This is how I solved the issue with custom models and BI and CP.AI running on different servers.
I created a new folder in the BI server - custom models. In there I created EMPTY files for the custom models that I am using. Pointed BI to the new folder and then I rebooted the BI server. After...
About 3 weeks ago I have pointed my AITool to an instance of CP.AI running on a separate docker server. I am running GPU with a nvidia 1080 and Yolov5 6.2).
I see better processing times (anywhere between 22ms to 60ms - but about 80% of the images processed by CP.AI is around 25ms). In...
I know it does. In my case (separate Linux server with docker) it just does not enable - Blue Iris and CodeProject.AI ALPR
I have tagged @MikeLud1 before about this issue but I haven't heard anything back.
@MikeLud1 please see above. Running 2.0.8
I have removed ALPR and re-installed it again. Below is the install log:
Trying to enable GPU mode for ALPR:
After enabling GPU is still using CPU:
Something is not working correct in the docker version.
I had the same issue with 2.0.7
I have my CodeProject.AI ALPR docker configured with local host folders mapped to the docker folders. (I run my CodeProject.AI ALPR on a separate Linux server in docker).
I have my custom models in the correct folder and CodeProject.AI ALPR GUI can see them (via /vison.html URL).
All...
I am running CodeProject.AI in a separate virtual linux PC via Docker + CUDA.
All working as it should for Object Detection using CUDA and getting good results.
I have tried to enable CUDA for License Plate Reader and it just doesn't work. It always defaults back to CPU.
Any ideas on how I...
Thanks - that is really interesting you having the opposite!
In regards to DS - I was only running one cloned camera through the integrated BI and DS. All other cameras were running through Ubuntu DS and AITool. I will try and disable Ubuntu DS and see.
In regards to triggering - it was all over...
I have been using the AI Tool almost from the beginning when GentlePumpkin released it.
Now I am running the latest version by Vorlon. Using it for person detection only.
Running BI on a virtual Win10 PC (enough vCPUs assigned that usage never spikes beyond 40% and 12GB of RAM) and Deepstack as...
Should work with a 1030. Performance might be different.
Not sure how to get it going on Windows - as mentioned I have DeepStack running on Ubuntu and only BI running on Widows
I have mine setup with clones. I find it much easier than single camera setup (and it doesn't use any additional resources in BI).
Works well like this (at least for me). I find single camera will generate too much junk in BI (alerts).