Update README.md

README.md

@@ -10,7 +10,9 @@ This achieves around 82% on the testing set
 
 Dataset Description: 
 
-The Stanford car dataset contains 16,185 images of 196 classes of cars. The data is split into 8,144 training images, 6,041 testing images, and 2000 validation images. 
+The stanford car dataset contains 16,185 images of 196 classes of cars. The data is split into 8144 training images, 6,041 testing images, and 2000 validation images. 
+
+ <img src="https://ai.stanford.edu/~jkrause/cars/class_montage.jpg"> 
 
 Citations: 
 3D Object Representations for Fine-Grained Categorization