Modeling Guides

The following documents describe the various modeling features provided by the MLTK.
For complete tutorials, please see the Tutorials.

• Model Profiler - Provides information about how efficiently a model may run on an embedded target

• Model Profiler Utility - Standalone model profiler executable with webpage interface

• Model Visualizer - View an ML model in an interactive webpage

• Model Specification - Specify everything needed to create, train, and evaluate a machine learning model

• Model Training - Train a Machine Learning model using the MLTK and Google Tensorflow

• Model Evaluation - Evaluate the accuracy of a trained model

• Model Quantization - Reduce memory usage by compressing model weights

• Model Parameters - Embed custom parameters into the generated model file

• Model Summary - Generate a text summary of a model

• Model Archive - Store model information in a distributable archive

• Model Search Path - Configure how models are found by the MLTK commands and APIs