pihnn.utils#
Utilities for building and training PIHNNs.
Functions#
Accessory function to get the ordinal number as a string from an int. |
|
|
|
|
|
|
Mean squared error (MSE). Equivalent to torch.nn.MSELoss() except it takes into account empty inputs. |
|
Evaluation of the loss function as Mean squared error (MSE). |
|
Called by |
|
Called by |
|
Stresses and displacements transformation for rotated systems of coordinates. |
|
Compute the J-integral. |
|
Implementation of the method from Yau et al. [1980] to evaluate the |
|
Performs the training of the neural network. |
|
Employ the RAD adaptive sampling from Wu et al. [2023]. |
|
Compute and print to screen the approximated relative \(L^p\) error between a model and a reference solution. I.e., |