# MLModel

The `MLModel` class abstracts a machine learning model, containing a computation graph for making predictions along with feature type information and metadata.

## Inspecting Feature Types

Models provide information about their expected input and output feature types. This type information is crucial for writing model predictors.

### Input Features

```csharp
/// <summary>
/// Model input feature types.
/// </summary>
MLFeatureType[] inputs { get; }
```

The model provides its expected input feature types. This information is crucial in order to create input features for predictions. Typically, a predictor will handle any necessary conversions of your input feature so that it matches the type that the model expects.

{% hint style="info" %}
The `inputs` are reported in the same order that they are expected by the model when making predictions.
{% endhint %}

### Output Features

```csharp
/// <summary>
/// Model output feature types.
/// </summary>
MLFeatureType[] outputs { get; }
```

The model provides its output feature types. This information is crucial in order to convert the model's raw outputs into more usable forms by predictors.

{% hint style="info" %}
The `outputs` are reported in the same order that they are produced by the model when making predictions.
{% endhint %}

## Inspecting Metadata

```csharp
/// <summary>
/// Get the model metadata dictionary.
/// </summary>
IReadOnlyDictionary<string, string> metadata { get; }
```

Models expose metadata that was defined when they were created.

## Disposing the Model

```csharp
/// <summary>
/// Dispose the model and release resources.
/// </summary>
void Dispose ();
```

Models can consume native and cloud resources, including threads, memory allocators, and so on. As a result, you must dispose of the model once you are done using it.

{% hint style="info" %}
The `MLModel` class implements the [`IDisposable`](https://docs.microsoft.com/en-us/dotnet/api/system.idisposable?view=net-5.0) interface, and as such can be used with `using` blocks.
{% endhint %}

{% hint style="danger" %}
Do not use a model once it has been disposed. Doing so will lead to a hard crash.
{% endhint %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.natml.ai/unity/api/mlmodel.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.