Unable to Run Safety Gear User Defined Function (UDF) on GPU with Intel® Edge Insights for Industrial (Intel® EII)

Ran into the following error when running the Safety Gear UDF Sample:
RuntimeError: Failed to create plugin for device GPU

The following steps will help you setup and run the Safety Gear User Defined Function (UDF) Sample on GPU with Intel® Edge Insights for Industrial (Intel® EII).

1. Create a copy of the original configuration files

   mv <working_dir>/edge_insights_industrial/Edge_Insights_for_Industrial_2.6.2/IEdgeInsights/VideoIngestion/config.json <working_dir>/edge_insights_industrial/Edge_Insights_for_Industrial_2.6.2/IEdgeInsights/VideoIngestion/config.json.bkup
    

   mv <working_dir>/edge_insights_industrial/Edge_Insights_for_Industrial_2.6.2/IEdgeInsights/VideoAnalytics/config.json <working_dir>/edge_insights_industrial/Edge_Insights_for_Industrial_2.6.2/IEdgeInsights/VideoAnalytics/config.json.bkup

2. Copy the Safety Gear UDF directory to the common directory

   cp -r <working_dir>/edge_insights_industrial/Edge_Insights_for_Industrial_2.6.2/IEdgeInsights/CustomUdfs/PySafetyGearAnalytics/safety_gear <working_dir>/edge_insights_industrial/Edge_Insights_for_Industrial_2.6.2/IEdgeInsights/common/video/udfs/python

3. Copy the test video to the test_videos directory

   cp <working_dir>/edge_insights_industrial/Edge_Insights_for_Industrial_2.6.2/IEdgeInsights/CustomUdfs/PySafetyGearIngestion/Safety_Full_Hat_and_Vest.avi <working_dir>/edge_insights_industrial/Edge_Insights_for_Industrial_2.6.2/IEdgeInsights/VideoIngestion/test_videos/Safety_Full_Hat_and_Vest.avi

4. Copy the attached configuration files to VideoIngestion and VideoAnalytics Directories

   cp config-VideoIngestion.json <working_dir>/edge_insights_industrial/Edge_Insights_for_Industrial_2.6.2/IEdgeInsights/VideoIngestion/config.json
   
   cp config-VideoAnalytics.json <working_dir>/edge_insights_industrial/Edge_Insights_for_Industrial_2.6.2/IEdgeInsights/VideoAnalytics/config.json

5. Provision and build Edge Insights for Industrial

   python3 builder.py -f usecases/video-streaming-all-udfs.yml
   cd <working_dir>/edge_insights_industrial/Edge_Insights_for_Industrial_2.6.2/IEdgeInsights/build
   cd provision && sudo -E ./provision.sh ../docker-compose.yml
   cd .. && docker-compose -f docker-compose-build.yml build

6. Run the sample

   docker-compose up -d
   xhost +

A visual will displayed with the inference results