bool) – Whether to split the solutions into multiple files or a single picture.