From 7551296681e6b150bd81749b0e6e41cca5e7e34c Mon Sep 17 00:00:00 2001
From: Aniela <walczakaniela116@gmail.com>
Date: Mon, 30 May 2022 17:56:30 +0200
Subject: [PATCH] Losowanie trzech liczb i tworzenie z nich liczby trzycyfrowej

---
 main.py           |  3 ++-
 neural_network.py | 35 +++++++++++++++++++++++------------
 2 files changed, 25 insertions(+), 13 deletions(-)

diff --git a/main.py b/main.py
index b64e9bd..b2c72f4 100644
--- a/main.py
+++ b/main.py
@@ -125,6 +125,7 @@ def main():
         if krata_magazynu.agent.cel is None:
             nadaj_cel_agentowi(krata_magazynu.agent)
             krata_magazynu.agent.idzDoCelu()
+            recognition()
 
         if flaga1 == 1:
             osoba.krata.krata[osoba.wiersz][osoba.kolumna] = ZawartoscPola.PUSTE
@@ -146,7 +147,7 @@ def main():
                 pygame.time.wait(1500)
             flaga1 = 0
             t = threading.Timer(5.0, zdarzenie_osoba).start()
-        recognition()
+
 
 try:
     main()
diff --git a/neural_network.py b/neural_network.py
index 04e4860..5e49146 100644
--- a/neural_network.py
+++ b/neural_network.py
@@ -5,6 +5,7 @@ import matplotlib.pyplot as plt
 import tensorflow as tf
 import random
 
+
 mnist = tf.keras.datasets.mnist
 (x_train, y_train), (x_test, y_test) = mnist.load_data()
 
@@ -12,32 +13,42 @@ x_train = tf.keras.utils.normalize(x_train, axis=1)
 x_test = tf.keras.utils.normalize(x_test, axis=1)
 
 model = tf.keras.models.Sequential()
-model.add(tf.keras.layers.Flatten(input_shape=(28, 28)))
+model.add(tf.keras.layers.Flatten(input_shape=(28,28)))
 model.add(tf.keras.layers.Dense(128, activation='relu'))
 model.add(tf.keras.layers.Dense(128, activation='relu'))
 model.add(tf.keras.layers.Dense(10, activation='softmax'))
 
-model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])
+model.compile(optimizer ='adam', loss = 'sparse_categorical_crossentropy', metrics = ['accuracy'])
 
-model.fit(x_train, y_train, epochs=3)
+model.fit(x_train, y_train, epochs = 3)
 model.save('handwritten.model')
 
 model = tf.keras.models.load_model('handwritten.model')
-
+numery_paczek=[]
 def recognition():
-    image_number = random.randint(1, 9)
+    digits=[]
     try:
-        img = cv2.imread(f"digits/digit{image_number}.png")[:,:,0]
-        img = np.invert(np.array([img]))
-        prediction = model.predict(img)
-        print(f"This digit is probably a {np.argmax(prediction)}")
-        plt.imshow(img[0], cmap = plt.cm.binary)
-        plt.show()
+        for i in range(0,3):
+            image_number = random.randint(1, 19)
+            img = cv2.imread(f"digits/digit{image_number}.png")[:,:,0]
+            img = np.invert(np.array([img]))
+            prediction = model.predict(img)
+            print(f"This digit is probably a {np.argmax(prediction)}")
+            digits.append(np.argmax(prediction))
+            plt.imshow(img[0], cmap = plt.cm.binary)
+            plt.show()
     except:
         print("Error!")
 
+    liczba = int(str(digits[0]) + str(digits[1])+str(digits[2]))
+    if liczba in numery_paczek or liczba<100:
+        recognition()
+    else:
+        numery_paczek.append(liczba)
+    print(liczba)
     loss, accuracy = model.evaluate(x_test, y_test)
-
     print(loss)
     print(accuracy)
+    print(numery_paczek)
+    return liczba
 recognition()
\ No newline at end of file