Training Logistic Regression with Cross-Entropy Loss in PyTorch
In the previous session of our PyTorch series, we demonstrated how badly initialized weights can impact the accuracy of a classification model when mean square error (MSE) loss is used. We noticed that the model didn’t converge during training and its accuracy was also significantly reduced.
In the following, you will see what happens if you randomly initialize the weights and use cross-entropy as loss function for model training. This loss function fits logistic regression and other categorical classification problems better. Therefore, cross-entropy loss is used for most of the classification problems today.
In this tutorial, you will train a logistic regression model using cross-entropy loss and make predictions on test data. Particularly, you will learn:
- How to train