.

ForkliftAgent.py

@@ -103,7 +103,7 @@ class ForkliftAgent(AgentBase):
                 stations = dict(self.graph.packingStations)
                 if i.real_type == ItemType.SHELF:
                     packing_station = stations[PatchType.packingA]
-                elif i.real_type == ItemType.FRIDGE:
+                elif i.real_type == ItemType.REFRIGERATOR:
                     packing_station = stations[PatchType.packingB]
                 elif i.real_type == ItemType.DOOR:
                     packing_station = stations[PatchType.packingC]

GameModel.py

@@ -21,6 +21,8 @@ from decision.ActionType import ActionType
 from pathfinding.PathfinderOnStates import PathFinderOnStates, PathFinderState
 from util.PathByEnum import PathByEnum
 from util.PathDefinitions import GridLocation, GridWithWeights
+from imageClasification.Classificator import image_clasification
+
 
 
 class Phase(Enum):
@@ -188,13 +190,13 @@ class GameModel(Model):
 
     def recognise_item(self, item: Item):
         # TODO IMAGE PROCESSING
-        val = self.classificator.image_clasification(self.picture_visualization.img)
+        val = image_clasification(self.picture_visualization.img, self.classificator)
         print("VAL: {}".format(val))
 
         if val == ItemType.DOOR:
             item.guessed_type = ItemType.DOOR
-        elif val == ItemType.FRIDGE:
-            item.guessed_type = ItemType.FRIDGE
+        elif val == ItemType.REFRIGERATOR:
+            item.guessed_type = ItemType.REFRIGERATOR
         elif val == ItemType.SHELF:
             item.guessed_type = ItemType.SHELF
 

data/enum/ItemType.py

@@ -4,4 +4,4 @@ from enum import Enum
 class ItemType(Enum):
     DOOR = "door"
     SHELF = "shelf"
-    FRIDGE = "fridge"
+    REFRIGERATOR = "refrigerator"

imageClasification/Classificator.py

@@ -0,0 +1,23 @@
+import numpy as np
+import tensorflow as tf
+
+
+def image_clasification(image_path, model):
+    # loaded_model = keras.models.load_model("my_model")
+    class_names = ['door', 'refrigerator', 'shelf']
+
+    img = tf.keras.utils.load_img(
+        image_path, target_size=(180, 180)
+    )
+    img_array = tf.keras.utils.img_to_array(img)
+    img_array = tf.expand_dims(img_array, 0)  # Create a batch
+
+    predictions = model.predict(img_array)
+    score = tf.nn.softmax(predictions[0])
+    # print(
+    #     "This image most likely belongs to {} with a {:.2f} percent confidence."
+    #         .format(class_names[np.argmax(score)], 100 * np.max(score))
+    # )
+    return class_names[np.argmax(score)]
+
+

imageClasification/usedAssets/ClassificatorInside.py

@@ -9,7 +9,7 @@ from tensorflow.keras import layers
 from tensorflow.keras.models import Sequential
 
 
-class Classificator():
+class ClassificatorInside():
 
     def __init__(self, data_dir: str) -> None:
         super().__init__()

main.py

@@ -2,6 +2,7 @@ import random
 
 from mesa.visualization.ModularVisualization import ModularServer
 from mesa.visualization.modules import CanvasGrid
+from tensorflow import keras
 
 from ForkliftAgent import ForkliftAgent
 from GameModel import GameModel
@@ -9,7 +10,6 @@ from PatchAgent import PatchAgent
 from PatchType import PatchType
 from PictureVisualizationAgent import PictureVisualizationAgent
 from data.enum.Direction import Direction
-from imageClasification.Classificator import Classificator
 from util.PathDefinitions import GridWithWeights
 from visualization.DisplayAttributeElement import DisplayAttributeElement
 from visualization.DisplayItemListAttribute import DisplayItemListAttributeElement
@@ -88,13 +88,13 @@ if __name__ == '__main__':
     ordersText = DisplayOrderList("orderList")
     fulfilled_orders = DisplayOrderList("fulfilled_orders")
 
-    classificator = Classificator("imageClasification/images")
+    loaded_model = keras.models.load_model("./imageClasification/my_model")
 
     server = ModularServer(GameModel,
                            [grid, readyText, provided_itesm, recognised_items, ordersText,
                             fulfilled_orders],
                            "Automatyczny Wózek Widłowy",
-                           dict(width=gridHeight, height=gridWidth, graph=diagram, items=50, orders=3, classificator=classificator))
+                           dict(width=gridHeight, height=gridWidth, graph=diagram, items=50, orders=3, classificator=loaded_model))
 
     server.port = 8888
     server.launch()

util/PathByEnum.py

@@ -9,7 +9,7 @@ class PathByEnum:
         if item == ItemType.DOOR:
             a = str(random.randint(1, 10))
             return "item_images/door/drzwi" + a + ".jpg"
-        if item == ItemType.FRIDGE:
+        if item == ItemType.REFRIGERATOR:
             a = str(random.randint(1, 10))
             return "item_images/refrigerator/lodowka" + a + ".jpg"
         if item == ItemType.SHELF: