działający

.idea/workspace.xml

@@ -3,13 +3,9 @@
   <component name="ChangeListManager">
     <list default="true" id="56453584-72bd-49f4-a39c-fccf91ab20c6" name="Default Changelist" comment="">
       <change beforePath="$PROJECT_DIR$/.idea/workspace.xml" beforeDir="false" afterPath="$PROJECT_DIR$/.idea/workspace.xml" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/astar.py" beforeDir="false" afterPath="$PROJECT_DIR$/astar.py" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/cart.py" beforeDir="false" afterPath="$PROJECT_DIR$/cart.py" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/graph.py" beforeDir="false" afterPath="$PROJECT_DIR$/graph.py" afterDir="false" />
       <change beforePath="$PROJECT_DIR$/neuralnetwork.py" beforeDir="false" afterPath="$PROJECT_DIR$/neuralnetwork.py" afterDir="false" />
       <change beforePath="$PROJECT_DIR$/plant.py" beforeDir="false" afterPath="$PROJECT_DIR$/plant.py" afterDir="false" />
       <change beforePath="$PROJECT_DIR$/py.py" beforeDir="false" afterPath="$PROJECT_DIR$/py.py" afterDir="false" />
-      <change beforePath="$PROJECT_DIR$/treelearn.py" beforeDir="false" afterPath="$PROJECT_DIR$/treelearn.py" afterDir="false" />
     </list>
     <option name="SHOW_DIALOG" value="false" />
     <option name="HIGHLIGHT_CONFLICTS" value="true" />
@@ -161,6 +157,13 @@
       <workItem from="1622471028909" duration="34000" />
       <workItem from="1622471098158" duration="2320000" />
       <workItem from="1622474297862" duration="2475000" />
+      <workItem from="1622482225447" duration="322000" />
+      <workItem from="1622483723661" duration="2000" />
+      <workItem from="1622484196227" duration="4095000" />
+      <workItem from="1622490223156" duration="88000" />
+      <workItem from="1622490315073" duration="1038000" />
+      <workItem from="1622491366806" duration="5374000" />
+      <workItem from="1622499624637" duration="5901000" />
     </task>
     <servers />
   </component>
@@ -168,65 +171,69 @@
     <option name="version" value="1" />
   </component>
   <component name="WindowStateProjectService">
-    <state x="414" y="195" key="#com.intellij.execution.impl.EditConfigurationsDialog" timestamp="1622365181713">
+    <state x="414" y="195" key="#com.intellij.execution.impl.EditConfigurationsDialog" timestamp="1622503192333">
       <screen x="0" y="0" width="1920" height="1080" />
     </state>
-    <state x="414" y="195" key="#com.intellij.execution.impl.EditConfigurationsDialog/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622365181713" />
+    <state x="414" y="195" key="#com.intellij.execution.impl.EditConfigurationsDialog/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622503192333" />
     <state x="628" y="343" key="#com.intellij.fileTypes.FileTypeChooser" timestamp="1622475063488">
       <screen x="0" y="0" width="1920" height="1080" />
     </state>
     <state x="628" y="343" key="#com.intellij.fileTypes.FileTypeChooser/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622475063488" />
     <state x="628" y="343" key="#com.intellij.fileTypes.FileTypeChooser/0.0.1920.1080@0.0.1920.1080" timestamp="1621109431051" />
-    <state x="690" y="287" key="#com.intellij.refactoring.safeDelete.UnsafeUsagesDialog" timestamp="1622413487618">
+    <state x="690" y="287" key="#com.intellij.refactoring.safeDelete.UnsafeUsagesDialog" timestamp="1622503875969">
       <screen x="0" y="0" width="1920" height="1080" />
     </state>
-    <state x="690" y="287" key="#com.intellij.refactoring.safeDelete.UnsafeUsagesDialog/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622413487618" />
+    <state x="690" y="287" key="#com.intellij.refactoring.safeDelete.UnsafeUsagesDialog/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622503875969" />
     <state x="690" y="287" key="#com.intellij.refactoring.safeDelete.UnsafeUsagesDialog/0.0.1920.1080@0.0.1920.1080" timestamp="1621429221570" />
-    <state width="1879" height="295" key="GridCell.Tab.0.bottom" timestamp="1622477545943">
+    <state width="1879" height="295" key="GridCell.Tab.0.bottom" timestamp="1622505570694">
       <screen x="0" y="0" width="1920" height="1080" />
     </state>
-    <state width="1879" height="295" key="GridCell.Tab.0.bottom/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622477545943" />
+    <state width="1879" height="295" key="GridCell.Tab.0.bottom/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622505570694" />
     <state width="1879" height="295" key="GridCell.Tab.0.bottom/0.0.1920.1080@0.0.1920.1080" timestamp="1621429389327" />
-    <state width="1879" height="295" key="GridCell.Tab.0.center" timestamp="1622477545943">
+    <state width="1879" height="295" key="GridCell.Tab.0.center" timestamp="1622505570694">
       <screen x="0" y="0" width="1920" height="1080" />
     </state>
-    <state width="1879" height="295" key="GridCell.Tab.0.center/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622477545943" />
+    <state width="1879" height="295" key="GridCell.Tab.0.center/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622505570694" />
     <state width="1879" height="295" key="GridCell.Tab.0.center/0.0.1920.1080@0.0.1920.1080" timestamp="1621429389327" />
-    <state width="1879" height="295" key="GridCell.Tab.0.left" timestamp="1622477545943">
+    <state width="1879" height="295" key="GridCell.Tab.0.left" timestamp="1622505570694">
       <screen x="0" y="0" width="1920" height="1080" />
     </state>
-    <state width="1879" height="295" key="GridCell.Tab.0.left/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622477545943" />
+    <state width="1879" height="295" key="GridCell.Tab.0.left/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622505570694" />
     <state width="1879" height="295" key="GridCell.Tab.0.left/0.0.1920.1080@0.0.1920.1080" timestamp="1621429389326" />
-    <state width="1879" height="295" key="GridCell.Tab.0.right" timestamp="1622477545943">
+    <state width="1879" height="295" key="GridCell.Tab.0.right" timestamp="1622505570694">
       <screen x="0" y="0" width="1920" height="1080" />
     </state>
-    <state width="1879" height="295" key="GridCell.Tab.0.right/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622477545943" />
+    <state width="1879" height="295" key="GridCell.Tab.0.right/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622505570694" />
     <state width="1879" height="295" key="GridCell.Tab.0.right/0.0.1920.1080@0.0.1920.1080" timestamp="1621429389327" />
-    <state width="1879" height="364" key="GridCell.Tab.1.bottom" timestamp="1619289752045">
+    <state width="1879" height="364" key="GridCell.Tab.1.bottom" timestamp="1622496797346">
       <screen x="0" y="0" width="1920" height="1080" />
     </state>
+    <state width="1879" height="364" key="GridCell.Tab.1.bottom/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622496797346" />
     <state width="1879" height="364" key="GridCell.Tab.1.bottom/0.0.1920.1080@0.0.1920.1080" timestamp="1619289752045" />
-    <state width="1879" height="364" key="GridCell.Tab.1.center" timestamp="1619289752045">
+    <state width="1879" height="364" key="GridCell.Tab.1.center" timestamp="1622496797346">
       <screen x="0" y="0" width="1920" height="1080" />
     </state>
+    <state width="1879" height="364" key="GridCell.Tab.1.center/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622496797346" />
     <state width="1879" height="364" key="GridCell.Tab.1.center/0.0.1920.1080@0.0.1920.1080" timestamp="1619289752045" />
-    <state width="1879" height="364" key="GridCell.Tab.1.left" timestamp="1619289752045">
+    <state width="1879" height="364" key="GridCell.Tab.1.left" timestamp="1622496797346">
       <screen x="0" y="0" width="1920" height="1080" />
     </state>
+    <state width="1879" height="364" key="GridCell.Tab.1.left/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622496797346" />
     <state width="1879" height="364" key="GridCell.Tab.1.left/0.0.1920.1080@0.0.1920.1080" timestamp="1619289752045" />
-    <state width="1879" height="364" key="GridCell.Tab.1.right" timestamp="1619289752045">
+    <state width="1879" height="364" key="GridCell.Tab.1.right" timestamp="1622496797346">
       <screen x="0" y="0" width="1920" height="1080" />
     </state>
+    <state width="1879" height="364" key="GridCell.Tab.1.right/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622496797346" />
     <state width="1879" height="364" key="GridCell.Tab.1.right/0.0.1920.1080@0.0.1920.1080" timestamp="1619289752045" />
-    <state x="0" y="0" key="com.intellij.ide.util.TipDialog" timestamp="1622474297784">
+    <state x="0" y="0" key="com.intellij.ide.util.TipDialog" timestamp="1622499624475">
       <screen x="0" y="0" width="1920" height="1080" />
     </state>
-    <state x="0" y="0" key="com.intellij.ide.util.TipDialog/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622474297784" />
+    <state x="0" y="0" key="com.intellij.ide.util.TipDialog/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622499624475" />
     <state x="0" y="0" key="com.intellij.ide.util.TipDialog/0.0.1920.1080@0.0.1920.1080" timestamp="1621439087317" />
-    <state x="623" y="235" width="672" height="678" key="search.everywhere.popup" timestamp="1622475419309">
+    <state x="623" y="235" width="672" height="678" key="search.everywhere.popup" timestamp="1622494466933">
       <screen x="0" y="0" width="1920" height="1080" />
     </state>
-    <state x="623" y="235" width="672" height="678" key="search.everywhere.popup/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622475419309" />
+    <state x="623" y="235" width="672" height="678" key="search.everywhere.popup/0.0.1920.1080/-1920.0.1920.1080@0.0.1920.1080" timestamp="1622494466933" />
   </component>
   <component name="XDebuggerManager">
     <breakpoint-manager>
@@ -240,7 +247,9 @@
     </breakpoint-manager>
   </component>
   <component name="com.intellij.coverage.CoverageDataManagerImpl">
+    <SUITE FILE_PATH="coverage/SmartCart$copy.coverage" NAME="copy Coverage Results" MODIFIED="1622503170538" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
+    <SUITE FILE_PATH="coverage/SmartCart$glue.coverage" NAME="glue Coverage Results" MODIFIED="1622501306368" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
     <SUITE FILE_PATH="coverage/SmartTractor$py.coverage" NAME="py Coverage Results" MODIFIED="1622469837941" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
-    <SUITE FILE_PATH="coverage/SmartCart$py.coverage" NAME="py Coverage Results" MODIFIED="1622475876802" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
+    <SUITE FILE_PATH="coverage/SmartCart$py.coverage" NAME="py Coverage Results" MODIFIED="1622505478603" SOURCE_PROVIDER="com.intellij.coverage.DefaultCoverageFileProvider" RUNNER="coverage.py" COVERAGE_BY_TEST_ENABLED="true" COVERAGE_TRACING_ENABLED="false" WORKING_DIRECTORY="$PROJECT_DIR$" />
   </component>
 </project>

neuralnetwork.py

@@ -4,12 +4,12 @@ from torch.optim import Adam
 from torch.utils.data import DataLoader
 from torchvision.transforms import transforms
 import glob
-import numpy as np
 import os
 import pathlib
 import torch
 import torch.nn as nn
 import torchvision
+transformer1 = transforms.Compose([transforms.Resize((150, 150)), transforms.ToTensor(), transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])])
 class ConvNet(nn.Module):
     def __init__(self, num_classes=6):
         super(ConvNet, self).__init__()
@@ -36,34 +36,27 @@ class ConvNet(nn.Module):
         output = output.view(-1, 32 * 75 * 75)
         output = self.fc(output)
         return output
-def create_neural_network():
-    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+def create_neural_network(): #tworzenie sieci neuronowej
+    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') #użyj cuda jeśli możliwe
     transformer = transforms.Compose([transforms.Resize((150, 150)), transforms.RandomHorizontalFlip(), transforms.ToTensor(), transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])])
-    train_path = os.path.join('resources/neural_network/train/')
-    test_path = os.path.join('resources/neural_network/test/')
-    pred_path = os.path.join('resources/neural_network/pred/')
+    train_path = os.path.join('resources/neural_network/train/') #ścieżka do obrazków do treningu
+    test_path = os.path.join('resources/neural_network/test/') #ścieżka do obrazków do testu
     train_loader = DataLoader(torchvision.datasets.ImageFolder(train_path, transform=transformer), batch_size=64, shuffle=True)
     test_loader = DataLoader(torchvision.datasets.ImageFolder(test_path, transform=transformer), batch_size=32, shuffle=True)
     root = pathlib.Path(train_path)
     classes = sorted([j.name.split('/')[-1] for j in root.iterdir()])
-    if os.path.exists("resources/neural_network/checkpoint.model"):
+    if os.path.exists("resources/neural_network/checkpoint.model"): #jeżeli istnieje model to wczytaj
         checkpoint = torch.load(os.path.join('resources/neural_network', 'checkpoint.model'))
         model = ConvNet(num_classes=6)
         model.load_state_dict(checkpoint)
         model.eval()
-        transformer1 = transforms.Compose([transforms.Resize((150, 150)), transforms.ToTensor(), transforms.Normalize([0.5, 0.5, 0.5], [0.5, 0.5, 0.5])])
-        images_path = glob.glob(pred_path+'/*.jpg')
-        pred_dict = {}
-        for i in images_path:
-            pred_dict[i[i.rfind('/') + 1:]] = prediction1(classes, i, model, transformer1)
-        print(pred_dict)
-    else:
+    else: #w przeciwnym razie utwórz nowy model
         model = ConvNet(num_classes=6).to(device)
         optimizer = Adam(model.parameters(), lr=0.001, weight_decay=0.0001)
         loss_function = nn.CrossEntropyLoss()
         num_epochs = 10
-        train_count = len(glob.glob(train_path + '/**/*.jpg'))
-        test_count = len(glob.glob(test_path + '/**/*.jpg'))
+        train_count = len(glob.glob(train_path + '/**/*.png')) #liczba obrazków treningowych
+        test_count = len(glob.glob(test_path + '/**/*.png')) #liczba obrazków testowych
         best_accuracy = 0.0
         for epoch in range(num_epochs):
             model.train()
@@ -97,8 +90,39 @@ def create_neural_network():
             if test_accuracy > best_accuracy:
                 torch.save(model.state_dict(), 'resources/neural_network/checkpoint.model')
                 best_accuracy = test_accuracy
-def prediction1(classes, img_path, model, transformer):
-    image = Image.open(img_path)
+        checkpoint = torch.load(os.path.join('resources/neural_network', 'checkpoint.model'))
+        model = ConvNet(num_classes=6)
+        model.load_state_dict(checkpoint)
+        model.eval()
+    return classes, model
+def predfield(classes, model): #zwraca miejsce pola z wyrośniętą rośliną na podstawie wykrywania obrazu
+    pred_path = os.path.join('resources/neural_network/sliced/') #ścieżka do obrazków do sprawdzenia
+    pred_dict = {}
+    images_path = glob.glob(pred_path + '/*.png')
+    x = None #x'owa pola
+    y = None#y'kowa  pola
+    for i in images_path: #dodajemy pocięte obrazki do listy i ustawiamy im przewidywaną metkę
+        pred_dict[i[i.rfind('/') + 1:]] = prediction1(classes, i, model, transformer1)
+    for img_name, field in pred_dict.items():
+        if field != "random": #jeżeli metka nie jest 'random' to przypisz do x'a i y'a miejsce wyrośniętej rośliny
+            x = img_name[15]
+            y = img_name[18]
+            x = int(x)
+            y = int(y)
+            if x == 0:
+                x = 9
+            else:
+                x = x - 1
+            if y == 0:
+                y = 9
+            else:
+                y = y - 1
+    if x == None and y == None: #jeżeli nie ma wyrośniętej rośliny to zwróć False
+        return False
+    else:
+        return y, x
+def prediction1(classes, img_path, model, transformer): #zwraca predykcję dla danego obrazka
+    image = Image.open(img_path).convert('RGB')
     image_tensor = transformer(image).float()
     image_tensor = image_tensor.unsqueeze_(0)
     if torch.cuda.is_available():

plant.py

@@ -12,30 +12,6 @@ class Plant:
     def set_state(self, state):
         self.state = state
     @staticmethod
-    def get_mature_plant(map):  #pobiera współrzędne jakiejś dojrzałej rośliny
-        x = -1
-        y = -1
-        for i in range(definitions.WIDTH_AMOUNT):
-            for j in range(definitions.HEIGHT_AMOUNT):
-                field = map.get_fields()[i][j]
-                if field.get_plant().get_name() == "beetroot" and field.get_plant().get_state() == definitions.BEETROOTS_MAXIMUM_STATE:
-                    x = i
-                    y = j
-                elif field.get_plant().get_name() == "carrot" and field.get_plant().get_state() == definitions.CARROTS_MAXIMUM_STATE:
-                    x = i
-                    y = j
-                elif field.get_plant().get_name() == "potato" and field.get_plant().get_state() == definitions.POTATOES_MAXIMUM_STATE:
-                    x = i
-                    y = j
-
-                elif field.get_plant().get_name() == "wheat" and field.get_plant().get_state() == definitions.WHEAT_MAXIMUM_STATE:
-                    x = i
-                    y = j
-        if x == -1 and y == -1:
-            return False
-        else:
-            return x, y
-    @staticmethod
     def grow_plants(map):  #metoda statyczna, która zwiększa pole state (etap rozwoju rośliny) dla danej rośliny na danym polu o 1
         for i in range(definitions.WIDTH_AMOUNT):
             for j in range(definitions.HEIGHT_AMOUNT):
@@ -47,18 +23,4 @@ class Plant:
                 elif field.get_plant().get_name() == "potato" and field.get_plant().get_state() > 0 and field.get_plant().get_state() < definitions.POTATOES_MAXIMUM_STATE:
                     field.get_plant().set_state(field.get_plant().get_state() + 1)
                 elif field.get_plant().get_name() == "wheat" and field.get_plant().get_state() > 0 and field.get_plant().get_state() < definitions.WHEAT_MAXIMUM_STATE:
-                    field.get_plant().set_state(field.get_plant().get_state() + 1)
-    @staticmethod
-    def if_any_mature_plant(map): #sprawdza czy na polu występuje choć jedna dojrzała roślina, jeśli tak zwraca prawdę, w przeciwnym razie zwraca fałsz
-        for i in range(definitions.WIDTH_AMOUNT):
-            for j in range(definitions.HEIGHT_AMOUNT):
-                field = map.get_fields()[i][j]
-                if field.get_plant().get_name() == "beetroot" and field.get_plant().get_state() == definitions.BEETROOTS_MAXIMUM_STATE:
-                    return True
-                elif field.get_plant().get_name() == "carrot" and field.get_plant().get_state() == definitions.CARROTS_MAXIMUM_STATE:
-                    return True
-                elif field.get_plant().get_name() == "potato" and field.get_plant().get_state() == definitions.POTATOES_MAXIMUM_STATE:
-                    return True
-                elif field.get_plant().get_name() == "wheat" and field.get_plant().get_state() == definitions.WHEAT_MAXIMUM_STATE:
-                    return True
-        return False
+                    field.get_plant().set_state(field.get_plant().get_state() + 1)

py.py

@@ -2,8 +2,10 @@ import astar
 import cart
 import definitions
 import graph
+import image_slicer
 import map
 import neuralnetwork
+import os
 import plant
 import pygame
 import station
@@ -23,7 +25,7 @@ def main():
     clock = pygame.time.Clock()
     tree = treelearn.treelearn() #tworzenie drzewa decyzyjnego
     decision = [0] #początkowa decyzja o braku powrotu do stacji (0)
-    #neuralnetwork.create_neural_network()
+    classes, model = neuralnetwork.create_neural_network() #uczenie sieci neuronowej
     run = True
     while run: #pętla główna programu
         clock.tick(definitions.FPS)
@@ -31,10 +33,13 @@ def main():
             if event.type == pygame.QUIT:
                 run = False
         map1.draw_window(cart1, cart1_rect)
-        if not move_list and plant.Plant.if_any_mature_plant(map1) is True: #jeżeli są jakieś ruchy do wykonania w move_list oraz istnieje jakaś dojrzała roślina
-            istate = graph.Istate(cart1.get_direction(), cart1.get_x() / definitions.BLOCK_SIZE, cart1.get_y() / definitions.BLOCK_SIZE) #stan początkowy wózka (jego orientacja oraz jego aktualne współrzędne)
+        pygame.image.save(pygame.display.get_surface(), os.path.join('resources/neural_network/sliced/', 'screen.jpg')) #zrzut obecnego ekranu
+        image_slicer.slice(os.path.join('resources/neural_network/sliced/', 'screen.jpg'), 100) #pocięcie ekranu na sto części
+        os.remove('resources/neural_network/sliced/screen.jpg')
+        if not move_list and neuralnetwork.predfield(classes, model) is not False: #jeżeli są jakieś ruchy do wykonania w move_list oraz istnieje jakaś dojrzała roślina
+            istate = graph.Istate(cart1.get_direction(), cart1.get_x() / definitions.BLOCK_SIZE, cart1.get_y() / definitions.BLOCK_SIZE) #stan początkowy wózka (jego orientacja oraz jego aktualne miejsce)
             if decision == [0]: #jeżeli decyzja jest 0 (brak powrotu do stacji) to uprawiaj pole
-                move_list = (astar.graphsearch([], astar.f, [], plant.Plant.get_mature_plant(map1), istate, map1, graph.succ))  #lista z ruchami, które należy po kolei wykonać, astar
+                move_list = (astar.graphsearch([], astar.f, [], neuralnetwork.predfield(classes, model), istate, map1, graph.succ))  #lista z ruchami, które należy po kolei wykonać, astar
             else:  #jeżeli decyzja jest 1 (powrót do stacji) to wróć do stacji uzupełnić zapasy
                 move_list = (graph.graphsearch([], [], (0, 0), istate, graph.succ)) #lista z ruchami, które należy po kolei wykonać, graphsearch
         elif move_list: #jeżeli move_list nie jest pusta