> For the complete documentation index, see [llms.txt](https://docs.degirum.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.degirum.com/ai-hub/hardware-explorer/inference-console.md).

# Inference Console

Explore model and hardware combinations with the AI Hub Inference Console.

Go to the Hardware Explorer, click any tile, and you'll see the Inference Console.

Use our pre-defined models and example images so you can see hardware and models in action.

<figure><img src="https://97157014-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FiNUrjcsNMTjUhiNPIF4u%2Fuploads%2Fgit-blob-58ebe0863e281ca664eb0ce20a2559d3b127b98c%2Fai-hub--hardware-explorer-inference-console.png?alt=media" alt=""><figcaption><p>Inference Console using an object detection model on an example image with two birds.</p></figcaption></figure>

## Using the Inference Console

All you need to do is select a model type, select an input image, and click **Run Inference**.

{% stepper %}
{% step %}
**Select a model type in the carousel**

When you open the Inference Console, you'll see a carousel featuring model types like object detection, instance segmentation, pose detection, and more. These are for use-cases like:

General:

* Object detection: Obtain bounding boxes with confidence levels.
* Instance Segmentation: Split an image into objects.

Specialized:

* Fire & Smoke Detection: Detect fire and smoke.
* PPE Detection: Detect personal protective equipment.
  {% endstep %}

{% step %}
**Select an input file**

The image on the left is the input image that will be provided to the model. Use the arrows select one of our sample images, or click **Input File** to upload your own.
{% endstep %}

{% step %}
**Run the inference**

Click **Run Inference** to run the inference using the model type on your input file. It should at most a couple seconds for the inference to run.
{% endstep %}

{% step %}
**View Results**

When the inference is complete, you'll see the image overlayed with inference results on the right. Click **Json Result** to see the inference results in JSON format, and click **Image Result** to see the image again.
{% endstep %}
{% endstepper %}