UNIQORN -- The Universal Neural-network Interface for Quantum Observable Readout from N-body wavefunctions
|
Functions | |
def | make_variable (tuple, initializer) |
def | shape (tensor) |
def | plot_interpol (xesnew, ynew) |
def | ApplyInterpolation (y_data, y_data_interpolation) |
def | Interpolation_MSE (y_true, y_pred) |
Custom Loss function evaluating the error of an interpolation. More... | |
def | MSE_plus_MAE (y_true, y_pred) |
def | MSE_plus_LogMSE (y_true, y_pred) |
def | LogCosh_plus_MAE (y_true, y_pred) |
def | LogCosh_plus_LogMSE (y_true, y_pred) |
def | LogCosh_plus_MSE (y_true, y_pred) |
def | LogCosh_plus_LogMSE_plus_MAE (y_true, y_pred) |
def | main (*args, **kwargs) |
def | ModelEvaluation (*args) |
Variables | |
threshold | |
xgrid = np.arange(0.0,1.0*inp.Npoints) | |
ygrid = np.arange(0.0,1.0*inp.Npoints) | |
test_predictions = ModelEvaluation(model, validation_generator) | |
test data: More... | |
int | size_predictions = 1 |
int | size_labels = 1 |
y_val = y_val.reshape(np.shape(test_predictions)) | |
def ModelTrainingAndValidation.ApplyInterpolation | ( | y_data, | |
y_data_interpolation | |||
) |
def ModelTrainingAndValidation.Interpolation_MSE | ( | y_true, | |
y_pred | |||
) |
Custom Loss function evaluating the error of an interpolation.
def ModelTrainingAndValidation.LogCosh_plus_LogMSE | ( | y_true, | |
y_pred | |||
) |
def ModelTrainingAndValidation.LogCosh_plus_LogMSE_plus_MAE | ( | y_true, | |
y_pred | |||
) |
def ModelTrainingAndValidation.LogCosh_plus_MAE | ( | y_true, | |
y_pred | |||
) |
def ModelTrainingAndValidation.LogCosh_plus_MSE | ( | y_true, | |
y_pred | |||
) |
def ModelTrainingAndValidation.main | ( | * | args, |
** | kwargs | ||
) |
def ModelTrainingAndValidation.make_variable | ( | tuple, | |
initializer | |||
) |
def ModelTrainingAndValidation.ModelEvaluation | ( | * | args | ) |
def ModelTrainingAndValidation.MSE_plus_LogMSE | ( | y_true, | |
y_pred | |||
) |
def ModelTrainingAndValidation.MSE_plus_MAE | ( | y_true, | |
y_pred | |||
) |
def ModelTrainingAndValidation.plot_interpol | ( | xesnew, | |
ynew | |||
) |
def ModelTrainingAndValidation.shape | ( | tensor | ) |
int ModelTrainingAndValidation.size_labels = 1 |
int ModelTrainingAndValidation.size_predictions = 1 |
ModelTrainingAndValidation.test_predictions = ModelEvaluation(model, validation_generator) |
test data:
OBTAIN PREDICTIONS ###
ModelTrainingAndValidation.threshold |
ModelTrainingAndValidation.xgrid = np.arange(0.0,1.0*inp.Npoints) |
ModelTrainingAndValidation.y_val = y_val.reshape(np.shape(test_predictions)) |
ModelTrainingAndValidation.ygrid = np.arange(0.0,1.0*inp.Npoints) |