Training a classification model with a standalone vision dataset

In the Training a classification model with a simple curated vision dataset recipe, you went through the steps to ingest a fastai curated dataset and use it to train an image classification model.

In this section, you will go through the same process for a standalone dataset called fruits-360. This dataset (described in more detail here: https://www.kaggle.com/moltean/fruits) contains over 90,000 images of fruits and vegetables organized into over 130 categories.

In this recipe, we'll begin by bringing this dataset into Gradient. Then we will work through the training_with_standalone_image_datasets.ipynb notebook to ingest the dataset and use it to train a fastai image classification model. Finally, we will see how well the trained model classifies images from the test set and save the trained model.

Getting ready

Ensure that you have uploaded the fruits-360 dataset to your Gradient environment by following...