data_driven¶
pymor-demo data_driven [OPTIONS] REGRESSOR GRID_INTERVALS TRAINING_SAMPLES
Model order reduction with machine learning methods (approach by Hesthaven and Ubbiali).
Arguments:
REGRESSORRegressor to use. Options are neural networks using PyTorch, pyMOR’s VKOGA algorithm or Gaussian process regression using scikit-learn. [Required, Choices:
fcnn,vkoga,gpr]GRID_INTERVALSGrid interval count. [Required]
TRAINING_SAMPLESNumber of samples used for computing the reduced basis and training the regressor. [Required]
Parameters:
--fv, --no-fvUse finite volume discretization instead of finite elements. [Default:
False]--vis, --no-visVisualize full order solution and reduced solution for a test set. [Default:
False]--validation-ratioRatio of training data used for validation of the neural networks. [Default:
0.1]--input-scaling, --no-input-scalingScale the input of the regressor (i.e. the parameter). [Default:
False]--output-scaling, --no-output-scalingScale the output of the regressor (i.e. reduced coefficients or output quantity. [Default:
False]