Java Deep Learning Cookbook

How it works...

In step 1, the parameters included are as follows:

• parentPathLabelGenerator—created during the data extraction stage (see the Extracting images from disk recipe in this chapter).
• channels—The number of color channels (default = 3 for RGB).
• ImageRecordReader(imageHeight, imageWidth, channels, parentPathLabelGenerator)—resize the actual image to the specified size (imageHeight, imageWidth) to reduce the data loading effort.
• The null attribute in the initialize() method is to indicate that we are not training transformed images.

In step 3, we use ImagePreProcessingScaler for min-max normalization. Note that we need to use both fit() and setPreProcessor() to apply normalization to the data.

For GPU-accelerated environments, ...