Core Concepts

All You Need to Know

You do not need to be an expert in AI research to develop or deploy ML models. NatML focuses on making ML deployment as painless as possible for interactive media developers. We have a separate project which focuses on making the model development process accessible and seamless.

Across both aspects, it is crucial to understand a few core concepts, and how they interact with one another. These concepts are:

  • Models

  • Features

  • Predictors

Models

An ML model is a 'black box' which receives one or more features and outputs one or more features. For example, a vision classifier receives an image feature and produces a probability distribution feature, telling you how likely the image is one label or another.

Under the hood, an ML model is a computation graph. This graph is what empowers ML models with the ability to learn and make predictions on new data.

NatML is built on the open-source ONNX specification. This is a concise format that allows for easy exchange of models, and wholly describes the input data, output data, and all intermediates required to execute the model. NatML allows you to instantiate models from ONNX files like so:

// Fetch the model data from a file
var modelData = MLModelData.FromFile("/path/to/model.onnx");
// Deserialize the model
var model = modelData.Deserialize();

Features

A feature is any data that can be produced or consumed by an MLModel. For example, you will use a lot of image features when working with vision models. NatML has built-in support for common features that might be used with ML models, including Texture2D and WebCamTexture instances:

// Some common feature types include:
float[] arrayFeature = ...;
Texture2D imageFeature = ...;
WebCamTexture webCamFeature = ...;
AudioClip audioFeature = ...;

Every MLFeature has a corresponding MLFeatureType. This type describes the feature and data that is contained within it. Similarly, every MLModel has a set of input and output feature types, describing what data the model can consume and produce, respectively.

Predictors

Predictors are lightweight primitives that use one or more models to make predictions on features. They are self-contained units that know how to transform inputs into a format that a model expects. But more importantly, they are able to transform outputs of a model into a usable format. For example, NatML includes a predictor for using image classification models:

var labels = new [] { "cat", "dog", ... };
var predictor = new MLClassificationPredictor(model, labels);

Whereas a standard classification model outputs a probability distribution, the classification predictor can transform this distribution into a form which is much more usable by developers. It simply returns a class label (string) along with a classification score (float):

var (label, confidence) = predictor.Predict(...);
Debug.Log($"Model predicted {label} with confidence {confidence}");

You can create custom predictors for different models, share them on NatML Hub!