Exploring the CIFAR10 Dataset

This is the CIFAR10 dataset, which consists of 60000 32x32 px colour images in 10 classes. Here are some sample images from the dataset:

alt
import os
import torch
import torchvision
import tarfile
from torchvision.datasets.utils import download_url
from torch.utils.data import random_split
project_name='seminar-code-2'

The images are in PNG format from this page, using some helper functions from the torchvision and tarfile packages.

# Dowload the dataset
dataset_url = "https://s3.amazonaws.com/fast-ai-imageclas/cifar10.tgz"
download_url(dataset_url, '.')
HBox(children=(FloatProgress(value=0.0, max=135107811.0), HTML(value='')))