### Dataset: CIFAR-10

Section 3 in this technical report describes the CIFAR10 dataset and the methodology followed when collecting it in much greater detail. Please cite the following work in your report. 
*Learning Multiple Layers of Features from Tiny Images, Alex Krizhevsky, 2009.*

- 60,000 32x32 color images in 10 classes, with 6,000 images per class.
- Official split: 50,000 training + 10,000 testing.
- Classes: airplane, automobile, bird, cat, deer, dog, frog, horse, ship, truck.

```python
from torchvision.datasets import CIFAR10
train_set = CIFAR10(root='./data', train=True, download=True)
test_set = CIFAR10(root='./data', train=False, download=True)
```