diff --git a/restaurant.xlsx b/restaurant.xlsx
index 4cb72c9..212a2da 100644
Binary files a/restaurant.xlsx and b/restaurant.xlsx differ
diff --git a/tiles.py b/tiles.py
index 69ccb7f..49ffaac 100644
--- a/tiles.py
+++ b/tiles.py
@@ -4,12 +4,20 @@ import numpy as np
 import pygame
 import pytmx
 from queue import Queue
-import math
 import pandas as pd
 from sklearn.model_selection import train_test_split
 from sklearn.tree import DecisionTreeClassifier
 import json
 import openpyxl
+import matplotlib.pyplot as plt
+import os
+import cv2
+from tqdm import tqdm
+from keras.models import Sequential
+from keras.layers import Dense, Dropout, Activation, Flatten
+from keras.layers import Conv2D, MaxPooling2D
+import math
+
 
 pygame.init()
 
@@ -532,8 +540,6 @@ def append_choice(ans, pre, d, df):
     n_df = pd.DataFrame(data, index=[len(df) + 1])
     append_df_to_excel(n_df, "restaurant.xlsx")
 
-
-
 def get_pizza(number):
     with open("dishes.json") as f:
         data = json.load(f)
@@ -542,6 +548,92 @@ def get_pizza(number):
             food = Food(i['name'], i['pos_in_card'], i['price'], i['spiciness'], i['vege'], i['size'], i['allergens'], i['ingridients'], i['drink_in'])
     return food
 
+#network
+def create_training_data():
+    DATADIR = "Images"
+    CATEGORIES = ["yes", "no"]
+    IMG_SIZE = 90
+    training_data = []
+    for category in CATEGORIES:
+        path = os.path.join(DATADIR, category)
+        class_num = CATEGORIES.index(category)  # 0 - pepperoni, 1 - no pepperoni
+        for img in tqdm(os.listdir(path)):
+            try:
+                img_array = cv2.imread(os.path.join(path, img), cv2.IMREAD_GRAYSCALE)
+                new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))
+                training_data.append([new_array, class_num])
+            except Exception as e:
+                pass
+    X = []
+    y = []
+
+    for features, label in training_data:
+        X.append(features)
+        y.append(label)
+
+    X = np.array(X).reshape(-1, IMG_SIZE, IMG_SIZE, 1)
+    y = np.array(y)
+
+    print("Training data created!")
+    return X,y
+
+def learn_neural_network(X,y):
+    X = X/255.0
+
+    model = Sequential()
+
+    model.add(Conv2D(64, (3, 3), input_shape=X.shape[1:]))
+    model.add(Activation('relu'))
+    model.add(MaxPooling2D(pool_size=(2, 2)))
+
+    model.add(Conv2D(64, (3, 3)))
+    model.add(Activation('relu'))
+    model.add(MaxPooling2D(pool_size=(2, 2)))
+
+    model.add(Flatten())
+
+    model.add(Dense(64))
+
+    model.add(Dense(1))
+    model.add(Activation('sigmoid'))
+
+    model.compile(loss='binary_crossentropy',
+                  optimizer='adam',
+                  metrics=['accuracy'])
+
+    model.fit(X, y, batch_size=1, epochs=10, validation_batch_size=0.1)
+
+    return model
+
+def prepare_img(filepath):
+    IMG_SIZE = 90
+    img_array = cv2.imread(filepath, cv2.IMREAD_GRAYSCALE)
+    new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))
+    return new_array.reshape(-1, IMG_SIZE, IMG_SIZE, 1) / 255
+
+def predict(model):
+    return model.predict([prepare_img('directory')])
+
+def reusult(prediction):
+    if prediction[0][0] >= 0.5:
+        print(math.ceil(prediction[0][0]))
+        print('No pepperoni')
+    elif prediction[0][0] < 0.5:
+        print(math.floor(prediction[0][0]))
+        print("Pepperoni")
+
+
+
+
+
+
+
+
+
+
+
+
+
 map = Map()
 waiter = Waiter([32, 32])
 
@@ -591,7 +683,7 @@ def main():
                 chair.render(display)
         key = pygame.key.get_pressed()
         left, middle, right = pygame.mouse.get_pressed()
-        if left:
+        if middle:
             waiterGo(mouseToNum())
         elif right:
             while True:
@@ -604,7 +696,7 @@ def main():
                 route = astar(map.get_arr(), (waiter.loc[1] // 32, waiter.loc[0] // 32), goal)
                 direction = [(x[1] - y[1], x[0] - y[0]) for x, y in zip(route[1:], route)]
                 break
-        elif middle:
+        elif left:
             if client.loc[0] in [64, 128, 192, 256, 352, 416, 480, 544]:
                 while True:
                     x = client.loc[1] - 32