5.5.8 - June 13, 2022 - Code Project’s SenseAI,

[Alan_F]

I can't seem to get the LPR module to install. I've read back about 10 pages on the forum here. I tried the full uninstall, deleted the two folders, then reinstalled, but no files ever show up in the C:\Program Files\CodeProject\AI\modules\ALPR\bin\windows\python37 folder, which explains the 'cannot find the file specified' error below. I get a similar error when I try to install the OCR module. I only have YOLOv5 6.2 running in CUDA GPU mode.

Also C:\Program Files\CodeProject\AI\downloads\windows\python37 is empty, which is probably the source of the downstream issue.

Any ideas?


Here are the logs from the install attempt:

14:15:42: ALPR has left the building
14:15:42: Starting C:\Program Files...ws\python37\venv\Scripts\python "C:\Program Files...\modules\ALPR\ALPR_adapter.py"
14:15:42:
14:15:42: Module 'License Plate Reader' (ID: ALPR)
14:15:42: Active: True
14:15:42: GPU: Support enabled
!14:15:42: Parallelism: 0
!14:15:42: Platforms: windows,linux,macos,macos-arm64
!14:15:42: FilePath: ALPR_adapter.py
!14:15:42: ModulePath: ALPR
!14:15:42: Install: PostInstalled
!14:15:42: Runtime:
!14:15:42: Queue: ALPR_queue
!14:15:42: Start pause: 1 sec
!14:15:42: Valid: True
!14:15:42: Environment Variables
!14:15:42: PLATE_CONFIDENCE = 0.4
!14:15:42:
!14:15:42: Error trying to start License Plate Reader (ALPR_adapter.py)
!14:15:42: An error occurred trying to start process 'C:\Program Files\CodeProject\AI\modules\ALPR\bin\windows\python37\venv\Scripts\python' with working directory 'C:\Program Files\CodeProject\AI\modules\ALPR'. The system cannot find the file specified.
!14:15:42: at System.Diagnostics.Process.StartWithCreateProcess(ProcessStartInfo startInfo) at CodeProject.AI.API.Server.Frontend.ModuleRunner.StartProcess(ModuleConfig module)
!14:15:42: *** Please check the CodeProject.AI installation completed successfully
!14:16:29: Response received (id 1e4262b7-1540-41d8-93ad-68113c588399)
!14:17:00: Queued: 'custom' request, id c96ee7d0-e235-4862-a510-068ea5719602

 

[MikeLud1]

I can't seem to get the LPR module to install. I've read back about 10 pages on the forum here. I tried the full uninstall, deleted the two folders, then reinstalled, but no files ever show up in the C:\Program Files\CodeProject\AI\modules\ALPR\bin\windows\python37 folder, which explains the 'cannot find the file specified' error below. I get a similar error when I try to install the OCR module. I only have YOLOv5 6.2 running in CUDA GPU mode.

Also C:\Program Files\CodeProject\AI\downloads\windows\python37 is empty, which is probably the source of the downstream issue.

Any ideas?


Here are the logs from the install attempt:

What version CP.AI are you on, should be v2.0.6? there where some issues with previous versions of 2.0.X.
Also you may what to check you antivirus and firewall to see if it is blocking CP.AI

 

[Alan_F]

What version CP.AI are you on, should be v2.0.6? there where some issues with previous versions of 2.0.X.
Also you may what to check you antivirus and firewall to see if it is blocking CP.AI

Yes, it is 2.0.6. I am only running Windows Defender, and I don't see any alerts from it. I turned off the anti-ransomware folder protection (which also was not throwing any alerts) and that didn't help either. I double-checked that this machine isn't using my ad-blocking proxy. I'm running out of things to check.

I think I'll try a full install on my other Windows box and see what it does.

Edit: It installed on my other computer but didn't seem to be working. It did however download the Python3.7 files. I copied that folder to my other PC, ran a repair, rebooted, and then installed the ALPR module. It looks like it successfully installed, but it isn't giving any returns when I test it in the Explorer. At least that's some progress. Maybe I'll try it in Docker tomorrow.

 

[ChrisPDuck]

Is anyone else getting significantly slower detection with 2.0.6 compared to 1.6.8.0?

I'm running:
An i5-11500 with 32Gb of RAM (no seperate graphics card)
Windows and Blue Iris (program, database and alerts) running off a NVME SSD
5 x 4k camera's. Cameras 1-3 recording to a 6Tb WD purple and camera's 4 and 5 recording to a 2nd 6Tb WD purple
24/7 substream recording and 4k alerts
4 cameras use substream for AI and 1 uses 4k (also captures license plates and gets a much better hit rate with 4k)

I ran DeepStack for the best part of a year and never had an issue
Changed to SenseAI 1.6.8.0 very early Jan and saw a slight speed improvement but a huge consistency improvement (fastest to slowest detection massively reduced)
I upgraded to 2.0.6 recently and both speed and accuracy have become much worse

Below shows the average response times for the 2 versions for each camera:

	1.6.8.0 (ms)	2.0.6 (ms)	Increase	Note
Garage	265.9​	507.4​	91%​	4k
House	124.3​	503.4​	305%​	Substream
Porch	147.5​	531.2​	260%​	Substream
Shed	117.9​	296.2​	151%​	Substream

While the number of samples on the new version is a lot smaller they are still >100 for each camera.

	1.6.8.0	2.0.6
Garage	906​	166​
House	642​	154​
Porch	420​	107​
Shed	157​	160​
Total	656​	1838​

Whilst I can't quantity it in the same way the number of missed objects also feels like it has gone up significantly (those where the 'Nothing Found' is returned but there was a person / vehicle in frame) especially in low light.

Blue Iris was on version 5.6.7.3 for all samples in the above data (now updated to 5.6.8.4 to see if that made a difference, it didn't)
Blue Iris was set to 'Medium' object detection for both versions
The single YOLOv5 6.2 is running on SenseAI, the single YOLO was running on the old version too (I didn't note the version before I uninstalled the old version)
I upgraded by stopping Blue Iris and SenseAI, uninstalling SenseAI, restarting, installing the new SenseAI then rebooting again

Any thoughts or suggestions would be more than welcome, I still have the install package for the old version so can downgrade but I thought I'd read most users seemed to be getting quicker times so I wonder why mine is different

 

[MikeLud1]

Is anyone else getting significantly slower detection with 2.0.6 compared to 1.6.8.0?

I'm running:
An i5-11500 with 32Gb of RAM (no seperate graphics card)
Windows and Blue Iris (program, database and alerts) running off a NVME SSD
5 x 4k camera's. Cameras 1-3 recording to a 6Tb WD purple and camera's 4 and 5 recording to a 2nd 6Tb WD purple
24/7 substream recording and 4k alerts
4 cameras use substream for AI and 1 uses 4k (also captures license plates and gets a much better hit rate with 4k)

I ran DeepStack for the best part of a year and never had an issue
Changed to SenseAI 1.6.8.0 very early Jan and saw a slight speed improvement but a huge consistency improvement (fastest to slowest detection massively reduced)
I upgraded to 2.0.6 recently and both speed and accuracy have become much worse

Below shows the average response times for the 2 versions for each camera:

	1.6.8.0 (ms)	2.0.6 (ms)	Increase	Note
Garage	265.9​	507.4​	91%​	4k
House	124.3​	503.4​	305%​	Substream
Porch	147.5​	531.2​	260%​	Substream
Shed	117.9​	296.2​	151%​	Substream

While the number of samples on the new version is a lot smaller they are still >100 for each camera.

	1.6.8.0	2.0.6
Garage	906​	166​
House	642​	154​
Porch	420​	107​
Shed	157​	160​
Total	656​	1838​

Whilst I can't quantity it in the same way the number of missed objects also feels like it has gone up significantly (those where the 'Nothing Found' is returned but there was a person / vehicle in frame) especially in low light.


Blue Iris was on version 5.6.7.3 for all samples in the above data (now updated to 5.6.8.4 to see if that made a difference, it didn't)
Blue Iris was set to 'Medium' object detection for both versions
The single YOLOv5 6.2 is running on SenseAI, the single YOLO was running on the old version too (I didn't note the version before I uninstalled the old version)
I upgraded by stopping Blue Iris and SenseAI, uninstalling SenseAI, restarting, installing the new SenseAI then rebooting again

Any thoughts or suggestions would be more than welcome, I still have the install package for the old version so can downgrade but I thought I'd read most users seemed to be getting quicker times so I wonder why mine is different

I think I know why the increase in detection times, If you want I send you a file to replace and test until it gets fixed.

 

[Vettester]

I think I know why the increase in detection times, If you want I send you a file to replace and test until it gets fixed.

You can send it to me, I’d like to try it.

 

[MikeLud1]

You can send it to me, I’d like to try it.

You need to replace detect_adapter.py

 

[Vettester]

You need to replace detect_adapter.py

Thanks Mike!

 

[ChrisPDuck]

Thanks Mike
Will give it a go and report back

I added the change from DeepStack for completeness, as can be seen there is definitely the potential for SenseAI to go faster.

Detection Times		Number of samples
	DeepStack (ms)	1.6.8.0 (ms)	2.0.6 (ms)	Note			DeepStack (ms)	1.6.8.0	2.0.6
Garage	343.4​	265.9​	507.4​	4k		Garage	1,193	906	166
House	313.9​	124.3​	503.4​	Substream		House	840	642	154
Porch	311.3​	147.5​	531.2​	Substream		Porch	478	420	107
Shed	232.8​	117.9​	296.2​	Substream		Shed	769	157	160
Overall	305.2​	188.7​	446.5​			Total	3,280	656	1,838

 

[ChrisPDuck]

Thanks Mike
Using that file and a few tests the times were in the 170-180ms range so a huge improvement over the >500ms most cameras took on 2.0.6.
Not quite as good as 1.6.8.0 so far but that was only a handful of tests in light that is failing but not quite reduced enough for the cameras to flip to B&W so I'll see how this is looking after a couple of weeks normal use.

Thanks for the help

 

[CrazyAsYou]

You need to replace detect_adapter.py

I see this dropping the resolution down from 640 to 416. I assume this is only any good if you're using medium models which should be 416 but would make no difference to us using larger models @ 640?

 

[AlphaBlueIris]

I installed codeproject 2.6 on an server with GPU, currently running a blueiris evaluation. On a good note, codeproject sees that I have a GPU. Quick recap, I coped the configuration that is working from the other server and it coped successfully all the values, cameras and etc. Unfortunately while I'm getting the alert on the other server no alerts on this one. In codeproject I'm getting this message. Timeout connecting to the server, alghouth the codeproject shows that is up and running using GPU and CPU. At one point I disabled the GPU without any effect to the alerts.

Thank you, this is a great group by the way.

Sent from my SM-S906U using Tapatalk

 

[MikeLud1]

Update on the ALPR module Blue Iris integration, Ken is working on this today and hopefully should be in the next Blue Iris release

 

[lk229]

For those that upgraded to 2.0.x, are you seeing better detection response or better accuracy? Is is stable at this point or should we wait until some of the initial reported bugs are ironed out?

I have detections set using ipcam-combined.pt and delivery.pt. My detections relying on the delivery.pt model never worked - everything was detected as FedEx. Since upgrading to the 2.06 beta, I get the correct indications for UPS, USPS, Amazon, etc. I did not make any other changes.

 

[Nunofya]

Update on the ALPR module Blue Iris integration, Ken is working on this today and hopefully should be in the next Blue Iris release

It's out with new BI update!

 

[sp3ctre]

It's out with new BI update!

Can someone point me in the direction of how to use it please? I'm not sure what settings to use on the following screen. Also, do we have access to the plate as a variable to be able to pass to an API?

Thanks

 

[Vettester]

I didn't change anything on the way mine is setup, but I don't think it is configured correctly. I got 1 license plate when the app first started and I enabled the LAPR option, but now all of my dayplate captures are going into the canceled alerts folder.



@MikeLud1 - Mike would you please give us some guidance on how to optimize this?



Edit: The CPAI Server seems to be capturing the plates.

 

[MikeLud1]

I didn't change anything on the way mine is setup, but I don't think it is configured correctly. I got 1 license plate when the app first started and I enabled the LAPR option, but now all of my dayplate captures are going into the canceled alerts folder.

View attachment 151859

@MikeLud1 - Mike would you please give us some guidance on how to optimize this?

View attachment 151858

Edit: The CPAI Server seems to be capturing the plates.

View attachment 151860

Below are my setting, I am still confirming on how Ken setup the integration.
In the camera AI setting I am using "t" so the AI runs all 4 real-time images

 

[Vettester]

Below are my setting, I am still confirming on how Ken setup the integration.
In the camera AI setting I am using "t" so the AI runs all 4 real-time images

View attachment 151861
View attachment 151862

Hmmm…it just started working on it's own.

 

[MikeLud1]

Also with the latest Blue Iris update Object Detection (YOLOv5 .NET) custom models now work. Blue Iris pulls the custom model list from CodeProject.AI's API, so no more folders to set for custom models.