Using the Deep Learning Guide Map

The Deep Learning Guide Map facilitates your journey through ENVI Deep Learning. It highlights the tools you may want to use at each step, explaining why you might want to use them. It also keeps track of the results you will produce along the way (trained models, label rasters, classification rasters, etc.) so that you do not have to keep track of them when it is time to use them.

To get started, select Deep Learning > Deep Learning Guide Map in the ENVI Toolbox.

Click the various buttons based on what you want to do. Click the Back and Forward buttons to navigate to different steps. The Guide Map keeps track of all of the input and output files that you create throughout the process so that you do not have to manually specify them in each step.

The menu bar of the Guide Map provides additional capabilities:

Tools

• Edit TensorFlow model metadata

• Train deep learning models using the ENVI Modeler

• Randomize training parameters using the ENVI Modeler

• Test installation and configuration

Tasks

Access individual tasks whenever you need them, regardless of where you are in the Guide Map.

Training Metrics

View and manage training metrics.

Getting Started

The first panel of the Guide Map lets you select the type of model you want to create. See the following topics for additional details:

• Pixel Segmentation

• Object Detection