# Appendix

<table><thead><tr><th width="222">Output Type</th><th width="145">Expected Output File Type</th><th>Output File Sample</th></tr></thead><tbody><tr><td>Image - Integer</td><td>TIFF File</td><td>An image file with different bands</td></tr><tr><td>Image - Float</td><td>TIFF File</td><td>An image file with multiple bands - they will specify what each band is, like NDMI, NDVI etc.</td></tr><tr><td>Segmentation - Binary Mask</td><td>TIFF File</td><td>Binary mask with 0s and 1s</td></tr><tr><td>Segmentation - Multi-class segmentation</td><td>TIFF File</td><td>Mask with n values in it, where n is the number of classes</td></tr><tr><td>Object Detection - Point</td><td>JSON</td><td><p></p><pre class="language-objectivec"><code class="lang-objectivec">prediction: [
    {
        score: 0.865,
        x: 12,
        y: 25,
    },
    {
        score: 0.765,
        x: 34,
        y: 67,
    }
]
</code></pre></td></tr><tr><td>Object Detection - Bounding Box</td><td>JSON</td><td><p></p><pre class="language-objectivec"><code class="lang-objectivec">prediction: [
    {
        score: 0.865,
        xmin: 12,
        ymin: 25,
        xmax: 35,
        ymax: 40
    },
    {
        score: 0.765,
        xmin: 34,
        ymin: 67,
        xmax: 65,
        ymax: 70
    }
]
</code></pre></td></tr><tr><td>Object Classification - Point</td><td>JSON</td><td><p></p><pre class="language-objectivec"><code class="lang-objectivec">prediction: [
    {
        class_id: 0,
        label: 'Tree',
        score: 0.865,
        x: 12,
        y: 25
    },
    {
        class_id: 1,
        label: 'Lake',
        score: 0.765,
        x: 34,
        y: 67
    }
]
</code></pre></td></tr><tr><td>Object Classification - BBox</td><td>JSON</td><td><p></p><pre class="language-objectivec" data-full-width="true"><code class="lang-objectivec">prediction: [

```
{
    class_id: 0,
    label: 'Tree',
    score: 0.865,
    xmin: 12,
    ymin: 25,
    xmax: 35,
    ymax: 40
},
{
    class_id: 1,
    label: 'Lake',
    score: 0.765,
    xmin: 34,
    ymin: 67,
    xmax: 65,
    ymax: 70
}
```

] </code></pre></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://skyserve.gitbook.io/skyserve-docs/model-submission/appendix.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.