This repository will give you concrete examples to get starting using GreengrassV2 to build Image Inferencing and Video Analytics Pipelines
Technologies used:
PLEASE NOTE: This deployment may install/modify components on your Jetson device. It will install some python packages outside of a virtual environment. This is because python-opencv is specially installed as part of Jetpack 4.4 and the debian package may run for a long period of time and not succesfully complete (numpy can also take a long time to install).
replace GreengrassCore where mentioned run:
cd ~/GreengrassCore
aws greengrassv2 create-component-version --inline-recipe fileb://recipes/aws.greengrass.JetsonDLRImageClassification-1.0.0.json
aws greengrassv2 create-component-version --inline-recipe fileb://recipes/variant.Jetson.DLR-1.0.0.json
aws greengrassv2 create-component-version --inline-recipe fileb://recipes/variant.Jetson.ImageClassification.ModelStore-1.0.0.json
deploy:
success: Now let's go to the MQTT Test client in the AWS Console to see our inference working:
{
"message": "{\"class\":\"Chihuahua\",\"confidence\":\"17.977331\"}",
"timestamp": "2021-01-06T18:30:05"
}
troubleshooting:
This library is licensed under the MIT-0 License. See the LICENSE file.