Deep Learning with R Cookbook

There's more...

There are mainly three ways to implement transfer learning:

• Use a pre-trained model with pre-realized weights and biases; that is, completely freeze the pre-trained model of your network and train on a new dataset.
• Partially freeze a few layers of the pre-trained model of our network and train it on a new dataset.
• Retain only the architecture of the pre-trained model and train your complete network for new weights and biases.

The following code snippet demonstrates how to partially freeze the pre-trained part of the network. Before we unfreeze selected layers of the pre-trained network, we must define the holistic model and freeze the pre-trained part:

unfreeze_weights(pre_trained_base, from = "block5_conv1", to = "block5_conv3") ...