bug fix - only 1 target was returned

utils/hdf5_generator.py

@@ -88,7 +88,12 @@ def convert_hdf5(data_parameters, file_information):
                                                         crop_flag = data_parameters['crop_flag']
                                                         )
 
-    write_hdf5(train_dMRI, train_rsfMRI, file_information, mode='train')                                                                                                    
+    print("The lenght of the training inputs is {} and the size of the elements is {}".format(len(train_dMRI), train_dMRI[len(train_dMRI)-1].shape))
+    print("The lenght of the training targets is {} and the size of the elements is {}".format(len(train_rsfMRI), train_dMRI[len(train_rsfMRI)-1].shape))
+
+    write_hdf5(train_dMRI, train_rsfMRI, file_information, mode='train')
+
+    del train_dMRI, train_rsfMRI                                                                                                 
 
     # Then, we'll do it for the validation data
 
@@ -114,8 +119,12 @@ def convert_hdf5(data_parameters, file_information):
                                                                     crop_flag = data_parameters['crop_flag']
                                                                     )
 
+    print("The lenght of the validation inputs is {} and the size of the elements is {}".format(len(validation_dMRI), train_dMRI[len(validation_dMRI)-1].shape))
+    print("The lenght of the validation targets is {} and the size of the elements is {}".format(len(validation_rsfMRI), train_dMRI[len(validation_rsfMRI)-1].shape))
+
     write_hdf5(validation_dMRI, validation_rsfMRI, file_information, mode='validation')
 
+    del validation_dMRI, validation_rsfMRI
 
 def write_hdf5(input_volumes, target_volumes, file_information, mode):
     """ HDF5 Writer

utils/preprocessor.py

@@ -319,9 +319,9 @@ def load_datasets(subjects, data_directory, input_file, output_target, mean_regr
         input_volumes.append(input_volume)
         target_volumes.append(target_volume)
 
-        print("\r Processed {:.3f}%".format(index/len_subjects * 100.0), end='')
+        print("\r Processed {:.3f}%: {}/{} inputs, {}/{} targets".format(index/len_subjects * 100.0, len(input_volumes), len_subjects, len(target_volumes), len_subjects), end='')
 
-    return input_volumes, target_volume
+    return input_volumes, target_volumes
 
 def load_and_preprocess(subject, data_directory, input_file, output_target, mean_regression_flag, mean_regression_all_flag, regression_weights_path,
                         dMRI_mean_mask_path, rsfMRI_mean_mask_path, mean_subtraction_flag, scale_volumes_flag, normalize_flag, minus_one_scaling_flag, negative_flag,
@@ -431,7 +431,7 @@ def preprocess(input_volume, target_volume, subject, mean_regression_flag, mean_
             target_volume = linear_regress_mean(target_volume, subject, regression_weights_path, crop_flag, target_flag=True, rsfMRI_mean_mask_path=rsfMRI_mean_mask_path)
             # Set scaling parameters to Andrei Scaling
             scaling_parameters = [-0.0626, 0.1146, -14.18, 16.9475]
-        else:
+        elif mean_regression_all_flag == False:
             # Regress only targets, leave inputs as they are
             target_volume = linear_regress_mean(target_volume, subject, regression_weights_path, crop_flag, target_flag=True, rsfMRI_mean_mask_path=rsfMRI_mean_mask_path)
             # Set scaling parameters to Mixed Scaling
@@ -441,8 +441,6 @@ def preprocess(input_volume, target_volume, subject, mean_regression_flag, mean_
         target_volume = subtract_mean(target_volume, crop_flag, rsfMRI_mean_mask_path)
         # Set Scaling parameters to Steve Scaling
         scaling_parameters = [0.0, 0.2, 0.0, 10.0]
-    else:
-        pass
 
     if scale_volumes_flag == True:
         input_volume = volume_scaling(input_volume, scaling_parameters, normalize_flag, minus_one_scaling_flag, negative_flag, outlier_flag, shrinkage_flag, hard_shrinkage_flag, target_flag=False)