Neural Network - #4

TesterRandom.py

@@ -11,23 +11,52 @@ model = keras.models.load_model('trained_model.h5')
 class_names = ['Empty', 'Food','People']
 
 # Path to the folder containing test images
-test_images_folder = 'Testing/
+test_images_folder = 'Testing/'
 
 # Iterate over the test images
-for filename in os.listdir(test_images_folder):
+i = 0
-    if filename.endswith('.jpg') or filename.endswith('.jpeg') or filename.endswith('.png'):
+errorcount = 0
-        # Load and preprocess the test image
+for folder_name in os.listdir(test_images_folder):
-        image_path = os.path.join(test_images_folder, filename)
+    folder_path = os.path.join(test_images_folder, folder_name)
-        test_image = image.load_img(image_path, target_size=(224, 224))
+    if os.path.isdir(folder_path):
-        test_image = image.img_to_array(test_image)
+        print('Testing images in folder:', folder_name)
-        test_image = np.expand_dims(test_image, axis=0)
-        test_image = test_image / 255.0  # Normalize the image
         
-        # Make predictions
+        # True class based on folder name
-        predictions = model.predict(test_image)
+        if folder_name == 'Empty':
-        predicted_class_index = np.argmax(predictions[0])
+            true_class = 'Empty'
-        predicted_class = class_names[predicted_class_index]
+        elif folder_name == 'Food':
+            true_class = 'Food'
+        elif folder_name == 'People':
+            true_class = 'People'
+        true_class = folder_name
         
-        print('Image:', filename)
+        # Iterate over the files in the subfolder
-        print('Predicted class:', predicted_class)
+        for filename in os.listdir(folder_path):
-        print()
+            if filename.endswith('.jpg') or filename.endswith('.jpeg'):
+                i+=1
+                # Load and preprocess the test image
+                image_path = os.path.join(folder_path, filename)
+                test_image = image.load_img(image_path, target_size=(100, 100))
+                test_image = image.img_to_array(test_image)
+                test_image = np.expand_dims(test_image, axis=0)
+                test_image = test_image / 255.0  # Normalize the image
+            
+                # Reshape the image array to (1, height, width, channels)
+                test_image = np.reshape(test_image, (1,100, 100, 3))
+            
+                # Make predictions
+                predictions = model.predict(test_image)
+                predicted_class_index = np.argmax(predictions[0])
+                predicted_class = class_names[predicted_class_index]
+                
+                direct = 'Results/'
+                filename = str(i) + predicted_class  + '.jpeg'
+                test_image = np.reshape(test_image, (100, 100, 3))
+                tf.keras.preprocessing.image.save_img(direct+filename, test_image)
+                if predicted_class != true_class:
+                    errorcount += 1
+                print('Image:', filename)
+                print('True class:', true_class)
+                print('Predicted class:', predicted_class)
+                print()
+print('Error count: ', errorcount)

testerZBS.py

@@ -47,7 +47,7 @@ for i in range(60):
 
     direct = 'Results/'
     filename = predicted_class + str(i) + '.jpeg'
-    tf.keras.preprocessing.image.save_img(direct+filename, val_images[i])
+    tf.keras.preprocessing.image.save_img(direct+filename, test_image)
     if predicted_class != true_class:
         errorcount += 1
     print('Image', i+1)