This one is much better

app.py

@@ -10,7 +10,7 @@ import pandas as pd
 warnings.filterwarnings('ignore')
 disable_eager_execution()
 
-load_data = np.load('train_test_split_data.npz')  # Data saved by the VAE
+load_data = np.load('data/train_test_split_data.npz')  # Data saved by the VAE
 
 # Convert Data to Tuples and Assign to respective variables
 box_matrix_train, box_density_train, additional_pixels_train, box_shape_train = tuple(load_data['box_matrix_train']), tuple(load_data['box_density_train']), tuple(load_data['additional_pixels_train']), tuple(load_data['box_shape_train'])
@@ -245,18 +245,18 @@ thickness_options = [str(int(x)) for x in numpy.linspace(0, 10, 11)]
 interpolation_options = [str(int(x)) for x in [3, 5, 10]]
 
 def interpolate(t1, t2, d1, d2, th1, th2, steps):
-    decoder_model_boxes = tensorflow.keras.models.load_model('decoder_model_boxes', compile=False)
+    decoder_model_boxes = tensorflow.keras.models.load_model('data/decoder_model_boxes', compile=False)
     # # compile=False ignores a warning from tensorflow, can be removed to see warning
 
     # # import the encoder model architecture
-    json_file_loaded = open('model.json', 'r')
+    json_file_loaded = open('data/model.json', 'r')
     loaded_model_json = json_file_loaded.read()
 
     # load model using the saved json file
     encoder_model_boxes = tensorflow.keras.models.model_from_json(loaded_model_json)
 
     # load weights into newly loaded_model
-    encoder_model_boxes.load_weights('model_tf')
+    encoder_model_boxes.load_weights('data/model_tf')
 
     num_internal = int(steps)
     number_1 = globals()[t1](int(th1), float(d1), 28)