Are you running BlueOnyx at the same time as CodeProject.AI, if so that may be why it is not using the GPU. Try setting the GPU ID to 0 and restart the VM to see if that works.
After using the built-in ALPR I found the model used to detect the license plate did not perform well at night. I trained a new plates.onnx model that performs well now during the day and at night. Below is the link to the new model. To use the new model save the model in folder...
The below change should fix it. One recommended change is to clone this camera and use the Clone camera just for license plate detection and the Clone Mater camera for object detection.
Did you download and install the models, also select whatever GPU you have
Check Primary object detection...
No, v6.0.1.x only supports YOLOv8 & YOLO11. Send Ken an email asking him to add support for custom YOLOv5 models. I have not got around to sending him the email yet, if enough ask for custom YOLOv5 models support hopefully he will add the support.
The issue is the JSON format from v6.0.1, the api is just objects, not alpr. This is something that Ken will need to fix because @algertc’s alpr database app only recognizes the api alpr or @algertc’s needs to look for the label plate and use this for the plate.
v6.0.1...
I am trying to upgrade to 6.0.1 and it is not showing available, I even download the upgrade file from Blue Iris's web site and it is still 6.0.0.1. How did you upgrade?
I looks like the current version of PaddleOCR is not compatible with the ALPR module. Try the below steps
Delete folder C:\Program Files\CodeProject\AI\modules\ALPR\bin
Replace requirements.txt with the attached
Open up a command prompt in admin mode
change directory to CD C:\Program...
Try uninstalling the License Plate Reader module then reinstall the module using Do not use download cache and Install verbosity Loud. After the install finishes run a test again to see if it works.