What is torch.nn really?

PyTorch provides the elegantly designed modules and classes torch.nn , torch.optim , Dataset , and DataLoader to help you create and train neural networks. In order to fully utilize their power and customize them for your problem, you need to really understand exactly what they’re doing. To develop this understanding, we will first train basic neural net on the MNIST data set without using any features from these models; we will initially only use the most basic PyTorch tensor functionality. Then, we will incrementally add one feature from torch.nn, torch.optim, Dataset, or DataLoader at a time, showing exactly what each piece does, and how it works to make the code either more concise, or more flexible.