Davout 0.1.1.dev180__tar.gz → 0.1.1.dev181__tar.gz

{davout-0.1.1.dev180/source/Davout.egg-info → davout-0.1.1.dev181}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: Davout
-Version: 0.1.1.dev180
+Version: 0.1.1.dev181
 Summary: Scientific computing utilities combining FEM, ANN and tooling
 Author: Matheus Janczkowski
 Author-email: Matheus Janczkowski <matheusj2009@hotmail.com>
@@ -29,7 +29,9 @@ to the repository and source files: https://github.com/Matheus-Janczkowski/Davou
 
 4. Link to the book on continuum mechanics: https://github.com/Matheus-Janczkowski/CompMechSelfStudy/tree/main/introduction_to_continuum_mechanics
 
-4. Link for the presentation template: https://www.overleaf.com/read/sbgxdphxswmm#6d7d64
+5. Link for the presentation template: https://www.overleaf.com/read/sbgxdphxswmm#6d7d64
+
+6. Link for the report/paper template: https://www.overleaf.com/read/vhpsmzhwdsfg#c5dee9
 
 # Citation
 https://doi.org/10.5281/zenodo.18806245
@@ -65,8 +67,9 @@ such as FEniCS, TensorFlow, GMSH, ParaView, and matplotlib.
 # Installation using pip
 pip install Davout
 
-Or for a special dev version (123 for example). Check the pyproject.toml file to consult the
-latest version at the line 'version = "0.1.1.dev123"':
+Or for a special dev version (123 for example). Check the pyproject.toml 
+file (see https://github.com/Matheus-Janczkowski/Davout/blob/main/pyproject.toml
+at line 66) to consult the latest version at the line 'version = "0.1.1.dev123"':
 
 pip install Davout==0.1.1.dev123
 

{davout-0.1.1.dev180 → davout-0.1.1.dev181}/README.md

@@ -10,7 +10,9 @@ to the repository and source files: https://github.com/Matheus-Janczkowski/Davou
 
 4. Link to the book on continuum mechanics: https://github.com/Matheus-Janczkowski/CompMechSelfStudy/tree/main/introduction_to_continuum_mechanics
 
-4. Link for the presentation template: https://www.overleaf.com/read/sbgxdphxswmm#6d7d64
+5. Link for the presentation template: https://www.overleaf.com/read/sbgxdphxswmm#6d7d64
+
+6. Link for the report/paper template: https://www.overleaf.com/read/vhpsmzhwdsfg#c5dee9
 
 # Citation
 https://doi.org/10.5281/zenodo.18806245
@@ -46,8 +48,9 @@ such as FEniCS, TensorFlow, GMSH, ParaView, and matplotlib.
 # Installation using pip
 pip install Davout
 
-Or for a special dev version (123 for example). Check the pyproject.toml file to consult the
-latest version at the line 'version = "0.1.1.dev123"':
+Or for a special dev version (123 for example). Check the pyproject.toml 
+file (see https://github.com/Matheus-Janczkowski/Davout/blob/main/pyproject.toml
+at line 66) to consult the latest version at the line 'version = "0.1.1.dev123"':
 
 pip install Davout==0.1.1.dev123
 

{davout-0.1.1.dev180 → davout-0.1.1.dev181}/pyproject.toml

@@ -63,7 +63,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "Davout"
-version = "0.1.1.dev180"
+version = "0.1.1.dev181"
 description = "Scientific computing utilities combining FEM, ANN and tooling"
 readme = "README.md"
 authors = [

{davout-0.1.1.dev180/source/Davout/DeepMech/aa_tests/mecsol_2026_quotient_space → davout-0.1.1.dev181/source/Davout/DeepMech/aa_tests/SVD_framework}/dataset_generator.py

@@ -162,10 +162,11 @@ save_snapshot_displacement=False):
             strain_energy_file_name+"_"+simulation_number+".npy")[:,1:
             ].tolist())
 
-            # Adds the Young modulus data and the displacement gradient
+            # Adds the displacement gradient and, then, the Young modulus
+            # data. The variables related to the quotient space must come
+            # first
 
-            successful_sample_data = [sample_data[variables_indices["p"+
-            "eak E"]], sample_data[variables_indices["base E"]]]
+            successful_sample_data = []
 
             successful_sample_data.extend(displacement_gradient[0])
 
@@ -173,6 +174,9 @@ save_snapshot_displacement=False):
 
             successful_sample_data.extend(displacement_gradient[2])
 
+            successful_sample_data.extend([sample_data[variables_indices[
+            "peak E"]], sample_data[variables_indices["base E"]]])
+
             succesful_data.append(successful_sample_data)
 
             # Updates the list of completed simulations
@@ -339,7 +343,7 @@ if __name__=="__main__":
 
     cube_size = 0.5
 
-    n_divisions = 10
+    n_divisions = 6#10
 
     E_extremum = 10E6
 
@@ -355,7 +359,8 @@ if __name__=="__main__":
 
     # Sets the paths and files names
 
-    results_path = get_parent_path_of_file()+"//results"
+    results_path = (get_parent_path_of_file()+"//results_n_divisions_"+
+    str(n_divisions))
 
     displacement_file_name = "displacement_young_modulus_field"
 

{davout-0.1.1.dev180 → davout-0.1.1.dev181}/source/Davout/DeepMech/aa_tests/SVD_framework/kinematics_surrogate_model.py

@@ -9,6 +9,8 @@ from time import time
 
 from .....Davout.DeepMech.tool_box import ANN_tools, training_tools
 
+from .....Davout.DeepMech.tool_box.numerical_tools import DataMatrixRegularization
+
 from .....Davout.DeepMech.tool_box.loss_assembler_classes import MaximumAbsoluteError
 
 from .....Davout.PythonicUtilities.path_tools import get_parent_path_of_file
@@ -22,12 +24,23 @@ class RVEKinematicsSurrogateModel:
     activations_list_auxiliar_network, quotient_space_dimension, 
     modulating_function, displacement_data_file, input_data_file, 
     results_path, loss_metric, n_training_samples, saved_model_file,
-    n_monte_carlo_realizations, n_best_models, 
+    n_monte_carlo_realizations, n_best_models, n_best_samples,
     maximum_training_iterations, verbose_delta_iterations,
-    parameters_dtype="float32", householder_epsilon=1.0, verbose=True):
+    mesh_file_name, optimizer, subdofs_to_learn, parameters_dtype="flo"+
+    "at32", householder_epsilon=1.0, verbose=True, integer_dtype="int3"+
+    "2", get_all_inputs_to_zeroth_order_of_magnitude=False, 
+    non_orthogonal_matrices=False, device_type="CPU", 
+    input_data_regularization_method=None):
 
         # Saves the needed information
 
+        self.non_orthogonal_matrices = non_orthogonal_matrices
+
+        self.device_type = device_type
+
+        self.get_all_inputs_to_zeroth_order_of_magnitude = (
+        get_all_inputs_to_zeroth_order_of_magnitude)
+
         self.activations_list_main_network = activations_list_main_network
 
         self.activations_list_auxiliar_network = (
@@ -45,6 +58,8 @@ class RVEKinematicsSurrogateModel:
 
         self.loss_metric = loss_metric
 
+        self.optimizer = optimizer
+
         self.n_training_samples = n_training_samples
 
         self.saved_model_file = saved_model_file
@@ -53,7 +68,9 @@ class RVEKinematicsSurrogateModel:
 
         self.n_best_models = n_best_models
 
-        self.parameters_dtype = parameters_dtype
+        self.n_best_samples = n_best_samples
+
+        self.mesh_file_name = mesh_file_name
 
         self.householder_epsilon = householder_epsilon
 
@@ -63,19 +80,38 @@ class RVEKinematicsSurrogateModel:
 
         self.verbose_delta_iterations = verbose_delta_iterations
 
-    # Defines a function to train the neural network model
+        # Saves the tensorflow dtypes
 
-    def train_surrogate_model(self):
+        self.parameters_dtype = parameters_dtype
 
-        # Reads the two files
+        self.integer_dtype = integer_dtype
 
-        output_data = np.load(self.results_path+"//"+
+        # Converts the tensor of DOFs to a tensorflow integer tensor
+
+        self.subdofs_to_learn = tf.convert_to_tensor(subdofs_to_learn,
+        dtype=tf.as_dtype(self.parameters_dtype))
+
+        # Gets the number of output neurons from the tensor of the indi-
+        # ces of the DOFs that will actually be learnt
+
+        self.n_output_neurons = self.subdofs_to_learn.shape[0]
+
+        # Reads the output data 
+
+        self.output_data = np.load(self.results_path+"//"+
         self.displacement_data_file)
 
+        # Gets the numbers of samples and of total of DOFs
+
+        self.number_of_samples, self.total_number_of_dofs = (
+        self.output_data.shape)
+
+        # Gets the input data
+
         input_data = np.load(self.results_path+"//"+self.input_data_file)
 
         # Checks whether there is sufficient samples in the dataset
-
+        
         if self.n_training_samples>=input_data.shape[0]:
 
             raise IndexError(str(self.n_training_samples)+" samples we"+
@@ -83,7 +119,7 @@ class RVEKinematicsSurrogateModel:
             input_data.shape[0])+" samples in the input data matrix at"+
             ":\n"+str(self.results_path+"//"+self.input_data_file))
 
-        if self.n_training_samples>=output_data.shape[0]:
+        if self.n_training_samples>=self.output_data.shape[0]:
 
             raise IndexError(str(self.n_training_samples)+" samples we"+
             "re asked for training, but there are only "+str(
@@ -91,26 +127,40 @@ class RVEKinematicsSurrogateModel:
             "t:\n"+str(self.results_path+"//"+
             self.displacement_data_file))
 
-        if output_data.shape[0]!=input_data.shape[0]:
+        if self.output_data.shape[0]!=input_data.shape[0]:
 
             raise IndexError("The output data matrix has "+str(
-            output_data.shape[0])+" samples, whereas the input data ma"+
-            "trix has "+str(input_data.shape[0])+" samples.\n\nThe out"+
-            "put data matrix is at:\n"+str(self.results_path+"//"+
+            self.output_data.shape[0])+" samples, whereas the input da"+
+            "ta matrix has "+str(input_data.shape[0])+" samples.\n\nTh"+
+            "e output data matrix is at:\n"+str(self.results_path+"//"+
             self.displacement_data_file)+"\n\nthe input data matrix is"+
             "at:\n"+str(self.results_path+"//"+self.input_data_file))
 
-        # Sets the training data
+        # Checks if a regularization technique was requested for the in-
+        # put data matrix
+
+        if input_data_regularization_method is not None:
+
+            # Instantiates the data regularization class
+
+            data_regularization_class = DataMatrixRegularization(
+            regularization_function=input_data_regularization_method)
 
-        training_data = input_data[0:self.n_training_samples,:]
+            # Regularizes the data matrix and saves the regularization
+            # data using this input data
 
-        training_true_values = output_data[0:self.n_training_samples,:]
+            self.input_data, _ = data_regularization_class(input_data, 
+            True)
 
-        # Gets the number of input and output neurons
+        # Otherwise, simply saves the input data into the class
+        
+        else:
+
+            self.input_data = input_data
 
-        n_input_neurons = input_data.shape[1]
+        # Gets the number of input neurons
 
-        n_output_neurons = output_data.shape[1]
+        self.n_input_neurons = self.input_data.shape[1]
 
         # Verifies if the output layer of the main network has the same
         # number of output neurons
@@ -121,32 +171,47 @@ class RVEKinematicsSurrogateModel:
 
             n_output_neurons_main_network += value
 
-        if n_output_neurons_main_network!=n_output_neurons:
+        if n_output_neurons_main_network!=self.n_output_neurons:
 
             raise ValueError("The main network has "+str(
             n_output_neurons_main_network)+" neurons in the output lay"+
             "er; whereas the data indicate that there must be "+str(
-            n_output_neurons)+" neurons in the output layer")
+            self.n_output_neurons)+" neurons in the output layer")
 
         # Sets the architecture dictionary
     
-        custom_architecture = {"name": "SVDQuotientSpace", "weights mo"+
-        "dulating function": self.modulating_function, "Householder ep"+
-        "silon": self.householder_epsilon, "activations accessory laye"+
-        "r list": self.activations_list_auxiliar_network}
+        self.custom_architecture = {"name": "SVDQuotientSpace", "weigh"+
+        "ts modulating function": self.modulating_function, "Household"+
+        "er epsilon": self.householder_epsilon, "activations accessory"+
+        " layer list": self.activations_list_auxiliar_network, "non-or"+
+        "thogonal matrices": self.non_orthogonal_matrices, "hardware d"+
+        "evice": self.device_type, "convex with respect to quotient sp"+
+        "ace": False}
+
+    # Defines a function to train the neural network model
+
+    def train_surrogate_model(self):
+
+        # Sets the training data
+
+        training_data = self.input_data[0:self.n_training_samples,:]
+
+        training_true_values = self.output_data[0:self.n_training_samples
+        ,:]
 
         # Creates the class of neural network information
 
-        ANN_class = ANN_tools.MultiLayerModel(n_input_neurons,
+        ANN_class = ANN_tools.MultiLayerModel(self.n_input_neurons,
         self.activations_list_main_network, enforce_customLayers=True, 
         verbose=self.verbose, parameters_dtype=self.parameters_dtype, 
-        custom_architecture=custom_architecture, input_size_main_network=
-        self.quotient_space_dimension)
+        custom_architecture=self.custom_architecture, 
+        input_size_main_network=self.quotient_space_dimension)
 
         self.custom_model = ANN_class()
 
         # Defines the loss metric
 
+        """
         self.live_loss_metric = None
 
         if isinstance(self.loss_metric, str):
@@ -159,7 +224,9 @@ class RVEKinematicsSurrogateModel:
                 "metric by the name '"+str(self.loss_metric)+"'")
 
             self.live_loss_metric = getattr(tf.keras.losses, 
-            self.loss_metric)(dtype=tf.as_dtype(self.parameters_dtype))
+            self.loss_metric)(dtype=tf.as_dtype(self.parameters_dtype))"""
+
+        self.live_loss_metric = self.loss_metric
 
         # Sets the optimization class for training
 
@@ -169,7 +236,7 @@ class RVEKinematicsSurrogateModel:
         self.maximum_training_iterations, verbose_deltaIterations=
         self.verbose_delta_iterations, save_model_file=
         self.saved_model_file, match_data_float_type_to_trainables=True, 
-        parent_path=self.results_path)
+        parent_path=self.results_path, optimizer=self.optimizer)
 
         t_initial = time()
 
@@ -183,7 +250,8 @@ class RVEKinematicsSurrogateModel:
 
         training_class.monte_carlo_training(n_realizations=
         self.n_monte_carlo_realizations, best_models_rank_size=
-        self.n_best_models, show_reinitialization_distance=True)
+        self.n_best_models, show_reinitialization_distance=True, 
+        model_base_name=self.saved_model_file)
 
         # Checks the loss again with the best model of the Monte Carlo
         # training
@@ -275,6 +343,10 @@ class RVEKinematicsSurrogateModel:
 
 if __name__=="__main__":
 
+    # Defines the array with the DOFs to be learnt
+
+    subdofs_to_learn = np.arange(0, 20577, 3)
+
     # Defines the number of input neurons of the main network. Remember
     # that the data matrix is a tensor [n_samples, n_input_variables]. 
     # The first quotient_space_dimension columns must be dedicated to 
@@ -307,6 +379,8 @@ if __name__=="__main__":
 
     # Sets the training information
 
+    optimizer = "Adam"
+
     n_training_samples = 10000
 
     maximum_training_iterations = 1000
@@ -317,6 +391,8 @@ if __name__=="__main__":
 
     n_best_models = 5
 
+    n_best_samples = 10
+
     loss_metric = "MeanSquaredError"
 
     parameters_dtype = "float32"
@@ -331,6 +407,26 @@ if __name__=="__main__":
 
     input_data_file = "00_successful_complete_and_filtered_data_matrix.npy"
 
+    mesh_file_name = get_parent_path_of_file()+"//box_mesh_mecsol"
+
+    # Sets the method to regularize the input data matrix
+
+    input_data_regularization_method = None
+
+    # Sets if the input data must be put into the same order of magnitu-
+    # de
+
+    get_all_inputs_to_zeroth_order_of_magnitude = False
+
+    # Sets the device type where the training will be performed
+
+    device_type = "GPU"
+
+    # Sets whether the constraint on orthogonality of the SVD matrices
+    # will not be enforced
+
+    non_orthogonal_matrices = False
+
     # Instantiates the class that owns all information about training 
     # and testing models
 
@@ -339,14 +435,23 @@ if __name__=="__main__":
     quotient_space_dimension, modulating_function, 
     displacement_data_file, input_data_file, results_path, loss_metric, 
     n_training_samples, saved_model_file, n_monte_carlo_realizations, 
-    n_best_models, maximum_training_iterations, verbose_delta_iterations,
-    parameters_dtype=parameters_dtype, householder_epsilon=1.0, verbose=
-    True)
+    n_best_models, n_best_samples, maximum_training_iterations, 
+    verbose_delta_iterations, mesh_file_name, optimizer, 
+    subdofs_to_learn, parameters_dtype=parameters_dtype, 
+    householder_epsilon=1.0, verbose=True, 
+    get_all_inputs_to_zeroth_order_of_magnitude=
+    get_all_inputs_to_zeroth_order_of_magnitude, device_type=
+    device_type, non_orthogonal_matrices=non_orthogonal_matrices,
+    input_data_regularization_method=input_data_regularization_method)
 
     training_flag = True
 
+    testing_flag = False
+
     if training_flag:
 
         modeling_class.train_surrogate_model()
 
-    modeling_class.test_surrogate_model()
+    if testing_flag:
+
+        modeling_class.test_surrogate_model()

{davout-0.1.1.dev180 → davout-0.1.1.dev181}/source/Davout/DeepMech/aa_tests/mecsol_2026_quotient_space/neural_network_trainer.py

@@ -9,9 +9,11 @@ from time import time
 
 from .....Davout.DeepMech.tool_box import ANN_tools, training_tools
 
+from .....Davout.DeepMech.tool_box.FEM_surrogate_testing_tools import FEMSurrogateEvaluator
+
 from .....Davout.DeepMech.tool_box.loss_assembler_classes import MaximumAbsoluteError
 
-from .....Davout.PythonicUtilities.path_tools import get_parent_path_of_file
+from .....Davout.PythonicUtilities.path_tools import get_parent_path_of_file, take_outFileNameTermination
 
 from .....Davout.MultiMech.tool_box.binary_tools import read_field_from_binary
 
@@ -113,9 +115,11 @@ class SurrogateModel:
         )+"; the maximum absolute is: "+str(np.max(np.abs(
         material_input_data)))+"\n")
 
-        input("The architecture is:\n"+str(self.activations_list)+"\n"+
+        print("The architecture is:\n"+str(self.activations_list)+"\n"+
         "\nThe output data has a total of "+str(self.total_number_of_dofs
-        )+" DOFs\n\nPress ENTER to continue\n\n")
+        )+" DOFs")
+        
+        #input("\nPress ENTER to continue\n\n")
 
         # The order of magnitude of the material data is expected to be 
         # larger than the kinematic data. Thus, gets the material input
@@ -127,6 +131,14 @@ class SurrogateModel:
         self.input_data = np.hstack((self.kinematic_input_data, 
         self.material_input_data))
 
+        # Saves the corrected input data
+
+        self.corrected_data_file = take_outFileNameTermination(
+        self.input_data_file)+"_corrected.npy"
+
+        np.save(self.results_path+"//"+self.corrected_data_file, 
+        self.input_data)
+
     # Defines a function to train the neural network model
 
     def train_surrogate_model(self):
@@ -215,7 +227,7 @@ class SurrogateModel:
             # Loads this model
 
             loaded_model = tf.keras.models.load_model(self.results_path+
-            "//"+str(i+1)+"_best_"+self.saved_model_file+".keras")
+            "//"+str(i+1)+"_"+self.saved_model_file+".keras")
 
             # Gets the output of the loaded model
 
@@ -230,7 +242,7 @@ class SurrogateModel:
             print("Loss function on test set:", format(test_loss.numpy(
             ), '.5e'))
 
-            # Verifies with the maximum absolute error
+            # Verifies with the maximum absolute error 
 
             maximum_absolute_value = maximum_absolute_error(
             test_true_values, output_model)
@@ -295,7 +307,7 @@ class SurrogateModel:
             self.n_training_samples:,:][best_samples_indices,:])
 
             np.save(self.results_path+"//surrogate_best_samples_of_"+
-            str(i+1)+"_best_"+self.saved_model_file+".npy", 
+            str(i+1)+"_"+self.saved_model_file+".npy", 
             model_displacement.numpy()[best_samples_indices,:])
 
     # Defines a function to insert the results into a function space and
@@ -324,6 +336,31 @@ class SurrogateModel:
 
             last_model = limit_model+0
 
+        # Initializes the class for performance testing
+
+        #"""
+        surrogate_evaluation_class = FEMSurrogateEvaluator(
+        self.corrected_data_file, self.displacement_data_file, 
+        self.n_training_samples, self.saved_model_file, "Displacement",
+        parent_path=self.results_path, verbose=True,
+        maximum_number_of_models_to_be_evaluated=last_model,
+        subdofs_to_learn=self.subdofs_to_learn, take_snapshots=True,
+        field_type="vector", polynomial_degree=2, 
+        interpolation_function="CG", mesh_file_name=self.mesh_file_name,
+        screenshots_path=self.screenshots_path, field_component_to_plot=
+        self.displacement_component_to_plot, number_of_best_samples=
+        self.n_best_samples, number_of_samples_to_be_snapshot=1,
+        set_camera_interactively=False, build_error_field=True,
+        mean_absolute_error_threshold=5E-3)
+
+        # Tests on the training dataset that has been set during instan-
+        # tiation of the class
+
+        surrogate_evaluation_class.evaluate_model_on_dataset()
+
+        #float(a)#"""
+
+        """
         # Iterates through the best models
 
         for i in range(last_model):
@@ -331,7 +368,7 @@ class SurrogateModel:
             # Loads this model
 
             loaded_model = tf.keras.models.load_model(self.results_path+
-            "//"+str(i+1)+"_best_"+self.saved_model_file+".keras")
+            "//"+str(i+1)+"_"+self.saved_model_file+".keras")
 
             # Gets the output of the loaded model
 
@@ -341,7 +378,7 @@ class SurrogateModel:
 
             test_loss = loss_metric(training_true_values, output_model)
 
-            print("Loads the "+str(i+1)+"-th best model")
+            print("\n\n\n\nLoads the "+str(i+1)+"-th best model")
 
             print("Loss function on training set:", format(
             test_loss.numpy(), '.5e'))
@@ -375,7 +412,7 @@ class SurrogateModel:
             # ment DOFs of this model
 
             displacement_output_file = (self.results_path+"//surrogate"+
-            "_best_training_samples_of_"+str(i+1)+"_best_"+
+            "_best_training_samples_of_"+str(i+1)+"_"+
             self.saved_model_file+".npy")
 
             # Recovers the name of the file with the true values of dis-
@@ -455,7 +492,7 @@ class SurrogateModel:
             # Sets the name of the screenshot file
 
             screenshot_file = ("surrogate_best_training_sample_of_"+str(
-            i+1)+"_best_"+self.saved_model_file+".png")
+            i+1)+"_"+self.saved_model_file+".png")
 
             # Sets the name of the screenshot file for the true displa-
             # cement
@@ -498,7 +535,7 @@ class SurrogateModel:
             legend_bar_visibility=True)
 
             print("\nThe input data for the "+str(i+1)+"-th model is: "+
-            str(training_data[best_samples_indices[0],:])+"\n")
+            str(training_data[best_samples_indices[0],:])+"\n")#"""
 
     # Defines a function to insert the results into a function space and
     # plot it for the samples of the test set
@@ -513,7 +550,7 @@ class SurrogateModel:
             # ment DOFs of this model
 
             displacement_output_file = (self.results_path+"//surrogate"+
-            "_best_samples_of_"+str(i+1)+"_best_"+self.saved_model_file+
+            "_best_samples_of_"+str(i+1)+"_"+self.saved_model_file+
             ".npy")
 
             # Recovers the name of the file with the true values of dis-
@@ -553,7 +590,7 @@ class SurrogateModel:
             # Sets the name of the screenshot file
 
             screenshot_file = ("surrogate_best_sample_of_"+str(i+1)+"_"+
-            "best_"+self.saved_model_file+".png")
+            self.saved_model_file+".png")
 
             # Sets the name of the screenshot file for the true displa-
             # cement
@@ -604,7 +641,7 @@ class SurrogateModel:
         # Gets the name of the screenshot file
         
         screenshot_file = ("surrogate_best_training_sample_of_"+str(
-        model_number)+"_best_"+self.saved_model_file+".png")
+        model_number)+"_"+self.saved_model_file+".png")
 
         # Sets the name of the screenshot file for the true displa-
         # cement
@@ -732,7 +769,7 @@ class SurrogateModel:
         # Loads the best gated model
         
         loaded_gated_model = tf.keras.models.load_model(
-        self.results_path+"//1_best_"+self.saved_model_file+".keras")
+        self.results_path+"//1_"+self.saved_model_file+".keras")
 
         # Gets the output of the loaded gated model
 
@@ -763,7 +800,7 @@ if __name__=="__main__":
 
     Lp_norm_exponent = 12
 
-    saved_model_file = "saved_model_lp_norm_"+str(Lp_norm_exponent)
+    saved_model_file = "best_saved_model_lp_norm_"+str(Lp_norm_exponent)
 
     saved_model_without_gate_file = ("saved_model_without_gate_lp_norm"+
     "_"+str(Lp_norm_exponent))
@@ -797,13 +834,13 @@ if __name__=="__main__":
 
     test_flag = False
 
-    plot_training_responses = False
+    plot_training_responses = True
 
     plot_test_responses = False
 
     collage_flag = False
 
-    compare_without_gate = True
+    compare_without_gate = False
 
     # Gets the mesh of the RVE