|
Which Docker image are you running?
"Mistakes are prevented by Experience. Experience is gained by making mistakes."
|
|
|
|
|
This is a fatal bug in the 2.5.4 (or maybe 2.5.5) version of the Linux Docker images that should be fixed in the 2.5.6 version of the Linux Docker images. To the best of my knowledge, a 2.5.6 Docker image for the RPi has not been released yet.
"Mistakes are prevented by Experience. Experience is gained by making mistakes."
|
|
|
|
|
We've released rpi64-2.5.6, please let us know if that helps.
Docker[^]
Thanks,
Sean Ewington
CodeProject
modified 14-Mar-24 12:22pm.
|
|
|
|
|
Works fine now with 2.5.6+0001
Thanks for all the work !
|
|
|
|
|
Same issue here, tried Arm64 version on Mac M1 and Oracle VM (Arm), both the same issue.
Mac: Docker version 24.0.6, build ed223bc
Oracle VM: Docker version 24.0.5, build 24.0.5-0ubuntu1~22.04.1
modified 14-Mar-24 12:22pm.
|
|
|
|
|
Thanks very much for the message. Does 2.6.2 work for you?
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
Hi there,
Am trying to install 2.1.4 of Object Detection with Coral. The install fails with the following two errors:
21:57:30:ObjectDetectionCoral: ERROR:root:Unable to create interpreter for TPU usb:0: Failed to load delegate from edgetpu.dll
21:57:30:ObjectDetectionCoral: WARNING:root:Unable to create interpreter for CPU using edgeTPU library: Failed to load delegate from edgetpu.dll
When I remove the module and re-install I receive the following errors:
22:27:43:objectdetection_coral_adapter.py: WARNING: Logging before InitGoogleLogging() is written to STDERR
22:27:43:objectdetection_coral_adapter.py: I20240303 22:27:43.622051 3948 pipelined_model_runner.cc:171] Thread: 3948 receives empty request
22:27:43:objectdetection_coral_adapter.py: I20240303 22:27:43.622051 3948 pipelined_model_runner.cc:244] Thread: 3948 is shutting down the pipeline...
22:27:43:objectdetection_coral_adapter.py: I20240303 22:27:43.622051 3948 pipelined_model_runner.cc:254] Thread: 3948 Pipeline is off.
22:27:43:objectdetection_coral_adapter.py: I20240303 22:27:43.622051 10928 pipelined_model_runner.cc:206] Queue is empty and `StopWaiters()` is called.
22:27:43:objectdetection_coral_adapter.py: I20240303 22:27:43.623049 3948 pipelined_model_runner.cc:171] Thread: 3948 receives empty request
22:27:43:objectdetection_coral_adapter.py: E20240303 22:27:43.623049 3948 pipelined_model_runner.cc:239] Thread: 3948 Pipeline was turned off before.
22:27:43:objectdetection_coral_adapter.py: I20240303 22:27:43.623049 3948 pipelined_model_runner.cc:206] Queue is empty and `StopWaiters()` is called.
22:27:43:objectdetection_coral_adapter.py: E20240303 22:27:43.623049 3948 pipelined_model_runner.cc:239] Thread: 3948 Pipeline was turned off before.
22:27:43:objectdetection_coral_adapter.py: E20240303 22:27:43.623049 3948 pipelined_model_runner.cc:146] Failed to shutdown status: INTERNAL: Pipeline was turned off before.
The error reported by Agent when motion is detected on a camera is:
10:35:17 PM Front Door: SetFailed: Message from CPAI: Unable to create interpreter at CoreLogic.AI.ObjectRecognizer.<Detect>d__7.MoveNext()
Any suggestions would be appreciated. Thanks.
modified 5-Mar-24 11:34am.
|
|
|
|
|
I’m not sure what’s going wrong, but wanted to mention that the messages in your second block quote are normal. While they look like errors, most are not.
It’s common to have problems with the Coral USB connection, but I don’t have a good answer for solutions there.
|
|
|
|
|
I'll need more info, but am I right in assuming Coral.AI using USB on Windows?
"unable to create interpter" is something I see often in this setup. For me, I either unplug the USB and try a different port, or restart the Coral module itself. It's very finicky unfortunately.
cheers
Chris Maunder
|
|
|
|
|
Thanks for the reply Chris,
Yes the coral stick is connected via USB. After re-installing the module a number of times I have managed to get the install to complete without the error in the first code block, however in all cases I still receive the errors in the second and third code block (the last code block is from Agent itself when it tries to call the object detection).
For now I have rolled back to CPAI beta 2.1.11 as this works flawlessly with my coral stick.
|
|
|
|
|
HI Everyone, trying to get CPAI setup to read license plates in blue iris. I have tried installing and reinstalling the module a few times, and the same error keeps happening below with the ALPR module every time I run it. Any ideas on why this may be happening>
I am using the following versions
CPAI Version: 2.5.4
Object Detection (YOLOv5 6.2) 1.9.1
License Plate Reader 3.0.2
15:08:02:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:45:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:45:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:45:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:45:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:45:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:45:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:45:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:45:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:45:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:45:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:45:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:45:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:45:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:45:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:45:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:45:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:45:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:46:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:46:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:46:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:46:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:46:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:46:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:46:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:46:ALPR_adapter.py: No open session available for ALPR to connect to the server.alpr_queue: No open session available for ALPR to connect to the server.
15:08:46:ALPR_adapter.py: No open session available for ALPR to connect to the server.alpr_queue: No open session available for ALPR to connect to the server.
15:08:46:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:46:ALPR_adapter.py: No open session available for ALPR to connect to the server.alpr_queue: No open session available for ALPR to connect to the server.
15:08:46:ALPR_adapter.py: No open session available for ALPR to connect to the server.alpr_queue: No open session available for ALPR to connect to the server.
15:08:46:ALPR_adapter.py: No open session available for ALPR to connect to the server.alpr_queue: No open session available for ALPR to connect to the server.
15:08:46:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:46:ALPR_adapter.py: No open session available for ALPR to connect to the server.alpr_queue: No open session available for ALPR to connect to the server.
15:08:46:ALPR_adapter.py: No open session available for ALPR to connect to the server.alpr_queue: No open session available for ALPR to connect to the server.
15:08:46:ALPR_adapter.py: No open session available for ALPR to connect to the server.alpr_queue: No open session available for ALPR to connect to the server.
15:08:46:ALPR_adapter.py: No open session available for ALPR to connect to the server.alpr_queue: No open session available for ALPR to connect to the server.
15:08:46:ALPR_adapter.py: No open session available for ALPR to connect to the server.alpr_queue: No open session available for ALPR to connect to the server.
15:08:46:ALPR_adapter.py: No open session available for ALPR to connect to the server.alpr_queue: No open session available for ALPR to connect to the server.
15:08:46:ALPR_adapter.py: Unable to store log entry: Permission denied
15:08:46:ALPR_adapter.py: No open session available for ALPR to connect to the server.alpr_queue: No open session available for ALPR to connect to the server.
15:08:46:ALPR_adapter.py: No open session available for ALPR to connect to the server.alpr_queue: No open session available for ALPR to connect to the server.
15:08:46:ALPR_adapter.py: No open session available for ALPR to connect to the server.alpr_queue: No open session available for ALPR to connect to the server.
modified 14-Mar-24 12:25pm.
|
|
|
|
|
Thanks very much for your report. Could you please share your System Info tab from your CodeProject.AI Server dashboard?
Thanks,
Sean Ewington
CodeProject
modified 14-Mar-24 12:25pm.
|
|
|
|
|
I am having the same issue heres the info for me:
<pre>Server version: 2.5.4
System: Windows
Operating System: Windows (Microsoft Windows 10.0.19045)
CPUs: Intel(R) Core(TM) i5-9600K CPU @ 3.70GHz (Intel)
1 CPU x 6 cores. 6 logical processors (x64)
GPU (Primary): NVIDIA GeForce RTX 2070 (8 GiB) (NVIDIA)
Driver: 551.23, CUDA: 12.4 (up to: 12.4), Compute: 7.5, cuDNN:
System RAM: 32 GiB
Platform: Windows
BuildConfig: Release
Execution Env: Native
Runtime Env: Production
.NET framework: .NET 7.0.5
Default Python:
Video adapter info:
NVIDIA GeForce RTX 2070:
Driver Version 31.0.15.5123
Video Processor NVIDIA GeForce RTX 2070
System GPU info:
GPU 3D Usage 0%
GPU RAM Usage 1 GiB
Global Environment variables:
CPAI_APPROOTPATH = <root>
CPAI_PORT = 32168
modified 14-Mar-24 12:25pm.
|
|
|
|
|
Hi there,
I have an ongoing issue after updating to ALPR 2.5. I have re-installed a few times but continue to receive the below error and ALPR fails to detect plate numbers in Agent 5.3. Not sure if there is any particular fix or if it's possible to roll back to the previous version?
Many thanks for any suggestions.
21:55:05:License Plate Reader: [KeyError] : Traceback (most recent call last):
File "C:\Program Files\CodeProject\AI\modules\ALPR\ALPR.py", line 86, in detect_platenumber
if not detect_plate_response["success"]:
KeyError: 'success'
modified 4-Mar-24 16:23pm.
|
|
|
|
|
You are on an old version of the ALPR module. Try update CodeProject.AI. The current version of CodeProject.AI has version 3.0.2 of the ALPR module.
|
|
|
|
|
Version 2.5.4 has been working quite well for me in GPU mode.
Blue Iris making the API calls with ipcam-combined
I have noticed a runtime error two times. No major problems and the system keeps running just fine.
Just thought I would post the traceback as feedback for the developers.
Thank you for all of your time and work.
12:39:33:Object Detection (YOLOv5 6.2): [RuntimeError] : Traceback (most recent call last):
File "C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-6.2\detect.py", line 141, in do_detection
det = detector(img, size=640)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\torch\nn\modules\module.py", line 1190, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\torch\autograd\grad_mode.py", line 27, in decorate_context
return func(*args, **kwargs)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\yolov5\models\common.py", line 705, in forward
y = self.model(x, augment=augment) # forward
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\torch\nn\modules\module.py", line 1190, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\yolov5\models\common.py", line 515, in forward
y = self.model(im, augment=augment, visualize=visualize) if augment or visualize else self.model(im)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\torch\nn\modules\module.py", line 1190, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\Lib\site-packages\yolov5\models\yolo.py", line 209, in forward
return self._forward_once(x, profile, visualize) # single-scale inference, train
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\Lib\site-packages\yolov5\models\yolo.py", line 121, in _forward_once
x = m(x) # run
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\torch\nn\modules\module.py", line 1190, in _call_impl
return forward_call(*input, **kwargs)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\Lib\site-packages\yolov5\models\yolo.py", line 75, in forward
wh = (wh * 2) ** 2 * self.anchor_grid[i] # wh
RuntimeError: The size of tensor a (48) must match the size of tensor b (80) at non-singleton dimension 3
modified 5-Mar-24 11:42am.
|
|
|
|
|
Thanks very much for your report. Is the module still working for you?
Also, could you please share your System Info tab from your CodeProject.AI Server dashboard?
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
Yes it works great, only see that error a couple times a day.
YOLO5 6.2
Today 51718 inferences
Only 2 errors
average time 113.8
Server version: 2.5.4
System: Windows
Operating System: Windows (Microsoft Windows 10.0.19045)
CPUs: Intel(R) Core(TM) i7-4790K CPU @ 4.00GHz (Intel)
1 CPU x 4 cores. 8 logical processors (x64)
GPU (Primary): NVIDIA GeForce GTX 1650 (4 GiB) (NVIDIA)
Driver: 536.23, CUDA: 12.2 (up to: 12.2), Compute: 7.5, cuDNN: 8.5
System RAM: 32 GiB
Platform: Windows
BuildConfig: Release
Execution Env: Native
Runtime Env: Production
.NET framework: .NET 7.0.5
Default Python:
Video adapter info:
Intel(R) HD Graphics 4600:
Driver Version 20.19.15.4624
Video Processor Intel(R) HD Graphics Family
Microsoft Remote Display Adapter:
Driver Version 10.0.19041.3636
Video Processor
NVIDIA GeForce GTX 1650:
Driver Version 31.0.15.3623
Video Processor NVIDIA GeForce GTX 1650
System GPU info:
GPU 3D Usage 11%
GPU RAM Usage 3.3 GiB
Global Environment variables:
CPAI_APPROOTPATH = <root>
CPAI_PORT = 32168
|
|
|
|
|
Since updating to 2.5.4 I'm getting lots of false positive. In Blue Iris I have confidence adjusted from what used to be 60% all the way to 75% and it's still triggering. How is that 76% a person?
modified 4-Mar-24 16:30pm.
|
|
|
|
|
I never go under 80% on my cameras and i'm on huge model. False positives are very rare.
|
|
|
|
|
I had the same issue too - I went back to 2.5.1. I have since switched to 2.5.6 and I updated the AI settings in blue iris which has kind of worked... but something has definitely changed since 2.5.1!
|
|
|
|
|
Thanks very much for your report. Could you please share your Blue Iris main AI settings and Artificial Intelligence settings?
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
Which object detection module are you using, and what model size do you have selected?
cheers
Chris Maunder
|
|
|
|
|
What module and what size model are you using?
cheers
Chris Maunder
|
|
|
|
|
I have 2 Blueiris installations with CodeProject running on each Blueiris server both servers are now on Blueiris 5.8.7.9. With CodeProject 5.2.1 things worked mostly fine, but when I upgraded to 5.2.4 I started getting the error below and AI_Timeout 500 errors in Blueiris. I was hoping upgrading to 5.2.5 would fix it, but as well know now that version had issues. so I went to 5.2.6 but I am still having the same issue.
Object Detection (YOLOv5 6.2): Unable to create YOLO detector for model yolov5m
14:46:42:Object Detection (YOLOv5 6.2): [RuntimeError] : Unable to load model at C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-6.2\assets\yolov5m.pt (CUDA error: CUDA-capable device(s) is/are busy or unavailable
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.)
modified 12-Mar-24 16:09pm.
|
|
|
|