A simple MNIST classifier showing PyTorch Lightning implementation
Introduction:
PyTorch Lightning is a library that provides a high-level interface for PyTorch. Problem with PyTorch is that every time you start a project you have to rewrite those training and testing loop. PyTorch Lightning fixes the problem by not only reducing boilerplate code but also providing added functionality that might come handy while training your neural networks. One of the things I love about Lightning is that the code is very organized and reusable, and not only that but it reduces the training and testing loop while retain the flexibility that PyTorch is known for. And once you learn how to use it you’ll see how similar the code is to that of PyTorch.