# Output interpretation

<table><thead><tr><th width="297">Feature</th><th>Example</th><th>Explanation</th></tr></thead><tbody><tr><td>Image_Class</td><td>indoor</td><td>The basic class of the image, which will define the further categorization.</td></tr><tr><td>ConfidencePercent_Image_Class</td><td>99.2</td><td>How much confident (in %) the model is that the image belongs to the predicted image class</td></tr><tr><td>Room_Class</td><td>other_room</td><td>The room identified in the image, if the image is indoors. If the class is 'other_room', a further categorization takes place.</td></tr><tr><td>ConfidencePercent_Room_Class</td><td>96.1</td><td>How much confident (in %) the model is that the image belongs to the predicted room class</td></tr><tr><td>Room_Subclass</td><td>hall_corridor</td><td>The further categorization applied to the image, to find the room subclass, if the main room class is 'other_room'.</td></tr><tr><td>ConfidencePercent_Room_Subclass</td><td>82.16</td><td>How much confident (in %) the model is that the image belongs to the predicted room subclass</td></tr><tr><td>Scene_Class1</td><td>facade</td><td>The first major scene class identified into the image, describing the outdoor scene of the house.</td></tr><tr><td>ConfidencePercent_Scene_Class1</td><td>70.5</td><td>How much confident (in %) the model is that the image belongs to the predicted scene class</td></tr><tr><td>Scene_Class2</td><td>balcony-garden</td><td>The second major scene class identified into the image, describing the outdoor scene of the house. It is identified, if the confidence for the 1st scene class falls under 70%</td></tr><tr><td>ConfidencePercent_Scene_Class2</td><td>75.2</td><td>How much confident (in %) the model is that the image belongs also to a second scene class</td></tr></tbody></table>


---

# 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.altum.ai/english/property-valuation-and-market/photo-labelling-api/output-interpretation.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.