New CodeProject.AI License Plate Recognition (YOLO11) Module
- Thread starter MikeLud1
- Start date
Mike,
I ran into this today. System had been running for 13 days or so, no changes so it, it's a headless system and only thing running on it is CPAI.
----
14:06:50:Response rec'd from License Plate Recognition (YOLO11 .NET) command 'alpr' (...2068b8) ['No license plates detected'] took 30ms
14:06:50:ALPRYOLO11NET.exe: Error detecting plates: [ErrorCode:Fail] D:\a\_work\1\s\onnxruntime\core\providers\dml\DmlExecutionProvider\src\ExecutionProvider.cpp(962)\onnxruntime.DLL!00007FFCF5EB8B59: (caller: 00007FFCF5EB8FA9) Exception(3839) tid(2db0) 887A0005 The GPU device instance has been suspended. Use GetDeviceRemovedReason to determine the appropriate action.
14:06:50:Response rec'd from License Plate Recognition (YOLO11 .NET) command 'alpr' (...f80447) ['No license plates detected'] took 8ms
14:06:50:ALPRYOLO11NET.exe: Error detecting plates: [ErrorCode:Fail] D:\a\_work\1\s\onnxruntime\core\providers\dml\DmlExecutionProvider\src\ExecutionProvider.cpp(962)\onnxruntime.DLL!00007FFCF5EB8B59: (caller: 00007FFCF5EB8FA9) Exception(3841) tid(2db0) 887A0005 The GPU device instance has been suspended. Use GetDeviceRemovedReason to determine the appropriate action.
14:06:50:Response rec'd from License Plate Recognition (YOLO11 .NET) command 'alpr' (...86caf2) ['No license plates detected'] took 12ms
14:06:50:ALPRYOLO11NET.exe: Error detecting plates: [ErrorCode:Fail] D:\a\_work\1\s\onnxruntime\core\providers\dml\DmlExecutionProvider\src\ExecutionProvider.cpp(962)\onnxruntime.DLL!00007FFCF5EB8B59: (caller: 00007FFCF5EB8FA9) Exception(3843) tid(2db0) 887A0005 The GPU device instance has been suspended. Use GetDeviceRemovedReason to determine the appropriate action.
14:06:50:Response rec'd from License Plate Recognition (YOLO11 .NET) command 'alpr' (...43d4d6) ['No license plates detected'] took 15ms
14:06:53:ALPRYOLO11NET.exe: Error detecting plates: [ErrorCode:Fail] D:\a\_work\1\s\onnxruntime\core\providers\dml\DmlExecutionProvider\src\ExecutionProvider.cpp(962)\onnxruntime.DLL!00007FFCF5EB8B59: (caller: 00007FFCF5EB8FA9) Exception(3845) tid(2db0) 887A0005 The GPU device instance has been suspended. Use GetDeviceRemovedReason to determine the appropriate action.
14:06:53:Response rec'd from License Plate Recognition (YOLO11 .NET) command 'alpr' (...c9e3c3) ['No license plates detected'] took 9ms
----
I restarted the module and it took about 5 mins or so to start (which is normally how long it takes on this system), and then it started working fine again. This is on a clean Windows 10 install with 11th gen Intel iGPU.
I ran into this today. System had been running for 13 days or so, no changes so it, it's a headless system and only thing running on it is CPAI.
----
14:06:50:Response rec'd from License Plate Recognition (YOLO11 .NET) command 'alpr' (...2068b8) ['No license plates detected'] took 30ms
14:06:50:ALPRYOLO11NET.exe: Error detecting plates: [ErrorCode:Fail] D:\a\_work\1\s\onnxruntime\core\providers\dml\DmlExecutionProvider\src\ExecutionProvider.cpp(962)\onnxruntime.DLL!00007FFCF5EB8B59: (caller: 00007FFCF5EB8FA9) Exception(3839) tid(2db0) 887A0005 The GPU device instance has been suspended. Use GetDeviceRemovedReason to determine the appropriate action.
14:06:50:Response rec'd from License Plate Recognition (YOLO11 .NET) command 'alpr' (...f80447) ['No license plates detected'] took 8ms
14:06:50:ALPRYOLO11NET.exe: Error detecting plates: [ErrorCode:Fail] D:\a\_work\1\s\onnxruntime\core\providers\dml\DmlExecutionProvider\src\ExecutionProvider.cpp(962)\onnxruntime.DLL!00007FFCF5EB8B59: (caller: 00007FFCF5EB8FA9) Exception(3841) tid(2db0) 887A0005 The GPU device instance has been suspended. Use GetDeviceRemovedReason to determine the appropriate action.
14:06:50:Response rec'd from License Plate Recognition (YOLO11 .NET) command 'alpr' (...86caf2) ['No license plates detected'] took 12ms
14:06:50:ALPRYOLO11NET.exe: Error detecting plates: [ErrorCode:Fail] D:\a\_work\1\s\onnxruntime\core\providers\dml\DmlExecutionProvider\src\ExecutionProvider.cpp(962)\onnxruntime.DLL!00007FFCF5EB8B59: (caller: 00007FFCF5EB8FA9) Exception(3843) tid(2db0) 887A0005 The GPU device instance has been suspended. Use GetDeviceRemovedReason to determine the appropriate action.
14:06:50:Response rec'd from License Plate Recognition (YOLO11 .NET) command 'alpr' (...43d4d6) ['No license plates detected'] took 15ms
14:06:53:ALPRYOLO11NET.exe: Error detecting plates: [ErrorCode:Fail] D:\a\_work\1\s\onnxruntime\core\providers\dml\DmlExecutionProvider\src\ExecutionProvider.cpp(962)\onnxruntime.DLL!00007FFCF5EB8B59: (caller: 00007FFCF5EB8FA9) Exception(3845) tid(2db0) 887A0005 The GPU device instance has been suspended. Use GetDeviceRemovedReason to determine the appropriate action.
14:06:53:Response rec'd from License Plate Recognition (YOLO11 .NET) command 'alpr' (...c9e3c3) ['No license plates detected'] took 9ms
----
I restarted the module and it took about 5 mins or so to start (which is normally how long it takes on this system), and then it started working fine again. This is on a clean Windows 10 install with 11th gen Intel iGPU.
Attachments
BI does this
Thanks for the feedback, I will look into this over the weekend.
What version of Blue Iris are you on this may be an issue with a GPU memory leak that one of the beta version had
I'm on 5.9.9.73 on BI. It's running on identical hardware but not the same machine as CPAI.
I just noticed that this also happened today with my dev/test system. This runs on the same versions of everything as my "production" system, BI/CPAI are also running on separate physical machines.
20:45:32:Response rec'd from License Plate Recognition (YOLO11 .NET) command 'alpr' (...4aa61f) ['No license plates detected'] took 42ms
20:45:32:ALPRYOLO11NET.exe: Error detecting plates: [ErrorCode:Fail] D:\a\_work\1\s\onnxruntime\core\providers\dml\DmlExecutionProvider\src\ExecutionProvider.cpp(962)\onnxruntime.DLL!00007FFF8E558B59: (caller: 00007FFF8E558FA9) Exception(10329) tid(7c) 887A0005 The GPU device instance has been suspended. Use GetDeviceRemovedReason to determine the appropriate action.
20:45:32:Response rec'd from License Plate Recognition (YOLO11 .NET) command 'alpr' (...ca7528) ['No license plates detected'] took 28ms
20:45:32:ALPRYOLO11NET.exe: Error detecting plates: [ErrorCode:Fail] D:\a\_work\1\s\onnxruntime\core\providers\dml\DmlExecutionProvider\src\ExecutionProvider.cpp(962)\onnxruntime.DLL!00007FFF8E558B59: (caller: 00007FFF8E558FA9) Exception(10331) tid(7c) 887A0005 The GPU device instance has been suspended. Use GetDeviceRemovedReason to determine the appropriate action.
20:45:32:Response rec'd from License Plate Recognition (YOLO11 .NET) command 'alpr' (...aa740c) ['No license plates detected'] took 43ms
20:45:33:ALPRYOLO11NET.exe: Error detecting plates: [ErrorCode:Fail] D:\a\_work\1\s\onnxruntime\core\providers\dml\DmlExecutionProvider\src\ExecutionProvider.cpp(962)\onnxruntime.DLL!00007FFF8E558B59: (caller: 00007FFF8E558FA9) Exception(10333) tid(7c) 887A0005 The GPU device instance has been suspended. Use GetDeviceRemovedReason to determine the appropriate action.
20:45:33:Response rec'd from License Plate Recognition (YOLO11 .NET) command 'alpr' (...de2452) ['No license plates detected'] took 34ms
20:45:32:Response rec'd from License Plate Recognition (YOLO11 .NET) command 'alpr' (...4aa61f) ['No license plates detected'] took 42ms
20:45:32:ALPRYOLO11NET.exe: Error detecting plates: [ErrorCode:Fail] D:\a\_work\1\s\onnxruntime\core\providers\dml\DmlExecutionProvider\src\ExecutionProvider.cpp(962)\onnxruntime.DLL!00007FFF8E558B59: (caller: 00007FFF8E558FA9) Exception(10329) tid(7c) 887A0005 The GPU device instance has been suspended. Use GetDeviceRemovedReason to determine the appropriate action.
20:45:32:Response rec'd from License Plate Recognition (YOLO11 .NET) command 'alpr' (...ca7528) ['No license plates detected'] took 28ms
20:45:32:ALPRYOLO11NET.exe: Error detecting plates: [ErrorCode:Fail] D:\a\_work\1\s\onnxruntime\core\providers\dml\DmlExecutionProvider\src\ExecutionProvider.cpp(962)\onnxruntime.DLL!00007FFF8E558B59: (caller: 00007FFF8E558FA9) Exception(10331) tid(7c) 887A0005 The GPU device instance has been suspended. Use GetDeviceRemovedReason to determine the appropriate action.
20:45:32:Response rec'd from License Plate Recognition (YOLO11 .NET) command 'alpr' (...aa740c) ['No license plates detected'] took 43ms
20:45:33:ALPRYOLO11NET.exe: Error detecting plates: [ErrorCode:Fail] D:\a\_work\1\s\onnxruntime\core\providers\dml\DmlExecutionProvider\src\ExecutionProvider.cpp(962)\onnxruntime.DLL!00007FFF8E558B59: (caller: 00007FFF8E558FA9) Exception(10333) tid(7c) 887A0005 The GPU device instance has been suspended. Use GetDeviceRemovedReason to determine the appropriate action.
20:45:33:Response rec'd from License Plate Recognition (YOLO11 .NET) command 'alpr' (...de2452) ['No license plates detected'] took 34ms
@PeteJ Since you had this issue I have be testing both the License Plate Recognition (YOLO11 .NET) 1.1.1 and the Object Detection (YOLO11 .NET) 1.4.0 modules on a similar system like yours to see if I can recreate the errors you were having and so far I did not have any issues.
Maybe you had a Windows update or some else happen when the errors happen. You can run Reliability Monitor and check if something did happen the time when you had the errors.
Mike, I didn't notice anything unusual, there were 2 Intel driver updates, one of them appear to be a video driver update based on the version numbering--but the running system currently shows an older
driver (32.0.101.6881) vs the updated one in system history (32.0.101.7026). It's been working fine since. Maybe it's just a Window's thing.
Thanks!
driver (32.0.101.6881) vs the updated one in system history (32.0.101.7026). It's been working fine since. Maybe it's just a Window's thing.
Thanks!
Any Linux support yet? I looked through and didn't see it yet.
Thought seeing Codeproject AI is stuck, maybe I could just go native on that BI box.
Thought seeing Codeproject AI is stuck, maybe I could just go native on that BI box.
Hello ! Thanks a lot for the great job! Just wandering is this is supposed to recognise also Italian Plates, or if we need to create a specific model ... On my setup plated detection is very unreliable and got worst as BI releases increased. I can't understand if there are braking changes, but I don't think so.
It should work with Italian Plates, can you post some full resolution images of cars with plates so I can test them.
Will send the images via DM
I've tried using License-plate-v5 from the explorer and very seldomly I get DayPlate.
I've tried using License-plate-v5 from the explorer and very seldomly I get DayPlate.
Last edited:
Sorry, I'm kindly asking for a clarification here.
How does BI process an image for ALPR?
If in the camera AI setting I've specified license-plate for the custom model, I suppose that BI will check if in the image there is a plate using the model in the folder
'C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLO11Net\custom-models-v5'
Then it sends the cropped image of the License Plate to the ALPR engine of CPAI, that only does OCR ? or does it send the full image and then CPAI alpr will try to find the plate again using the models in the folder
' C:\Program Files\CodeProject\AI\modules\ALPRYOLO11NET\models' ?
and then do ALPR?
If alpr API call would do the full image processing again, it would explain why using the CPAI explorer I don't get good results using the license-plate custom model, but I get excellent results using the alpr test feature.
Maybe I could just reuse the plate_detector.onnx model for initial filterning of car images or even use the regular object detection to detect a car and let alpr API to do the rest...
Am I getting the process wrong?
How does BI process an image for ALPR?
If in the camera AI setting I've specified license-plate for the custom model, I suppose that BI will check if in the image there is a plate using the model in the folder
'C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLO11Net\custom-models-v5'
Then it sends the cropped image of the License Plate to the ALPR engine of CPAI, that only does OCR ? or does it send the full image and then CPAI alpr will try to find the plate again using the models in the folder
' C:\Program Files\CodeProject\AI\modules\ALPRYOLO11NET\models' ?
and then do ALPR?
If alpr API call would do the full image processing again, it would explain why using the CPAI explorer I don't get good results using the license-plate custom model, but I get excellent results using the alpr test feature.
Maybe I could just reuse the plate_detector.onnx model for initial filterning of car images or even use the regular object detection to detect a car and let alpr API to do the rest...
Am I getting the process wrong?
The flow is described in details here:
Thanks for posting the link. I went through it , but I think that is just related to the ALPR part, not BI. I think BI is not sending any ALPR requests if it doesn't find a License Plate throught the custom model. I suppose then, that it could be just necessary to untick vehicles detection in BI to have ALPR processing everything.
It is why I asked you to post images from your plate camera - many times people come to this thread or create a new one because their ALPR isn't working and it turns out they have too wide a view and it won't work.
I don't know if that is the issue in your situation, but it is a common one we see of someone trying to do too much with one camera and thinking these things are like we see on TV and the movies.