Mastering the init method
In PyTorch Lightning, the __init__ method is the heart of your LightningModule setup. It's where you define model layers, parameters, and any initial configuration before training. By cleanly separating this setup step, PyTorch Lightning makes it easier to maintain and scale your projects. In this exercise, you'll focus on initializing the class for your classification model.
This exercise is part of the course
Scalable AI Models with PyTorch Lightning
Exercise instructions
- Create a class named
ClassifierModelthat inherits frompl.LightningModule. - Initialize the parent class to leverage LightningModule's capabilities.
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
import lightning.pytorch as pl
import torch.nn as nn
# Create the class
class ClassifierModel(____):
# Create init method
def __init__(self, input_dim, output_dim):
____
self.classifier = nn.Linear(input_dim, output_dim)