Apache Spark Deep Learning Cookbook

How to do it...

This section explains how the process of transfer learning works.

1. Collect a series of datasets or images that you are interested in classifying, just as you would with traditional machine learning or deep learning.
2. Split the dataset into a training and testing split such as 75/25 or 80/20. 
3. Identify a pre-trained model that will be used to identify the patterns and recognition of the images you are looking to classify.
4. Build a deep learning pipeline that connects the training data to the pre-trained model and develops the weights and parameters needed to identify the test data.
5. Finally, evaluate the model performance on the test data.