PyTorch Lightning template for MNIST Classification problem

• Add learning rate scheduler and logger
• Add custom callback class
• Add early stopping callback
• Add Model Checkpoint
• Add TensorBoard for visualisation metric
• Show how to training, validation, testing, and inference the model

READ THIS QUICK START PAGE

Lightning is a way to organize your PyTorch code to decouple the science code from the engineering. It's more of a PyTorch style-guide than a framework.

In Lightning, you organize your code into 3 distinct categories:

1. Research code (goes in the LightningModule).
2. Engineering code (you delete, and is handled by the Trainer).
3. Non-essential research code (logging, etc... this goes in Callbacks).

Here's an example of how to refactor your research code into a LightningModule.

The rest of the code is automated by the Trainer!

Everything in Blue! This is how lightning separates the science (red) from engineering (blue).

Although your research/production project might start simple, once you add things like GPU AND TPU training, 16-bit precision, etc, you end up spending more time engineering than researching. Lightning automates AND rigorously tests those parts for you.

pip install pytorch-lightning

pl_mnist.ipynb

👤 Ruben Stefanus

• Website: Ruben Stefanus
• Twitter: @mindbelowink
• Github: @rubentea16
• LinkedIn: @rubenstefanus

Give a ⭐️ if this project helped you!