Update README.md

README.md

@@ -8,15 +8,12 @@ Base model: https://huggingface.co/google/vit-base-patch16-224
 
 * This achieves around 82% on the testing set
 
-
 Dataset Description: 
 
-The car dataset contains 16,185 images of 196 classes of cars. The data is split into 8,144 training images and 8,041 testing images. It is a popular choice in computer vision.
-
+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. 
 
 
 Citations: 
-
 3D Object Representations for Fine-Grained Categorization
 Jonathan Krause, Michael Stark, Jia Deng, Li Fei-Fei
 4th IEEE Workshop on 3D Representation and Recognition, at ICCV 2013 (3dRR-13). Sydney, Australia. Dec. 8, 2013.