CodeProject.AI Version 2.5

I have no AI working at all not detecting people/Vehicles. although it did work for most of the night it has stopped. So currently with the Updated Version, No ALPR module won't stay running, Object Detection is running with GPU enabled but does not detect any object via Blue iris, Face processing appears to be running with GPU enabled. Testing the .Net version to see if that detects any cars/people then Reverting to the previous version because the LPR option was Nice Feature. If I Test image it appears to be detecting, objects only look like Blueiris is ignoring the AI. its 11AM last car detected at our gate was 8:11am. So it did work for a little while.
the .NET detection appears to work I am detecting vehicles again. :-) description does say this is for non Cuda GPU which mine is cuda enabled.
 
Last edited:
Dixit said:
Alright updating this that somehow now it just started working. I just let it sit for about 15-20mins after it went into Lost Contact, and now its started and processing.

View attachment 184118

Initial thoughts are its not faster since its showing like 200-300ms where as the Yolov6.2 and 8 were only taking about 100-125ms. But going to leave it on this to experiment some more.
Click to expand...
Yep it works but slooooow :-)
 
I installed YOLOv5.net YOLO v5 3.1 and YOLOv8 is there a method to determine which one is working, is there any way to get the LIcense Plate reader back to the GPU where it was with previous version, Also getting lots of RED in the console

file "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-3.1\bin\windows\python37\venv\lib\site-packages\torch\nn\modules\module.py", line 1190, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-3.1\models\yolo.py", line 149, in forward
return self.forward_once(x, profile) # single-scale inference, train
File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-3.1\models\yolo.py", line 176, in forward_once
x = m(x) # run
 
Dudleydogg said:
I had custom models in the list before updating, but they are blank now how do I populate that field again?View attachment 186692
Click to expand...


I am having the same issue after upgrading Codeprojet Ai 2.5.4. The Custom Model field is blank in Blue Iris Ai window. I have restarted and rebooted to no avail.

I have checked the Codeproject directory, and the Custom Models are there.

Any other ideas?

Thanks,

Rick
 
Mine installed just fine.

Did you follow the uninstall/install directions @MikeLud1 has posted previously on how to update CodeProject?

CodeProject.AI Version 2.5

CodeProject.AI version 2.5 was released Jan 23, 2024, this thread is for all topic CodeProject.AI version 2.5 and greater. This version is no longer beta https://www.codeproject.com/Articles/5322557/CodeProject-AI-Server-AI-the-easy-way If you need any info on CodeProject.AI version 2.0 to...
ipcamtalk.com ipcamtalk.com
 
Skinny1 said:
I am having the same issue after upgrading Codeprojet Ai 2.5.4. The Custom Model field is blank in Blue Iris Ai window. I have restarted and rebooted to no avail.

I have checked the Codeproject directory, and the Custom Models are there.

Any other ideas?

Thanks,

Rick
Click to expand...
I have seen that any updating of BI version requires at least one, on occasion more, restarts of the Blue Iris service in windows services panel, in order to see the custom models in BI settings/ AI tab
 
  • Like
Reactions: Skinny1
wittaj said:
Mine installed just fine.

Did you follow the uninstall/install directions @MikeLud1 has posted previously on how to update CodeProject?

CodeProject.AI Version 2.5

CodeProject.AI version 2.5 was released Jan 23, 2024, this thread is for all topic CodeProject.AI version 2.5 and greater. This version is no longer beta https://www.codeproject.com/Articles/5322557/CodeProject-AI-Server-AI-the-easy-way If you need any info on CodeProject.AI version 2.0 to...
ipcamtalk.com ipcamtalk.com
Click to expand...

Yes, I did. I am not the only one having this issue.
 
Dudleydogg said:
I installed YOLOv5.net YOLO v5 3.1 and YOLOv8 is there a method to determine which one is working, is there any way to get the LIcense Plate reader back to the GPU where it was with previous version, Also getting lots of RED in the console

file "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-3.1\bin\windows\python37\venv\lib\site-packages\torch\nn\modules\module.py", line 1190, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-3.1\models\yolo.py", line 149, in forward
return self.forward_once(x, profile) # single-scale inference, train
File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-3.1\models\yolo.py", line 176, in forward_once
x = m(x) # run
Click to expand...
Post the below screenshots

1708197006761.png

1708196977724.png
 
I could not get the ALPR to run, but everything else kicked in and detections are working, what is interesting is on one of my cameras I am getting Tag info. these modules are working for me currently
1708206035805.png
 
MikeLud1 said:
Rick

The Object Detection (YOLOv5 .NET) module should be using your iGPU. On CodeProject.AI Dashboard go to the module settings an Enable GPU. The License Plate Reader module does not support iGPU so this module will still use your CPU only

View attachment 186730
Click to expand...
Mike,

The only option is Model Size. There is no GPU Enable option.


Rick
 
You must log in or register to reply here.
Top Bottom