Deep Learning with PyTorch

Model ensembling

There could be times when we would need to try to combine multiple models to build a very powerful model. There are many techniques that can be used for building an ensemble model. In this section, we will learn how to combine outputs using the features generated by three different models (ResNet, Inception, and DenseNet) to build a powerful model. We will be using the same dataset that we used for other examples in this chapter.

The architecture for the ensemble model would look like this:

This image shows what we are going to do in the ensemble model, which can be summarized in the following steps:

1. Create three models