diff --git a/Network.py b/Network.py
index d82394b..1eb259b 100644
--- a/Network.py
+++ b/Network.py
@@ -9,9 +9,12 @@ import PIL
 import PIL.Image
 import numpy
 
+
+def normalize(image, label):
+    return image / 255, label
+
 # Set the paths to the folders containing the training data
 train_data_dir = "Training/"
-validation_data_dir = "Validation/"
 
 
 # Set the number of classes and batch size
@@ -20,7 +23,7 @@ batch_size = 32
 
 # Set the image size and input shape
 img_width, img_height = 100, 100
-input_shape = (img_width, img_height, 3)
+input_shape = (img_width, img_height, 1)
 
 train_ds = tf.keras.utils.image_dataset_from_directory(
   train_data_dir,
@@ -42,3 +45,36 @@ val_ds = tf.keras.utils.image_dataset_from_directory(
 
 class_names = train_ds.class_names
 print(class_names)
+
+train_ds = train_ds.map(normalize)
+val_ds = val_ds.map(normalize)
+
+# Define the model architecture
+model = tf.keras.Sequential([
+    layers.Conv2D(16, 3, padding='same', activation='relu', input_shape=(img_height, img_width, 1)),
+    layers.MaxPooling2D(),
+    layers.Conv2D(32, 3, padding='same', activation='relu'),
+    layers.MaxPooling2D(),
+    layers.Conv2D(64, 3, padding='same', activation='relu'),
+    layers.MaxPooling2D(),
+    layers.Flatten(),
+    layers.Dense(128, activation='relu'),
+    layers.Dense(num_classes, activation='softmax')
+])
+
+# Compile the model
+model.compile(optimizer='adam',
+              loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True),
+              metrics=['accuracy'])
+
+model.summary()
+
+
+epochs=10
+# Train the model
+model.fit(train_ds,
+          validation_data=val_ds,
+          epochs=epochs)
+
+# Save the trained model
+model.save('trained_model.h5')
diff --git a/Tester2.py b/Tester2.py
new file mode 100644
index 0000000..f6dd52e
--- /dev/null
+++ b/Tester2.py
@@ -0,0 +1,38 @@
+import os
+import numpy as np
+import tensorflow as tf
+from tensorflow import keras
+
+train_data_dir = "Training/"
+
+train_ds = tf.keras.utils.image_dataset_from_directory(train_data_dir, validation_split=0.2,
+                                                       subset="training", seed=123, batch_size=32, image_size=(100, 100))
+val_ds = tf.keras.utils.image_dataset_from_directory(train_data_dir, validation_split=0.2,
+                                                     subset="validation", seed=123, batch_size=32, image_size=(100, 100))
+
+model = keras.models.load_model("trained_model")
+predictions = model.predict(val_ds.take(32))
+
+
+classNames = ['Empty', 'Food','People']
+
+# Make predictions
+direct = ''
+i = 0
+for image, _ in val_ds.take(32):
+    predicted_class_index = np.argmax(predictions[i])
+    predicted_class = classNames[predicted_class_index]
+    filename = predicted_class + str(i) + '.jpeg'
+    tf.keras.preprocessing.image.save_img(direct+filename, image[0])
+    print('Predicted class:', predicted_class)
+    i += 1
+
+#direct = ''
+
+#i = 0
+#for image, _ in val_ds.take(32):
+#    predictedLabel = int(predictions[i] >= 0.5)
+#
+#    filename = classNames[predictedLabel] + str(i) + '.jpeg'
+#    tf.keras.preprocessing.image.save_img(direct+filename, image[0])
+#    i += 1
\ No newline at end of file