How do I get CodeProject AI to use cuda/GPU instead of CPU

See more: (untagged)

Using Blue Iris ver. 5.8.2.5 and Code Project 2.4.7-Beta But can not get CodeProject to see the CUDA/GPU that I have using the Gefource GTX-1650

Server version:   2.4.7-Beta
System:           Windows
Operating System: Windows (Microsoft Windows 11 version 10.0.22621)
CPUs:             Intel(R) Core(TM) i7-9700 CPU @ 3.00GHz (Intel)
                  1 CPU x 8 cores. 8 logical processors (x64)
GPU (Primary):    NVIDIA GeForce GTX 1650 (4 GiB) (NVIDIA) 
                  Driver: 522.06, CUDA: 11.8 (up to: 11.8), Compute: 7.5, cuDNN: 
System RAM:       32 GiB
Platform:         Windows
BuildConfig:      Release
Execution Env:    Native
Runtime Env:      Production
.NET framework:   .NET 7.0.10
Default Python:
Video adapter info:
  VNC Mirror Driver:
    Driver Version     1.8.0.0
    Video Processor    
  DisplayLink USB Device:
    Driver Version     9.3.3324.0
    Video Processor    
  DisplayLink USB Device:
    Driver Version     9.3.3324.0
    Video Processor    
  Intel(R) UHD Graphics 630:
    Driver Version     30.0.101.1692
    Video Processor    Intel(R) UHD Graphics Family
  NVIDIA GeForce GTX 1650:
    Driver Version     31.0.15.2206
    Video Processor    NVIDIA GeForce GTX 1650
System GPU info:
  GPU 3D Usage       19%
  GPU RAM Usage      528 MiB
Global Environment variables:
  CPAI_APPROOTPATH = <root>
  CPAI_PORT        = 32168

******************************************
When I first installed CodeProject 2.4.7-Beta I was able to click on the configuration Gear for Object Detection (YOLOv5 6.2) and CUDA/GPU was a selection possibility but now all I get is: Model Size No selection for GPU The same thing goes for Facial recognition except it shows Half Precision

What I have tried:

I've uninstalled both Blue Iris and CodeProject. I re-installed both Nvidia driver and CUDA still no luck at seeing GPU option in CodeProject. It was doing the same with older version of CodeProject AI but the one time I had it working until I was playing with the drivers is when I updated from an older version of CodeProject to the lates 2.4.7-Beta