The CIFAR-10 data consists of 60,000 32x32 color images in 10 classes, with 6000 images per class. There are 50,000 training images and 10,000 test images in the official data. We have preserved the train/test split from the original dataset. The provided files are: train_images.npy - a folder containing the training images in numpy format test_images.npy - a folder containing the test images in numpy format train_labels.csv - the training labels sample_submission.csv - a sample for how you submit the predicted labels on the test data To discourage certain forms of cheating (such as hand labeling) we have added 190,000 junk images in the test set. These images are ignored in the scoring. We have also made trivial modifications to the official 10,000 test images to prevent looking them up by file hash. These modifications should not appreciably affect the scoring. You should predict labels for all 200,000 images. The label classes in the dataset are: (airplane - automobile- bird - cat - deer - dog - frog - horse - ship - truck)