CodeProject.AI Version 2.0

MikeLud1 said:
Try refreshing the page by doing a Ctrl+F5, I think it might fix it.
Click to expand...

i am pretty sure I gave that a go. I do that often.
How does the RKNM compare to the Coral?

that is pretty cheap now.

i am doing the lpr on a red hat Xeon. Seemed to be my fastest option. is There a way to accelerate that? We can’t do alpr on the orange pi
 
Guys,

Getting some recurring errors after I updated CP.ai on my Unraid box (it's an external setup that my BI box offloads AI processing to). No other changes were made.

Here's part of the log.

22:13:34:Object Detection (YOLOv5 6.2): Queue request for Object Detection (YOLOv5 6.2) command 'detect' (...e97e48) took 4ms
22:13:34:Object Detection (YOLOv5 6.2): [RuntimeError] : Traceback (most recent call last):
File "/app/preinstalled-modules/ObjectDetectionYolo/detect.py", line 142, in do_detection
det = detector(img, size=640)
File "/usr/local/lib/python3.8/dist-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/usr/local/lib/python3.8/dist-packages/yolov5/models/common.py", line 669, in forward
with dt[0]:
File "/usr/local/lib/python3.8/dist-packages/yolov5/utils/general.py", line 158, in enter
self.start = self.time()
File "/usr/local/lib/python3.8/dist-packages/yolov5/utils/general.py", line 167, in time
torch.cuda.synchronize()
File "/usr/local/lib/python3.8/dist-packages/torch/cuda/init.py", line 688, in synchronize
return torch._C._cuda_synchronize()
RuntimeError: CUDA error: an illegal memory access was encountered
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.
Click to expand...

Basically, BI will fail to register any AI events.
Restarting the CP.ai docker works for a while, but then screws itself again.

Here's some screens.

1691411470860.png
1691411611132.png


Also (maybe unrelated), but CTRL+click no longer works on a clip to bring up the AI status window. Even on confirmed alerts. Is anyone else experiencing this? How do I fix it?
 
Last edited:
Corvus85 said:
Guys,

Getting some recurring errors after I updated CP.ai on my Unraid box (it's an external setup that my BI box offloads AI processing to). No other changes were made.

Here's part of the log.



Basically, BI will fail to register any AI events.
Restarting the CP.ai docker works for a while, but then screws itself again.

Here's some screens.

View attachment 169506
View attachment 169508


Also (maybe unrelated), but CTRL+click no longer works on a clip to bring up the AI status window. Even on confirmed alerts. Is anyone else experiencing this? How do I fix it?
Click to expand...
This is over my head, please post your issue on CodeProject.AI forum

CodeProject.AI Discussions - CodeProject

www.codeproject.com www.codeproject.com
 
  • Wow
Reactions: Nunofya
Corvus85 said:
Guys,

Getting some recurring errors after I updated CP.ai on my Unraid box (it's an external setup that my BI box offloads AI processing to). No other changes were made.

Here's part of the log.

Basically, BI will fail to register any AI events.
Restarting the CP.ai docker works for a while, but then screws itself again.
Click to expand...

I would start by disabling the GPU acceleration and see if that fixes the error. If it is stable after that, we can debug the CUDA issues..

Do you have a docker-compose.yml file? Or are you kicking off docker from the command line?
 
wpiman said:
I would start by disabling the GPU acceleration and see if that fixes the error. If it is stable after that, we can debug the CUDA issues..
Click to expand...

The problem is that my BI machine doesn't have a GPU. It struggles so much that it frequently times out and gives error 500 on AI alerts anyway, which is why I offloaded it to a machine that has a GPU in the first place.

Do you have a docker-compose.yml file? Or are you kicking off docker from the command line?
[/QUOTE]

Neither. I'm running the docker container on Unraid.
 
I have cpai installed on docker. It works fine but I am unable to find a way to set the model.
i would like to set it to ipcam-general but have been able to find how.
In ai explorer I can select it to do a bench mark but I have not found any mention of it being used in the logs.
I am not using blueiris.
 
Last edited:
Guys, I keep seeing 'AI error 500' in BI ever since I updated CP.ai to the latest version.
I've tried reinstalling an disabling half precision, but no effect.
Restarting the docker container works temporarily, then keeps failing after a few hours.
Am I the only one with this problem?
CP.ai forums are useless so far in diagnosing it and I want to know if I'm not alone.
 
Corvus85 said:
Guys, I keep seeing 'AI error 500' in BI ever since I updated CP.ai to the latest version.
I've tried reinstalling an disabling half precision, but no effect.
Restarting the docker container works temporarily, then keeps failing after a few hours.
Am I the only one with this problem?
CP.ai forums are useless so far in diagnosing it and I want to know if I'm not alone.
Click to expand...

Just set the container to 2.0.9 and see if that resolves your issue.
 
I don't use unraid-- but somewhere when you specify the docker image-- you specify the image to pull, and you probably select the latest...

For me:
image: codeproject/ai-server:latest

Change it to one of these tags...


For me, that would be

codeproject/ai-server:2.1.9

You might need the GPU version or ARM depending on your system...
 
  • Like
Reactions: Corvus85
wpiman said:
I don't use unraid-- but somewhere when you specify the docker image-- you specify the image to pull, and you probably select the latest...

For me:
image: codeproject/ai-server:latest

Change it to one of these tags...


For me, that would be

codeproject/ai-server:2.1.9

You might need the GPU version or ARM depending on your system...
Click to expand...

Thanks so much, I'll try it out
 
@Corvus85 @wpiman is correct with the syntax (assuming your unraid container was previously on the last latest release of CPAI).
Docker <--- this shows the exact image names as they get replaced if you want to pull an older one.
Here is where in Unraid you would set it.
screen cap 1, normal mouse click on the CPAI icon in the docker tab. This brings up the menu as you see in screen cap 1. Select edit.
This brings up screen cap 2.
In the noted field (ignore all the other fields that may show) this is where/how you tell docker to pull the image from.

I am using "Plex" as my example in screen cap 1 & 2.
In the final screen cap I show you exactly how it should look for it to pull the last version (with GPU & CUDA).
Code: 
codeproject/ai-server:gpu-2.1.9

Then you have to scroll to the bottom and hit "apply". The container will update / create a new one & remove the current one automatically.

Hope that helps and solves your issue. Otherwise you will have some more digging to do.Unraid_01.pngUnraid_02.pngUnraid_03.png
 
Last edited:
  • Like
Reactions: Corvus85
You must log in or register to reply here.
Top Bottom