Hands-On Python Deep Learning for the Web

Improving the deep learning backend

The simple model we have trained here is hardly one that we can claim is close to a perfect model. There are several methods that we can use to extend this model to make it better. For instance, some of the most basic steps that we can take to improve our deep learning model are as follows:

• Increase training epochs: We have only trained our model for 10 epochs, which is usually a very small value for any deep learning model. Increasing the number of training epochs can improve the accuracy of the model. However, it can also lead to overfitting and so the number of epochs must be experimented with.
• More training samples: Our web client currently doesn't do much more than show the predicted value. However, ...