Scaling a dataset to improve model accuracy

Scaling a dataset is the process of ensuring that the variables are confined to a finite range. In this section, we will confine the independent variables’ values to between 0 and 1 by dividing each input value by the maximum possible value in the dataset. This is a value of 255, which corresponds to white pixels:

For brevity’s sake, we have only provided the modified code (from the previous section) in the upcoming code. The full code can be found in the Scaling_the_dataset.ipynb file located in the Chapter03 folder on GitHub at https://bit.ly/mcvp-2e.

1. Fetch the dataset, as well as the training images and targets, as we did in the previous section.
2. Modify FMNISTDataset, which fetches data, so that the input image is divided by 255 (the maximum intensity/value of a pixel):

   class FMNISTDataset(Dataset):
       def __init__(self, x, y):
           x = x.float()/255
           x = x.view(-1,28*28...