Enable MLOps in Vision AI Detection Apps#

Applications for industrial edge insights vision can also be used to demonstrate MLOps workflow using Model Download microservice. With this feature, during runtime, you can download a new model using the microservice and restart the pipeline with the new model.

Contents#

Prerequisites#

This guide assumes that Model Download service has already downloaded the model to be updated to /tmp/models. To learn how to setup Model Download, see here.

If not available, you can simulate this by downloading the appropriate sample model from the Edge AI Resources repository by using the link from the tabs below. Once downloaded, extract to /tmp/models directory.

Pallet Defect Detection

Download Pallet Defect Detection Model

PCB Anomaly Detection

Download PCB Anomaly Detection Model

Steps#

Note: If you are running multiple instances of the application, ensure to provide NGINX_HTTPS_PORT number in the URL for the app instance, i.e., replace <HOST_IP> with <HOST_IP>:<NGINX_HTTPS_PORT>. If you are running a single instance and using an NGINX_HTTPS_PORT other than the default 443, replace <HOST_IP> with <HOST_IP>:<NGINX_HTTPS_PORT>.

Set up the sample application to start a pipeline. A named pipeline (pallet_defect_detection_mlops or pcb_anomaly_detection_mlops) is already provided in the pipeline-server-config.json for this demonstration with the Pallet Defect Detection or PCB Anomaly Detection sample app.

Note: Ensure that the pipeline inference element, such as gvadetect/gvaclassify/gvainference, does not have a model-instance-id property set. If set, this would not allow the new model to be run with the same value provided in the model-instance-id.

Navigate to the [WORKDIR]/edge-ai-suites/manufacturing-ai-suite/industrial-edge-insights-vision directory and set up the app.
Pallet Defect Detection
cp .env_pallet-defect-detection .env
PCB Anomaly Detection
cp .env_pcb-anomaly-detection .env

Update the following variables in the .env file.

HOST_IP= # <IP Address of the host machine>

MINIO_ACCESS_KEY=   # MinIO service & client access key e.g. intel1234
MINIO_SECRET_KEY=   # MinIO service & client secret key e.g. intel1234

MTX_WEBRTCICESERVERS2_0_USERNAME=  # Webrtc-mediamtx username. e.g intel1234
MTX_WEBRTCICESERVERS2_0_PASSWORD=  # Webrtc-mediamtx password. e.g intel1234

Run the setup script using the following command.
```
./setup.sh
```
Bring up the containers.
```
docker compose up -d
```
Check to see if the pipeline (pallet_defect_detection_mlops or pcb_anomaly_detection_mlops) is present among the list of loaded pipelines.
```
./sample_list.sh
```

Modify the payload in the appropriate payload.json to launch an instance for the MLOps pipeline.

Pallet Defect Detection

apps/pallet-defect-detection/payload.json

[
 {
   "pipeline": "pallet_defect_detection_mlops",
   "payload": {
     "source": {
       "uri": "file:///home/pipeline-server/resources/videos/warehouse.avi",
       "type": "uri"
     },
     "destination": {
       "frame": {
         "type": "webrtc",
         "peer-id": "pdd"
       }
     },
     "parameters": {
       "detection-properties": {
         "model": "/home/pipeline-server/resources/models/pallet-defect-detection/deployment/Detection/model/model.xml",
         "device": "CPU"
       }
     }
   }
 }
]

PCB Anomaly Detection

apps/pcb-anomaly-detection/payload.json

[
   {
       "pipeline": "pcb_anomaly_detection_mlops",
       "payload":{
           "source": {
               "uri": "file:///home/pipeline-server/resources/videos/anomalib_pcb_test.avi",
               "type": "uri"
           },
           "destination": {
           "frame": {
               "type": "webrtc",
               "peer-id": "anomaly"
           }
           },
           "parameters": {
               "classification-properties": {
                   "model": "/home/pipeline-server/resources/models/pcb-anomaly-detection/deployment/Anomaly classification/model/model.xml",
                   "device": "CPU"
               }
           }
       }
   }
]

Start the pipeline with the selected payload.
Pallet Defect Detection
./sample_start.sh -p pallet_defect_detection_mlops
PCB Anomaly Detection
./sample_start.sh -p pcb_anomaly_detection_mlops
Note the instance-id of the pipeline launched.
Verify the pipeline is running. You can View the WebRTC streaming on https://<HOST_IP>/mediamtx/<peer-str-id> by replacing <peer-str-id> with the value used in the original cURL command to start the pipeline.

Pallet Defect Detection

PCB Anomaly Detection

Downloading a Model with Model Download

At this point, restart the pipeline with a newer model. The new model can be a retrained version of the existing model or a different model altogether. We use the Model Download microservice to help download the model. It supports downloading public models as well as Geti™ models from a running Geti™ server. To learn more about the microservice, see how to get started with it.

For this demonstration, the guide assumes that:
- the appropriate model (Pallet Defect Detection or PCB Anomaly Detection) has been retrained and is available for download from a Geti™ server using the Model Download service.
- the downloaded location is accessible by the DL Streamer Pipeline Server. In our example, it is /tmp/models.
- the /tmp directory is already accessible by the sample application. If not, add it to the volumes section of dlstreamer-pipeline-server service in the docker-compose file.

Stop the running pipeline by using the pipeline instance-id noted in step 7.

curl -k --location -X DELETE https://<HOST_IP>/api/pipelines/{instance_id}

Modify the payload.json to use the new model and start a new pipeline with it. Notice the model path in the payload has changed to the new model.

Pallet Defect Detection

apps/pallet-defect-detection/payload.json

[
 {
   "pipeline": "pallet_defect_detection_mlops",
   "payload": {
     "source": {
       "uri": "file:///home/pipeline-server/resources/videos/warehouse.avi",
       "type": "uri"
     },
     "destination": {
       "frame": {
         "type": "webrtc",
         "peer-id": "pdd"
       }
     },
     "parameters": {
       "detection-properties": {
         "model": "/tmp/models/pallet-defect-detection/deployment/Detection/model/model.xml",
         "device": "CPU"
       }
     }
   }
 }
]

Run the following.

./sample_start.sh -p pallet_defect_detection_mlops

PCB Anomaly Detection

apps/pcb-anomaly-detection/payload.json

[
  {
     "pipeline": "pcb_anomaly_detection_mlops",
     "payload":{
           "source": {
              "uri": "file:///home/pipeline-server/resources/videos/anomalib_pcb_test.avi",
              "type": "uri"
           },
           "destination": {
           "frame": {
              "type": "webrtc",
              "peer-id": "anomaly"
           }
           },
           "parameters": {
              "classification-properties": {
                 "model": "/tmp/models/pcb-anomaly-detection/deployment/Anomaly classification/model/model.xml",
                 "device": "CPU"
              }
           }
     }
  }
]

Run the following.

./sample_start.sh -p pcb_anomaly_detection_mlops

View the WebRTC streaming on https://<HOST_IP>/mediamtx/<peer-str-id> by replacing <peer-str-id> with the value used in the original cURL command to start the pipeline.

Additional resources#

Downloading models from Geti™ Server#

To learn how to download models from a running Geti™ server, see here.

Note: The downloaded model(s) must be accessible to the DL Streamer Pipeline Server container. If necessary, add it to volumes section of dlstreamer-pipeline-server in compose file, and restart the DLSPS service.

Enable MLOps in Vision AI Detection Apps#

Contents#

Prerequisites#

Steps#

Downloading a Model with Model Download

Additional resources#

Downloading models from Geti™ Server#

This Page