Evaluating a model - AWS DeepComposer

Evaluating a model

By examining trained models, you can learn what a useful model is and the features a model should include. You should always evaluate a model to understand the predictions that it generates. To evaluate a model, you can examine the changes in your model’s loss function over time and use the epoch explorer tool to examine the results at different epochs. In this topic, we look at what makes a good model and which hyperparameters are available for different models.

Important

We assume that you chose the hyperparameters as documented in training a custom MuseGAN model. If you chose another model or different hyperparameters, your results will differ from those shown in this topic.