CodeProject.AI Discussions

15-May-24 5:02

Quote:
Operating System: Linux (Ubuntu 24.04)

First: how is 24.04? I've not updated my system yet (waiting till August for RTM) but I'd be interested in your take.

Second, the error is that MongoDB can't be installed. I'm guessing this is related to 24.04 given the 24.04 release notes specifically state there will be app incompatibilities until full release in August.

cheers
Chris Maunder

"Nothing found"

fotingo12-May-24 8:08

fotingo

12-May-24 8:08

Hello,
I have been having this issue where I do not get motion alert at night, even though AI detects a car in my driveway at over 90%, but then it says "nothing found" and I do not get an alert.

My son comes home at night around 2am, so I am able to test this very regularly.

This only happens at night. My driveway is very well lit and very clear. Some nights it works fine and other nights it's a complete miss.

Why would AI not send an alert if it sees a car at 93%, but other other times it will send it?
My CPU hovers around 8-10% with 8 cameras and I use sub streams. I also have 16 Gigs of ram.. so I doubt it's a system limitation.

Any ideas?

Member 1587624113-May-24 1:07

Member 15876241

13-May-24 1:07

The first question I have is whether you are using BlueIris or AgentDVR. I use AgentDVR.

If you are using AgentDVR, you can check its logging around that time (2am or whenever the car shows up). See what the log says when the car arrives.

If the logs do not say anything about that time, it could be that the motion detection did not go off at all. This means that when the car arrived, the motion it caused on the camera was not enough to trigger the motion detection. In this case, you would need to increase the sensitivity of the motion detector for the camera so that it would trigger.

There could be other reasons too, but I think you can start with checking the log and seeing what it says. My suggestion above is based on my own experience.

And, your system is fine based on your description.

modified 13-May-24 7:28am.

fotingo13-May-24 11:42

fotingo

13-May-24 11:42

I use Blue Iris. The other thing is sometimes it says nothing found, but other times it detects the car, but it will not send a motion alert. It's like nothing happened in front of the camera. It won't say nothing found or cancelled motion... just does nothing.

It seemed like it just completely ignored the motion, but you can clearly see it was tracking it using "Analyze with AI".

This is very odd, but like I said, it only happens at night.

Member 1587624114-May-24 21:38

Member 15876241

14-May-24 21:38

I see. Unfortunately, I don't know about BlueIris, so my suggestion might not help solve the problem. However, you could check the settings for the motion detector, the schedule of the detector (if there is one), the confidence setting of the AI, etc.

I think the best way to debug this is to test it on the spot. Have someone go in front of the camera to trigger the motion detector at the time when you are having problems with the detection, while another person is on BlueIris testing different settings to figure out what is wrong.

Hopefully it helps.

Chris Maunder15-May-24 5:03

15-May-24 5:03

This sounds like a Blue Iris issue, rather than a detection issue. Is that correct?

cheers
Chris Maunder

CPAI ver 2.6.2 failed inferences in Coral ver 2.2.2 vs YOLOv5 .NET?

fotingo15-May-24 7:39

fotingo

15-May-24 7:39

I'm not sure. This is an example of AI "seeing" an object, but not firing an alert.
But other times, it just says.."nothing found".

I noticed it was seeing deer as sheep..so I added "sheep" to the settings, but I still not get alerts.

Steve Winn11-May-24 9:48

Re: CPAI ver 2.6.2 failed inferences in Coral ver 2.2.2 vs YOLOv5 .NET?

11-May-24 9:48

I tend to see a large amount of failed inferences using the Coral ver 2.2.2 module as opposed to using the YOLOv5 .NET module. What are failed inferences? What does this mean?

Coral ver 2.2.2:

Module 'Object Detection (Coral)' 2.2.2 (ID: ObjectDetectionCoral)
Valid:         True
Module Path:   <root>\modules\ObjectDetectionCoral
AutoStart:     True
Queue:         objectdetection_queue
Runtime:       python3.9
Runtime Loc:   Local
FilePath:      objectdetection_coral_adapter.py
Start pause:   1 sec
Parallelism:   16
LogVerbosity:  
Platforms:     all
GPU Libraries: installed if available
GPU Enabled:   enabled
Accelerator:   
Half Precis.:  enable
Environment Variables
   CPAI_CORAL_MODEL_NAME = MobileNet SSD
   CPAI_CORAL_MULTI_TPU  = true
   MODELS_DIR            = <root>\modules\ObjectDetectionCoral\assets
   MODEL_SIZE            = Small
Status Data:  {
  "inferenceDevice": "TPU",
  "inferenceLibrary": "TF-Lite",
  "canUseGPU": "false",
  "successfulInferences": 22839,
  "failedInferences": 9402,
  "numInferences": 32241,
  "averageInferenceMs": 7.730373483952888
}
Started:      08 May 2024 3:36:09 PM Central Standard Time
LastSeen:     09 May 2024 5:05:38 PM Central Standard Time
Status:       Stopped
Requests:     32268 (includes status calls)

YOLOv5 .NET:

Module 'Object Detection (YOLOv5 .NET)' 1.10.0 (ID: ObjectDetectionYOLOv5Net)
Valid:         True
Module Path:   <root>\modules\ObjectDetectionYOLOv5Net
AutoStart:     True
Queue:         objectdetection_queue
Runtime:       dotnet
Runtime Loc:   System
FilePath:      bin\ObjectDetectionYOLOv5Net.exe
Start pause:   1 sec
Parallelism:   0
LogVerbosity:  
Platforms:     all
GPU Libraries: installed if available
GPU Enabled:   enabled
Accelerator:   
Half Precis.:  enable
Environment Variables
   CUSTOM_MODELS_DIR = <root>\modules\ObjectDetectionYOLOv5Net\custom-models
   MODELS_DIR        = <root>\modules\ObjectDetectionYOLOv5Net\assets
   MODEL_SIZE        = MEDIUM
Status Data:  {
  "InferenceDevice": "GPU",
  "inferenceLibrary": "DirectML",
  "canUseGPU": true,
  "successfulInferences": 62370,
  "failedInferences": 0,
  "numInferences": 62370,
  "averageInferenceMs": 278,
  "Histogram": {
    "car": 112067,
    "truck": 2855,
    "person": 3756,
    "bus": 166,
    "bird": 6,
    "motorcycle": 43,
    "bicycle": 332,
    "dog": 18,
    "squirrel": 17,
    "horse": 4,
    "cow": 2,
    "cat": 5,
    "Car": 5310,
    "Person": 81,
    "Motorcycle": 3,
    "Dog": 9
  },
  "NumItemsFound": 124674
}
Started:      10 May 2024 6:30:55 AM Central Standard Time
LastSeen:     11 May 2024 2:21:28 PM Central Standard Time
Status:       Started
Requests:     62372 (includes status calls)

For reference, System Info:

Server version:   2.6.2
System:           Windows
Operating System: Windows (Microsoft Windows 10.0.19045)
CPUs:             Intel(R) Core(TM) i5-7500 CPU @ 3.40GHz (Intel)
                  1 CPU x 4 cores. 4 logical processors (x64)
GPU (Primary):    Intel(R) HD Graphics 630 (1,024 MiB) (Intel Corporation) 
                  Driver: 31.0.101.2111
System RAM:       16 GiB
Platform:         Windows
BuildConfig:      Release
Execution Env:    Native
Runtime Env:      Production
Runtimes installed:
  .NET runtime:     7.0.5
  .NET SDK:         Not found
  Default Python:   Not found
  Go:               Not found
  NodeJS:           Not found
  Rust:             Not found
Video adapter info:
  Intel(R) HD Graphics 630:
    Driver Version     31.0.101.2111
    Video Processor    Intel(R) HD Graphics Family
System GPU info:
  GPU 3D Usage       4%
  GPU RAM Usage      0
Global Environment variables:
  CPAI_APPROOTPATH = <root>
  CPAI_PORT        = 32168

Steve Winn14-May-24 5:27

Re: CPAI ver 2.6.2 failed inferences in Coral ver 2.2.2 vs YOLOv5 .NET?

14-May-24 5:27

The difference between Failed Inferences in the Coral module and the YOLOv5 .NET module is dramatic.
Coral = ~18% of total Failed.
Yolo = 0 failed out of 150,000 total inferences.
This leads me to not use the Coral module, as it indicates there is something wrong.
Again, what does failed inferences mean? How does the program identify an inference as failed? Does anyone know?

Sean Ewington14-May-24 12:44

Re: CPAI ver 2.6.2 failed inferences in Coral ver 2.2.2 vs YOLOv5 .NET?

14-May-24 12:44

Just to confirm, are you using a Small model size for Coral in all these tests, and Medium for YOLOv5.NET?

Also, are you using other software with this, like Blue Iris?

Thanks,
Sean Ewington
CodeProject

Steve Winn14-May-24 13:36

Re: CPAI ver 2.6.2 failed inferences in Coral ver 2.2.2 vs YOLOv5 .NET?

14-May-24 13:36

Blue Iris latest stable version.
Coral small
YOLOv5 .NET medium
In ver. 2.6.2, with the Coral I tried changing models, and changing to medium from small.
This just resulted in apparent crashes of the module, and a lot of difficulty getting results to Blue Iris. Also, during that period, trying to make those changes, I kept losing the TPU Multi TPU setting. I have uninstalled and reinstalled CPAI 2.6.2 with no good results, and also uninstalled and reinstalled the Coral version 2.2.2 module with Do not use download cache checked.
I may be imagining things, but I thought I saw a period of good results with the Coral ver 2.2.0 module, but I can't seem to get back to it.
For me, the Yolo modules with ipcam-combined and ipcam-dark work pretty well.
I suppose I should download the current code and see if I can figure out what increments the failed inferences counter. It must be in there somewhere.
In some discussions with @mailseth, he asked if I see anything in the logs. I looked, but replied that nothing jumps out at me. Of course, I don't know what I'm looking for.

Chris Maunder15-May-24 5:06

Re: CPAI ver 2.6.2 failed inferences in Coral ver 2.2.2 vs YOLOv5 .NET?

15-May-24 5:06

Coral on Windows is just not great. There's no getting around it I'm sorry. Failed inferences could be anything from the device overheating and shutting down, to a memory issue, to the USB driver failing. I constantly have issues on Windows with Coral, far less so on Linux (or even macOS 11).

cheers
Chris Maunder

Steve Winn15-May-24 5:43

CPAI ver 2.6.2 YOLOv5.NET CPU vs GPU on status screen?

15-May-24 5:43

The Coral accelerator in the Windows Blue Iris Code Project machine is an M.2, not USB.
My impression is that although it is very fast, accuracy seems poor, and lack of any custom models, it finds everything, even if it's wrong.
My Coral USB device on the Ubuntu machine has been flawless with Frigate NVR for about 5 months. It is the only detector specified, so I know it is working.
My big gripe with Coral is that the test program that you are supposed to use according to the installation web page will not run without an older version of py and pycoral. (I think. I haven't tried it for several months.) I like to be able to use the manufacturer's diagnostics to verify functionality.

Steve Winn11-May-24 9:37

Re: CPAI ver 2.6.2 YOLOv5.NET CPU vs GPU on status screen?

11-May-24 9:37

I am seeing the YOLOv5 .NET module displaying CPU (DirectML) despite the module info screen showing that GPU is enabled. Did I read somewhere that there is something wrong in the code that displays CPU instead of GPU on the status screen? I don't remember where I heard this.

Sean Ewington13-May-24 7:47

Re: CPAI ver 2.6.2 YOLOv5.NET CPU vs GPU on status screen?

13-May-24 7:47

Thanks very much for your report. Could you please share your System Info tab from your CodeProject.AI Server dashboard?

Thanks,
Sean Ewington
CodeProject

Steve Winn13-May-24 9:00

Re: CPAI ver 2.6.2 YOLOv5.NET CPU vs GPU on status screen?

13-May-24 9:00

Server version:   2.6.2
System:           Windows
Operating System: Windows (Microsoft Windows 10.0.19045)
CPUs:             Intel(R) Core(TM) i5-7500 CPU @ 3.40GHz (Intel)
                  1 CPU x 4 cores. 4 logical processors (x64)
GPU (Primary):    Intel(R) HD Graphics 630 (1,024 MiB) (Intel Corporation) 
                  Driver: 31.0.101.2111
System RAM:       16 GiB
Platform:         Windows
BuildConfig:      Release
Execution Env:    Native
Runtime Env:      Production
Runtimes installed:
  .NET runtime:     7.0.5
  .NET SDK:         Not found
  Default Python:   Not found
  Go:               Not found
  NodeJS:           Not found
  Rust:             Not found
Video adapter info:
  Intel(R) HD Graphics 630:
    Driver Version     31.0.101.2111
    Video Processor    Intel(R) HD Graphics Family
System GPU info:
  GPU 3D Usage       0%
  GPU RAM Usage      0
Global Environment variables:
  CPAI_APPROOTPATH = <root>
  CPAI_PORT        = 32168

Sean Ewington15-May-24 1:32

Re: CPAI ver 2.6.2 YOLOv5.NET CPU vs GPU on status screen?

15-May-24 1:32

Thanks very much for that. And are you able to confirm that the GPU is actually being used for that module, but on the CodeProject.AI Server dashboard, CPU is displayed?

Thanks,
Sean Ewington
CodeProject

Mr Dunu14-May-24 14:48

Mr Dunu

14-May-24 14:48

I'm experiencing the exact same issue:

Server version:   2.6.2
System:           Windows
Operating System: Windows (Microsoft Windows 10.0.19045)
CPUs:             Intel(R) Core(TM) i5-8259U CPU @ 2.30GHz (Intel)
                  1 CPU x 4 cores. 8 logical processors (x64)
GPU (Primary):    Intel(R) Iris(R) Plus Graphics 655 (1,024 MiB) (Intel Corporation) 
                  Driver: 31.0.101.2127
System RAM:       16 GiB
Platform:         Windows
BuildConfig:      Release
Execution Env:    Native
Runtime Env:      Production
Runtimes installed:
  .NET runtime:     7.0.7
  .NET SDK:         Not found
  Default Python:   3.10.7
  Go:               Not found
  NodeJS:           12.16.3
  Rust:             Not found
Video adapter info:
  Intel(R) Iris(R) Plus Graphics 655:
    Driver Version     31.0.101.2127
    Video Processor    Intel(R) Iris(R) Plus Graphics Family
System GPU info:
  GPU 3D Usage       0%
  GPU RAM Usage      0
Global Environment variables:
  CPAI_APPROOTPATH = <root>
  CPAI_PORT        = 32168

Re: CPAI ver 2.6.2 YOLOv5.NET CPU vs GPU on status screen?

Sean Ewington15-May-24 1:32

Re: CPAI ver 2.6.2 YOLOv5.NET CPU vs GPU on status screen?

15-May-24 1:32

Thanks very much for that. And are you able to confirm that the GPU is actually being used for that module, but on the CodeProject.AI Server dashboard, CPU is displayed?

Thanks,
Sean Ewington
CodeProject

Steve Winn15-May-24 1:48

Re: CPAI ver 2.6.2 YOLOv5.NET CPU vs GPU on status screen?

15-May-24 1:48

I haven't been back to the machine yet, but the system info screen shows GPU usage=0.
Looked at the performance monitor just now, that shows occasional 3d activity, but nothing else. 1% memory constant. GPU0
Maybe it's not using the GPU.
I again clicked enable GPU, log says GPU enabled when the module restarts.
Maybe uninstall reinstall the module? I've uninstalled and reinstalled ver. 2.6.2 a couple of times already trying to figure out the Coral failed inferences. I just don't know.

Mr Dunu15-May-24 2:01

Mr Dunu

15-May-24 2:01

In my case, GPU is not used.

CPU (DirectML) is utilised despite selecting Enable GPU

Re: CPAI ver 2.6.2 YOLOv5.NET CPU vs GPU on status screen?

Chris Maunder15-May-24 2:38