When you've built a deep learning model using neural networks, you are left with the question of how well it can predict when presented with new data. Are the predictions made by the model accurate enough to be usable in a real-world scenario? In this chapter, we will look at how to measure the performance of your deep learning models. We'll also dive into tooling to monitor and debug your models.
By the end of this chapter, you'll have a solid understanding of different validation techniques you can use to measure the performance of your model. You'll also know how to use a tool such as TensorBoard to get into the details of your neural network. Finally, you will know how to apply different visualizations to ...
