The fastai library provides several standard evaluation metrics for classification problems. But what if we want to use a custom metric instead? In this tutorial I show how to do this.
Not for every kind of image classification problem you will be able to find a ready-to-use training dataset online. In this blog post I show how to create an own training dataset of mushroom images using the Google Image Search.
This tutorial shows how to create predictions for test set images using the fastai library and how to submit these predictions to Kaggle using the Kaggle API.
People can get distracted in various ways while driving. This tutorial shows how to classify images of distracted drivers by the kind of distraction using the fastai library.