diff --git a/image-classification/dlnd_image_classification.ipynb b/image-classification/dlnd_image_classification.ipynb
index 4828a51381..a0698b809c 100644
--- a/image-classification/dlnd_image_classification.ipynb
+++ b/image-classification/dlnd_image_classification.ipynb
@@ -765,7 +765,7 @@
     "    Test the saved model against the test dataset\n",
     "    \"\"\"\n",
     "\n",
-    "    test_features, test_labels = pickle.load(open('preprocess_training.p', mode='rb'))\n",
+    "    test_features, test_labels = pickle.load(open('preprocess_test.p', mode='rb'))\n",
     "    loaded_graph = tf.Graph()\n",
     "\n",
     "    with tf.Session(graph=loaded_graph) as sess:\n",
@@ -784,10 +784,10 @@
     "        test_batch_acc_total = 0\n",
     "        test_batch_count = 0\n",
     "        \n",
-    "        for train_feature_batch, train_label_batch in helper.batch_features_labels(test_features, test_labels, batch_size):\n",
+    "        for test_feature_batch, test_label_batch in helper.batch_features_labels(test_features, test_labels, batch_size):\n",
     "            test_batch_acc_total += sess.run(\n",
     "                loaded_acc,\n",
-    "                feed_dict={loaded_x: train_feature_batch, loaded_y: train_label_batch, loaded_keep_prob: 1.0})\n",
+    "                feed_dict={loaded_x: test_feature_batch, loaded_y: test_label_batch, loaded_keep_prob: 1.0})\n",
     "            test_batch_count += 1\n",
     "\n",
     "        print('Testing Accuracy: {}\\n'.format(test_batch_acc_total/test_batch_count))\n",
diff --git a/image-classification/helper.py b/image-classification/helper.py
index 71c8025d6d..40b69c95dc 100644
--- a/image-classification/helper.py
+++ b/image-classification/helper.py
@@ -102,17 +102,17 @@ def preprocess_and_save_data(cifar10_dataset_folder_path, normalize, one_hot_enc
     with open(cifar10_dataset_folder_path + '/test_batch', mode='rb') as file:
         batch = pickle.load(file, encoding='latin1')
 
-    # load the training data
+    # load the test data
     test_features = batch['data'].reshape((len(batch['data']), 3, 32, 32)).transpose(0, 2, 3, 1)
     test_labels = batch['labels']
 
-    # Preprocess and Save all training data
+    # Preprocess and Save all test data
     _preprocess_and_save(
         normalize,
         one_hot_encode,
         np.array(test_features),
         np.array(test_labels),
-        'preprocess_training.p')
+        'preprocess_test.p')
 
 
 def batch_features_labels(features, labels, batch_size):