TF Lite Object Detection Model with Metadata
Explore how to include metadata in TF Lite object detection models using the Metadata Writer API. Understand the role of metadata in model inputs, outputs, and labels, and learn to extract associated files for Android app integration. This lesson equips you to prepare models for efficient use with TF Lite Task Library and ML Kit.
We'll cover the following...
Metadata refers to the data that describes other data or information. For DL models, metadata can include the model architecture, input and output details, training details, accuracy metrics, and label files. Let’s use TF Lite Metadata Writer API to include the metadata to an existing object detection TF Lite model.
TF Lite model metadata
TF Lite model metadata is a self-descriptive format that contains information about the model, its inputs and outputs, and associated files.
Note: To enable model inference using either TF Lite Task ...