6 Training the Model and Running Experiments
This chapter covers
- An overview of the end-to-end training process
- Selecting subsets of the dataset for training the model, for validation during the training, and for testing the trained model
- Doing an initial training run
- Measuring the performance of your model
- Optimizing your training time by exploiting Keras’ early stopping feature
- Shortcuts to scoring
- Saving trained models
- Running a series of training experiments to improve model performance
So far in this book we have prepared the data and examined the code that makes up the model itself. Now we are finally ready to train the model. We’ll review some of the basics, including selecting the training, test and validation dataset. Then we’ll go through an initial training run to validate that the code functions without errors. Then we will cover the critical topic of how to monitor your model’s performance. Next, we’ll show you how to take advantage of the early stopping facility in Keras to get maximum benefit from your training runs. After that we will go over how you can quickly use your trained model to score a new record before you have the model fully deployed. Finally, we will a series of experiments to improve the performance of the deep learning model.