Exercise

Calculating accuracy using torchmetrics

Tracking accuracy during training helps identify the best-performing epoch.

In this exercise, you'll use torchmetrics to calculate accuracy on a facemask dataset with three classes. The plot_errors function will highlight misclassified samples, helping you analyze model errors.

torchmetrics package is already imported. Model outputs are softmax probabilities, and labels are one-hot encoded vectors.

Instructions 1/2

undefined XP

1

2

Create a "multiclass" accuracy metric with three classes.
Calculate the accuracy for each batch of the dataloader.

.css-6su6fj{-webkit-flex-shrink:0;-ms-flex-negative:0;flex-shrink:0;}Exercise

Instructions 1/2

Exercise