"Hello world" for fastai – creating a model for MNIST
Now that you have set up your environment for fastai, it's time to run through an example. In this section, you will go through the process of creating a simple deep learning model trained on the MNIST dataset. This dataset consists of images of handwritten digits. The goal of the trained model is to predict the digit given an image. For example, we want the trained model to predict that the following digits are 6, 3, 9, and 6:
Figure 1.30 – Sample handwritten digits from the MNIST dataset
We won't be covering every detail of the fastai solution for MNIST in this section, but we will be running a complete example that demonstrates one of the key values of fastai—getting a powerful deep learning result with only a few lines of code. This example should also whet your appetite for the more advanced fastai examples that are coming in subsequent chapters.
