diff --git a/DeepEncode.py b/DeepEncode.py
index fc7ba24..8c20ecd 100644
--- a/DeepEncode.py
+++ b/DeepEncode.py
@@ -7,10 +7,10 @@ from video_compression_model import VideoCompressionModel
 NUM_CHANNELS = 3
 
 # Step 2: Load the trained model
-model = tf.keras.models.load_model('ai_rate_control_model.keras', custom_objects={'VideoCompressionModel': VideoCompressionModel})
+model = tf.keras.models.load_model('models/model.keras', custom_objects={'VideoCompressionModel': VideoCompressionModel})
 
 # Step 3: Load the uncompressed video
-UNCOMPRESSED_VIDEO_FILE = 'test_video.mkv'
+UNCOMPRESSED_VIDEO_FILE = 'test_data/test_video.mkv'
 
 def load_frames_from_video(video_file, num_frames = 0):
     print("Extracting video frames...")
diff --git a/train_model.py b/train_model.py
index e3d961a..304c483 100644
--- a/train_model.py
+++ b/train_model.py
@@ -10,8 +10,8 @@ BATCH_SIZE = 32       # Batch size used during training
 EPOCHS = 20           # Number of training epochs
 
 # Step 1: Data Preparation
-TRAIN_VIDEO_FILE = 'native_video.mkv'  # The training video file name
-VAL_VIDEO_FILE = 'training_video.mkv'      # The validation video file name
+TRAIN_VIDEO_FILE = 'test_data/native_video.mkv'  # The training video file name
+VAL_VIDEO_FILE = 'test_data/training_video.mkv'      # The validation video file name
 TRAIN_SAMPLES = 2  # Number of video frames used for training
 VAL_SAMPLES = 2     # Number of video frames used for validation
 
@@ -77,5 +77,5 @@ model.fit(
 print("\nTraining completed.")
 
 # Step 3: Save the trained model
-model.save('ai_rate_control_model.keras')
+model.save('models/model.keras')
 print("Model saved successfully!")