Deep learning capabilities are available in ArcGIS Pro through several tools and capabilities.
Model training
Before a deep learning model can be used to identify features or objects in an image, it must first be trained to recognize those objects. Training a deep learning model involves many of the same steps as when training a traditional machine learning image classification model. You must collect and provide training samples and input imagery; then train the model so that it learns to recognize those features or objects.
The Label Objects for Deep Learning pane is used to collect and generate labeled datasets to train a deep learning model. You can interactively identify and label objects in an image, and export the training data as the image chips, labels, and statistics required to train a model. If you have existing labeled vector or raster data, you can use the Export Training Data For Deep Learning geoprocessing tool to generate the training data needed for the next step.
The Train Deep Learning Model tool uses the exported training data to train a deep learning model. A number of model types and arguments are available to configure the training process.
Model inferencing
Model inferencing refers to the process of extracting information from an image using a trained model. The options for model inferencing in ArcGIS Pro are as follows:
- Detect objects—Generate bounding boxes around objects or features in an image to identify their location. Use the Detect Objects Using Deep Learning tool.
- Classify objects—Generate labels for features in an image to identify their class or category. Use the Classify Objects Using Deep Learning tool.
- Classify pixels—Generate a classified raster where each pixel belongs to a class or category. Use the Classify Pixels Using Deep Learning tool.
Exploratory analysis
The Object Detection exploratory analysis tool uses a trained deep learning model to recognize objects displayed in the current map or scene. Each identified feature is represented by a point feature with a location in the coordinate system of the map, attributes detailing the orientation and extent of the object, and its confidence value. The tool can work with any trained Faster R-CNN model and is designed for on-demand detection of objects in the active view.
Review results
After using a deep learning model, it's important that you review the results and assess the accuracy of the model.
Use the Attributes pane to review the results from your object-based inferencing (Classify Objects Using Deep Learningtool or Detect Objects Using Deep Learning tool). You can also use the Compute Accuracy For Object Detection tool to generate a table and report for accuracy assessment.