Tutorial: Perform sample image classification inference on images from a camera using TensorFlow Lite

In the Amazon IoT Greengrass console navigation menu, choose Components.

On the Components page, on the Public components tab, choose aws.greengrass.TensorFlowLiteImageClassification.

On the aws.greengrass.TensorFlowLiteImageClassification page, choose Deploy.

From Add to deployment, choose one of the following:

1. To merge this component to an existing deployment on your target device, choose Add to existing deployment, and then select the deployment that you want to revise.

2. To create a new deployment on your target device, choose Create new deployment. If you have an existing deployment on your device, choosing this step replaces the existing deployment.

On the Specify target page, do the following:

1. Under Deployment information, enter or modify the friendly name for your deployment.

2. Under Deployment targets, select a target for your deployment, and choose Next. You cannot change the deployment target if you are revising an existing deployment.

On the Select components page, under Public components, verify that the aws.greengrass.TensorFlowLiteImageClassification component is selected, and choose Next.

On the Configure components page, do the following:

1. Select the inference component, and choose Configure component.

2. Under Configuration update, enter the following configuration update in the Configuration to merge box.

   {
     "InferenceInterval": "60",
     "UseCamera": "true"
   }

   With this configuration update, the component accesses the camera module on your device and performs inference on images taken by the camera. The inference code runs every 60 seconds.

3. Choose Confirm, and then choose Next.

On the Configure advanced settings page, keep the default configuration settings, and choose Next.

On the Review page, choose Deploy

Create a deployment.json file to define the deployment configuration for the TensorFlow Lite image classification component. This file should look like the following:

{
  "targetArn":"targetArn",
  "components": {
    "aws.greengrass.TensorFlowLiteImageClassification": {
      "componentVersion": 2.1.0,
      "configurationUpdate": {
        "InferenceInterval": "60",
        "UseCamera": "true"
      }
    }
  }
}

With this configuration update, the component accesses the camera module on your device and performs inference on images taken by the camera. The inference code runs every 60 seconds. Replace the following values

Run the following command to deploy the TensorFlow Lite image classification component on the device:

aws greengrassv2 create-deployment \
    --cli-input-json file://path/to/deployment.json