Unit 2 Exercises

Exercise 1: Introducing More PyTorch Functions To Make Your Code More Efficient

The goal of this exercise is to simplify the code implementation of the Perceptron class. For this, we are going to use the torch.where function for the forward method.

Your task is to learn about torch.where using the PyTorch documentation. Finding torch.where in the API documentation is part of this exercise :).

Then, using torch.where, make the appropriate changes in the forward method as instructed in the notebook below.

Link to exercise notebook: https://github.com/Lightning-AI/dl-fundamentals/blob/main/unit02-pytorch-tensors/exercises/1_torch-where/exercise_1_torch-where.ipynb

Exercise 2: Make the Perceptron More Efficient Using Matrix Multiplication

In this exercise, you are going to modify the Perceptron class such that it creates the predictions for multiple input examples all at once.

Link to exercise notebook: https://github.com/Lightning-AI/dl-fundamentals/blob/main/unit02-pytorch-tensors/exercises/2_perceptron-matmul/exercise_2_perceptron-matmul.ipynb

Watch Video 1