Exploring a curated image location dataset

Back in Chapter 2, Exploring and Cleaning Up Data with fastai, we went through the process of ingesting and exploring a variety of datasets using fastai.

In this section, we are going to explore a special curated image dataset called COCO_TINY. This is an image location dataset. Unlike the CIFAR dataset that we used in the Training a classification model with a simple curated vision dataset recipe, which had a single labeled object in each image, the images in image location datasets are labeled with bounding boxes (which indicate where in the image a particular object occurs) as well as the name of the object. Furthermore, images in the COCO_TINY dataset can contain multiple labeled objects, as shown here:

Figure 6.17 – Labeled image from an image location dataset

In the recipe in this section, we'll ingest the dataset and apply its annotation information to create a dataloaders object for the dataset...