Skip to content

Latest commit

 

History

History
72 lines (48 loc) · 2.63 KB

README.md

File metadata and controls

72 lines (48 loc) · 2.63 KB

moondream modular vision service

This module implements the rdk vision API in a viam-labs:vision:moondream model.

This model leverages the Moondream tiny vision language model to allow for image classification and querying.

The Moondream model and inference will run locally, and therefore speed of inference is highly dependant on hardware.

Build and Run

To use this module, follow these instructions to add a module from the Viam Registry and select the viam-labs:vision:moondream model from the viam-labs moondream-vision module.

Configure your vision service

Note

Before configuring your vision service, you must create a machine.

Navigate to the Config tab of your robot’s page in the Viam app. Click on the Service subtab and click Create service. Select the vision type, then select the viam-labs:vision:moondream model. Enter a name for your vision service and click Create.

On the new service panel, copy and paste the following attribute template into your vision service's Attributes box:

{
  "revision": "<optional model revision>"
}

Note

For more information, see Configure a Robot.

Attributes

The following attributes are available for viam-labs:vision:yolov8 model:

Name Type Inclusion Description
revision string Required Moondream model revision, defaults to "2024-08-26"

Example Configurations

{
  "revision": "2024-08-26"
}

API

The moondream resource provides the following methods from Viam's built-in rdk:service:vision API

get_classifications(image=binary, count)

get_classifications_from_camera(camera_name=string, count)

Note: if using this method, any cameras you are using must be set in the depends_on array for the service configuration, for example:

      "depends_on": [
        "cam"
      ]

By default, the Moondream model will be asked the question "describe this image". If you want to ask a different question about the image, you can pass that question as the extra parameter "question". For example:

moondream.get_classifications(image, 1, extra={"question": "what is the person wearing?"})