Test your knowledge

Of the four application areas that fastai explicitly supports (tabular, text, recommender systems, and image/vision), fastai provides the most thorough support for creating models that work with image datasets. In this chapter, we have just scratched the surface of what you can do with fastai and image datasets. In this section, you will get a chance to dig a bit deeper into one of the fastai image dataset recipes from this chapter.

Getting ready

Ensure that you have followed the Training a multi-image classification model with a curated vision dataset recipe. In this section, you will be adapting the notebook you worked through in that recipe to try some new variations on deep learning with image datasets.

How to do it…

You can follow the steps in this section to try some variations on the image classification model that you trained with the PASCAL_2007 dataset in the Training a multi-image classification model with a curated vision dataset recipe...