|
Is there an install.log file in the C:\Program Files\CodeProject\AI\modules\ObjectDetectionYolo folder you can share?
cheers
Chris Maunder
|
|
|
|
|
Installing CodeProject.AI Analysis Module
========================================================================
CodeProject.AI Installer
========================================================================
CUDA Present...True
Allowing GPU Support: Yes
Allowing CUDA Support: Yes
General CodeProject.AI setup
Creating Directories...Done
Installing module ObjectDetectionYolo
Installing python37 in C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37
Checking for python37 download...Present
Creating Virtual Environment...Python 3.7 Already present
Enabling our Virtual Environment...Done
Confirming we have Python 3.7...present
Ensuring Python package manager (pip) is installed...Done
Ensuring Python package manager (pip) is up to date...Done
Choosing Python packages from requirements.windows.cuda.txt
ERROR: Exception:
Traceback (most recent call last):
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_internal\cli\base_command.py", line 169, in exc_logging_wrapper
status = run_func(*args)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_internal\cli\req_command.py", line 248, in wrapper
return func(self, options, args)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_internal\commands\install.py", line 378, in run
reqs, check_supported_wheels=not options.target_dir
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_internal\resolution\resolvelib\resolver.py", line 93, in resolve
collected.requirements, max_rounds=limit_how_complex_resolution_can_be
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_vendor\resolvelib\resolvers.py", line 546, in resolve
state = resolution.resolve(requirements, max_rounds=max_rounds)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_vendor\resolvelib\resolvers.py", line 397, in resolve
self._add_to_criteria(self.state.criteria, r, parent=None)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_vendor\resolvelib\resolvers.py", line 173, in _add_to_criteria
if not criterion.candidates:
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_vendor\resolvelib\structs.py", line 156, in __bool__
return bool(self._sequence)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_internal\resolution\resolvelib\found_candidates.py", line 155, in __bool__
return any(self)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_internal\resolution\resolvelib\found_candidates.py", line 143, in <genexpr>
return (c for c in iterator if id(c) not in self._incompatible_ids)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_internal\resolution\resolvelib\found_candidates.py", line 47, in _iter_built
candidate = func()
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_internal\resolution\resolvelib\factory.py", line 211, in _make_candidate_from_link
version=version,
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_internal\resolution\resolvelib\candidates.py", line 299, in __init__
version=version,
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_internal\resolution\resolvelib\candidates.py", line 156, in __init__
self.dist = self._prepare()
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_internal\resolution\resolvelib\candidates.py", line 225, in _prepare
dist = self._prepare_distribution()
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_internal\resolution\resolvelib\candidates.py", line 304, in _prepare_distribution
return preparer.prepare_linked_requirement(self._ireq, parallel_builds=True)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_internal\operations\prepare.py", line 516, in prepare_linked_requirement
return self._prepare_linked_requirement(req, parallel_builds)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_internal\operations\prepare.py", line 593, in _prepare_linked_requirement
hashes,
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_internal\operations\prepare.py", line 170, in unpack_url
hashes=hashes,
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_internal\operations\prepare.py", line 107, in get_http_url
from_path, content_type = download(link, temp_dir.path)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_internal\network\download.py", line 134, in __call__
resp = _http_get_download(self._session, link)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_internal\network\download.py", line 117, in _http_get_download
resp = session.get(target_url, headers=HEADERS, stream=True)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_vendor\requests\sessions.py", line 600, in get
return self.request("GET", url, **kwargs)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_internal\network\session.py", line 517, in request
return super().request(method, url, *args, **kwargs)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_vendor\requests\sessions.py", line 587, in request
resp = self.send(prep, **send_kwargs)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_vendor\requests\sessions.py", line 701, in send
r = adapter.send(request, **kwargs)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_vendor\cachecontrol\adapter.py", line 57, in send
resp = super(CacheControlAdapter, self).send(request, **kw)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_vendor\requests\adapters.py", line 584, in send
return self.build_response(request, resp)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_vendor\cachecontrol\adapter.py", line 84, in build_response
request, response
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_vendor\cachecontrol\controller.py", line 410, in update_cached_response
cached_response = self.serializer.loads(request, self.cache.get(cache_url))
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_vendor\cachecontrol\serialize.py", line 95, in loads
return getattr(self, "_loads_v{}".format(ver))(request, data, body_file)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_vendor\cachecontrol\serialize.py", line 186, in _loads_v4
cached = msgpack.loads(data, raw=False)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_vendor\msgpack\fallback.py", line 125, in unpackb
ret = unpacker._unpack()
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_vendor\msgpack\fallback.py", line 590, in _unpack
ret[key] = self._unpack(EX_CONSTRUCT)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_vendor\msgpack\fallback.py", line 590, in _unpack
ret[key] = self._unpack(EX_CONSTRUCT)
File "C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\lib\site-packages\pip\_vendor\msgpack\fallback.py", line 603, in _unpack
return bytes(obj)
MemoryError
Installing Packages into Virtual Environment...Success
Ensuring Python package manager (pip) is installed...Done
Ensuring Python package manager (pip) is up to date...Done
Choosing Python packages from requirements.txt
Installing Packages into Virtual Environment...Success
Downloading Standard YOLO models...Expanding...Done.
Downloading Custom YOLO models...Expanding...Done.
Module setup complete
Installer exited with code 0
|
|
|
|
|
Do you want it in another format?
|
|
|
|
|
Did you want me to send this somehow? I posted it on this thread earlier but maybe you wanted it a different way.
|
|
|
|
|
I am using the .net module now- it is kind of working but it is running my GPU at 100% all the time. I sure would like to get back to the 6.2 module if possible. Thanks!
|
|
|
|
|
i've tried to setup nvr agent with codeproject.al. i'm wondering if there is a log file that will tell me if a request was made to codeproject to detect an object, at a certain time and what was codeproject response. object = true or maybe object = false. sorry, really really newbie.
|
|
|
|
|
You can open the Dashboard and select the trace Logging level.
|
|
|
|
|
|
Hi all. I’m just wondering if this is a known bug or if it is something to look into.
This occurred whilst running 2.14 and now on 2.18 via docker with both the rpi64 and also the arm docker images. I have the usb coral stick installed on an rpi4/ odroid M1. I’m using Blue Iris on bare metal windows 10 machine. After several hours of use with <100ms detection times the detection times rise to >1000ms and no detections reported on Blue Iris. The problem is fixed by having to restart either the docker container or simply by restarting the TF-Lite module from the codeproject.ai server web page. After this detection times return to <100ms (I’m using the small model size and the sub stream for analysis) .
If it’s a known issue I’ll patiently wait but if you think it’s something wrong with my setup let me know!
|
|
|
|
|
I've not experienced this, but I'll add this one to our bug list and see if we can replicate / fix the issue.
Off the bat it sounds like a resource (memory?) depletion issue.
cheers
Chris Maunder
|
|
|
|
|
I am having exactly the same problem. It occurs after about 12 hours of use, detection times will rise to 1000ms from approximately 100ms. I have version 2.19 with docker on a raspberry pi 3. If I restart TF-lite using the "..." on the web interface, that solves the problem for another 12 hours or so before detection times rise again to 1000ms.
|
|
|
|
|
I've played around with it a little more leaving the logs at trace and this is what I've found out.
Memory remains pretty constant from the time it is <100ms through the time I notice it increase to >1000ms. So that doesn't suggest it's a memory issue. Specifically, when I view the memory usage through Portainer, the container for Code Proejct AI shows a constant usage of 700 MB
HOWEVER, I notice in the trace logs lots of: "The interpreter is in use. Please try again later."
Does any of this information help? Is there anything else that might help in resolving this issue?
Thank you
|
|
|
|
|
|
Sorry for this question, but can someone remind me where to see the detection time?
|
|
|
|
|
You can see them on the Dashboard Log. Also when using Explorer.
|
|
|
|
|
Thank you. I seem to also recall seeing the same info in Blue Iris.
|
|
|
|
|
Are you seeing the memory use increase over time? How many detections per second, minute, or hour are you processing?
cheers
Chris Maunder
|
|
|
|
|
I will have to check regarding the memory issues. I think what may be happening is the for some reason CP.AI stops using the TPU or it becomes unavailable and then TFLite uses the CPU instead. I have just checked on this this morning as it seemed to have been quite stable since I wrote this comment about 2.18. However, as I was getting reliable detections in blue iris however I have only checked this morning and lo and behold the TPU is not being detected by TF-lite. (Watchtower has updated me to 2.19-beta) I had not noticed the increased detection time as my CPU seems to be handling TF Lite on the Odroid M1 at 240ms response times on average.
I have restarted the Docker container and the Host device and the Coral TPU is now no-longer detected by 2.19-beta container. I have had to delete the TF-lite module and reinstall which seems to have worked.
Here is a snapshot of the log over 5 minutes I hope this helps estimate the number of detections/hr.
09:26:31:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...a742a5) took 59ms
09:26:45:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...3ba9b6) took 43ms
09:26:45:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...b7ef09) took 50ms
09:26:45:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...0076b0) took 45ms
09:26:45:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...d7d5f5) took 49ms
09:26:45:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...c89d7f) took 46ms
09:28:31:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...e56b12) took 59ms
09:28:45:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...a7015f) took 45ms
09:29:15:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...94ad42) took 49ms
09:29:32:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...cb1206) took 50ms
09:30:01:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...b3b5cf) took 171ms
09:30:31:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...ba2ca2) took 55ms
09:30:31:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...2a6a94) took 43ms
|
|
|
|
|
So I can confirm this still happens with my RPi 4 4GB version with 2.19Beta. The Coral TPU is still showing as connected in the CPAI webserver.
This is an example of the log output.
17:15:40:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...0c1c9c) took 1021ms
17:15:40:Response received (...0c1c9c): The interpreter is in use. Please try again later
17:16:18:Request 'detect' dequeued from 'objectdetection_queue' (...7d4f6c)
17:16:18:Client request 'detect' in queue 'objectdetection_queue' (...7d4f6c)
Memory Allocation:
total used free shared buff/cache available
Mem: 3794 649 153 24 2991 3069
Swap: 99 0 99
Restarting the TF-Lite module from within the CPAI web page again fixes this error.
|
|
|
|
|
Just wanted to confirm I'm also experiencing the TF-Lite detection time spike issue as previously discussed.
I'm running Version 2.1.9 on a Raspberry Pi 4 via Docker, and the same issue was present on Version 2.1.4 as well.
The detection time starts at 150-300ms but then increases to over 1000ms after a few hours and restarting the model or container only temporarily mitigate the problem.
In light of memory usage being highlighted as a possible culprit (as per Chris's suggestion), I switched to a 2 GB Pi variant. However, the problem persists, and memory usage seems unaffected, maintaining around 600MiB used, 600MiB free, and 700MiB cached. Interestingly, I'm not seeing a significant increase in CPU usage when detection time exceeds 1000ms, as one might expect if the CPU is compensating for the TPU.
Just adding my experience to the data pool here. Any additional insights would be much appreciated.
If I could provide any other information or check something else, please feel free to ask.
|
|
|
|
|
Any resolution to this? I am seeing the same; Have to restart everyday.
Server version: 2.1.8-Beta
Operating System: Linux (Linux 6.1.21-v8+ #1642 SMP PREEMPT Mon Apr 3 17:24:16 BST 2023)
CPUs: 1 CPU. (Arm64)
System RAM: 4 GiB
Target: Linux-Arm64
BuildConfig: Release
Execution Env: Docker
Runtime Env: Production
.NET framework: .NET 7.0.5
System GPU info:
GPU 3D Usage 0%
GPU RAM Usage 0
Video adapter info:
Global Environment variables:
CPAI_APPROOTPATH = /app
CPAI_PORT = 32168
Will add log next time incident repeats.
|
|
|
|
|
Here is log in trace that shows 1000ms restart < 100ms
15:35:23:ObjectDetection (TF-Lite): Retrieved objectdetection_queue command
15:35:25:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...8e1d8e) took 1044ms
15:35:25:Response received (...8e1d8e): The interpreter is in use. Please try again later
15:35:25:Client request 'detect' in queue 'objectdetection_queue' (...6b2822)
15:35:25:Request 'detect' dequeued from 'objectdetection_queue' (...6b2822)
15:35:25:ObjectDetection (TF-Lite): Retrieved objectdetection_queue command
15:35:26:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...6b2822) took 1055ms
15:35:26:Response received (...6b2822): The interpreter is in use. Please try again later
15:35:27:Client request 'detect' in queue 'objectdetection_queue' (...17074b)
15:35:27:Request 'detect' dequeued from 'objectdetection_queue' (...17074b)
15:35:27:ObjectDetection (TF-Lite): Retrieved objectdetection_queue command
15:35:28:Client request 'Quit' in queue 'objectdetection_queue' (...f92f46)
15:35:28:Request 'Quit' dequeued from 'objectdetection_queue' (...f92f46)
15:35:28:Sending shutdown request to python3.9/ObjectDetectionTFLite
15:35:28:ObjectDetection (TF-Lite): Retrieved objectdetection_queue command
15:35:28:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...17074b) took 1070ms
15:35:28:Response received (...17074b): The interpreter is in use. Please try again later
15:35:30:Client request 'detect' in queue 'objectdetection_queue' (...42d81d)
15:35:30:Request 'detect' dequeued from 'objectdetection_queue' (...42d81d)
15:35:31:Client request 'detect' in queue 'objectdetection_queue' (...380d5d)
15:35:31:Client request 'detect' in queue 'objectdetection_queue' (...a50b13)
15:35:35:Client request 'detect' in queue 'objectdetection_queue' (...8350f0)
15:35:36:Client request 'detect' in queue 'objectdetection_queue' (...bb11d1)
15:35:36:Client request 'detect' in queue 'objectdetection_queue' (...eb4c78)
15:35:37:Client request 'detect' in queue 'objectdetection_queue' (...793b24)
15:35:41:Client request 'detect' in queue 'objectdetection_queue' (...34bc7f)
15:35:42:Client request 'detect' in queue 'objectdetection_queue' (...c33106)
15:35:46:Client request 'detect' in queue 'objectdetection_queue' (...4f1564)
15:35:47:Client request 'detect' in queue 'objectdetection_queue' (...8118f7)
15:35:51:Client request 'detect' in queue 'objectdetection_queue' (...8c5d82)
15:35:51:Client request 'detect' in queue 'objectdetection_queue' (...1f9738)
15:35:52:Client request 'detect' in queue 'objectdetection_queue' (...b836cd)
15:35:58:Client request 'detect' in queue 'objectdetection_queue' (...9cb8ab)
15:36:01:Forcing shutdown of python3.9/ObjectDetectionTFLite
15:36:01:Module ObjectDetectionTFLite has shutdown
15:36:01:GetCommandByRuntime: Runtime=python39, Location=Shared
15:36:01:Command: python3.9
15:36:01:Starting python3.9 "/app...nTFLite/objectdetection_tflite_adapter.py"
15:36:01:
15:36:01:Attempting to start ObjectDetectionTFLite with python3.9 "/app/preinstalled-modules/ObjectDetectionTFLite/objectdetection_tflite_adapter.py"
15:36:01:
15:36:01:Module 'ObjectDetection (TF-Lite)' (ID: ObjectDetectionTFLite)
15:36:01:Module Path: /app/preinstalled-modules/ObjectDetectionTFLite
15:36:01:AutoStart: True
15:36:01:Queue: objectdetection_queue
15:36:01:Platforms: windows,linux,linux-arm64,macos,macos-arm64
15:36:01:GPU: Support enabled
15:36:01:Parallelism: 0
15:36:01:Accelerator:
15:36:01:Half Precis.: enable
15:36:01:Runtime: python39
15:36:01:Runtime Loc: Shared
15:36:01:FilePath: objectdetection_tflite_adapter.py
15:36:01:Pre installed: True
15:36:01:Start pause: 1 sec
15:36:01:LogVerbosity:
15:36:01:Valid: True
15:36:01:Environment Variables
15:36:01:MODELS_DIR = %CURRENT_MODULE_PATH%/assets
15:36:01:MODEL_SIZE = Tiny
15:36:01:
15:36:01:Started ObjectDetection (TF-Lite) module
15:36:02:Running init for ObjectDetection (TF-Lite)
15:36:03:Client request 'detect' in queue 'objectdetection_queue' (...f0621d)
15:36:07:objectdetection_tflite_adapter.py: NUM_THREADS not found. Setting to default 1
15:36:07:objectdetection_tflite_adapter.py: MIN_CONFIDENCE not found. Setting to default 0.5
15:36:07:objectdetection_tflite_adapter.py: MODULE_PATH: /app/preinstalled-modules/ObjectDetectionTFLite
15:36:07:objectdetection_tflite_adapter.py: MODELS_DIR: /app/preinstalled-modules/ObjectDetectionTFLite/assets
15:36:07:objectdetection_tflite_adapter.py: MODEL_SIZE: small
15:36:07:objectdetection_tflite_adapter.py: CPU_MODEL_NAME: tf2_ssd_mobilenet_v2_coco17_ptq.tflite
15:36:07:objectdetection_tflite_adapter.py: TPU_MODEL_NAME: tf2_ssd_mobilenet_v2_coco17_ptq_edgetpu.tflite
15:36:07:objectdetection_tflite_adapter.py: Edge TPU detected
15:36:07:objectdetection_tflite_adapter.py: Timeout connecting to the server
15:36:07:objectdetection_tflite_adapter.py: ObjectDetection (TF-Lite) started.ObjectDetection (TF-Lite): ObjectDetection (TF-Lite) started.
15:36:07:objectdetection_tflite_adapter.py: Input details: {'name': 'serving_default_input:0', 'index': 0, 'shape': array([ 1, 300, 300, 3], dtype=int32), 'shape_signature': array([ 1, 300, 300, 3], dtype=int32), 'dtype': , 'quantization': (0.007843137718737125, 127), 'quantization_parameters': {'scales': array([0.00784314], dtype=float32), 'zero_points': array([127], dtype=int32), 'quantized_dimension': 0}, 'sparsity_parameters': {}}
15:36:07:objectdetection_tflite_adapter.py: Output details: {'name': 'StatefulPartitionedCall:3;StatefulPartitionedCall:2;StatefulPartitionedCall:1;StatefulPartitionedCall:02', 'index': 8, 'shape': array([ 1, 20], dtype=int32), 'shape_signature': array([ 1, 20], dtype=int32), 'dtype': , 'quantization': (0.0, 0), 'quantization_parameters': {'scales': array([], dtype=float32), 'zero_points': array([], dtype=int32), 'quantized_dimension': 0}, 'sparsity_parameters': {}}
15:36:07:ObjectDetection (TF-Lite): ObjectDetection (TF-Lite) started.
15:36:07:Request 'detect' dequeued from 'objectdetection_queue' (...380d5d)
15:36:07:Request 'detect' dequeued from 'objectdetection_queue' (...a50b13)
15:36:07:Request 'detect' dequeued from 'objectdetection_queue' (...8350f0)
15:36:07:Request 'detect' dequeued from 'objectdetection_queue' (...bb11d1)
15:36:07:Request 'detect' dequeued from 'objectdetection_queue' (...eb4c78)
15:36:07:Request 'detect' dequeued from 'objectdetection_queue' (...793b24)
15:36:07:Request 'detect' dequeued from 'objectdetection_queue' (...34bc7f)
15:36:07:Request 'detect' dequeued from 'objectdetection_queue' (...c33106)
15:36:07:Client request 'detect' in queue 'objectdetection_queue' (...f98921)
15:36:07:Request 'detect' dequeued from 'objectdetection_queue' (...4f1564)
15:36:07:ObjectDetection (TF-Lite): Retrieved objectdetection_queue command
15:36:07:Request 'detect' dequeued from 'objectdetection_queue' (...8118f7)
15:36:07:ObjectDetection (TF-Lite): Retrieved objectdetection_queue command
15:36:07:ObjectDetection (TF-Lite): Retrieved objectdetection_queue command
15:36:07:ObjectDetection (TF-Lite): Retrieved objectdetection_queue command
15:36:08:Request 'detect' dequeued from 'objectdetection_queue' (...8c5d82)
15:36:08:Response received (...c33106): No objects found
15:36:08:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...c33106) took 230ms
15:36:08:ObjectDetection (TF-Lite): Retrieved objectdetection_queue command
15:36:08:Request 'detect' dequeued from 'objectdetection_queue' (...1f9738)
15:36:08:Response received (...34bc7f): Found person
15:36:08:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...34bc7f) took 288ms
15:36:08:ObjectDetection (TF-Lite): Retrieved objectdetection_queue command
15:36:08:Request 'detect' dequeued from 'objectdetection_queue' (...b836cd)
15:36:08:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...4f1564) took 138ms
15:36:08:Response received (...4f1564): Found person
15:36:08:ObjectDetection (TF-Lite): Retrieved objectdetection_queue command
15:36:08:Request 'detect' dequeued from 'objectdetection_queue' (...9cb8ab)
15:36:08:Response received (...8118f7): Found person
15:36:08:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...8118f7) took 142ms
15:36:08:ObjectDetection (TF-Lite): Retrieved objectdetection_queue command
15:36:08:Request 'detect' dequeued from 'objectdetection_queue' (...f0621d)
15:36:08:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...8c5d82) took 128ms
15:36:08:Response received (...8c5d82): Found person
|
|
|
|
|
Updated to 2.1.9-Beta and issue is still persistent about every 12 hours have to re-start TF-Lite module; reverting to deepstack - will try again in a few versions.
|
|
|
|
|
Having same issue. This has existed for me since initial release on pi4 (2.1.3?). Interestingly, before using with CodeProject on pi4 I tried with Scrypted on Windows and had same issue with it quitting working after a number of hours and requiring reloading the TPU. May be a bigger issue somehow.
00:50:44:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...c9a1f7) took 68ms
00:50:44:Response received (...c9a1f7): No objects found
00:50:46:Client request 'detect' in queue 'objectdetection_queue' (...4bdf35)
00:50:46:Request 'detect' dequeued from 'objectdetection_queue' (...4bdf35)
00:50:46:ObjectDetection (TF-Lite): Retrieved objectdetection_queue command
00:50:46:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...4bdf35) took 85ms
00:50:46:Response received (...4bdf35): No objects found
00:52:04:Request 'detect' dequeued from 'objectdetection_queue' (...335f69)
00:52:04:Client request 'detect' in queue 'objectdetection_queue' (...335f69)
00:52:04:ObjectDetection (TF-Lite): Retrieved objectdetection_queue command
00:52:41:Request 'detect' dequeued from 'objectdetection_queue' (...7c7201)
00:52:41:Client request 'detect' in queue 'objectdetection_queue' (...7c7201)
00:52:41:ObjectDetection (TF-Lite): Retrieved objectdetection_queue command
00:52:42:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...7c7201) took 1073ms
00:52:42:Response received (...7c7201): The interpreter is in use. Please try again later
00:52:44:Request 'detect' dequeued from 'objectdetection_queue' (...74bf42)
00:52:44:Client request 'detect' in queue 'objectdetection_queue' (...74bf42)
00:52:44:ObjectDetection (TF-Lite): Retrieved objectdetection_queue command
00:52:45:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...74bf42) took 1031ms
00:52:45:Response received (...74bf42): The interpreter is in use. Please try again later
00:52:46:Client request 'detect' in queue 'objectdetection_queue' (...eccb06)
00:52:46:Request 'detect' dequeued from 'objectdetection_queue' (...eccb06)
00:52:46:ObjectDetection (TF-Lite): Retrieved objectdetection_queue command
00:52:47:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...eccb06) took 1086ms
00:52:47:Response received (...eccb06): The interpreter is in use. Please try again later
00:54:04:Client request 'detect' in queue 'objectdetection_queue' (...97f7aa)
00:54:04:Request 'detect' dequeued from 'objectdetection_queue' (...97f7aa)
00:54:04:ObjectDetection (TF-Lite): Retrieved objectdetection_queue command
00:54:05:ObjectDetection (TF-Lite): Queue request for ObjectDetection (TF-Lite) command 'detect' (...97f7aa) took 1051ms
00:54:05:Response received (...97f7aa): The interpreter is in use. Please try again later
00:54:41:Client request 'detect' in queue 'objectdetection_queue' (...c9eda9)
00:54:41:Request 'detect' dequeued from 'objectdetection_queue' (...c9eda9)
|
|
|
|
|
Lots of this issue reported. Chris tried some fixes in later versions, but they didn't work. Here's a dupe issue: CDAI 2.1.9 Coral Dies after a while Pin[^]
Note that when the detection time goes up to that classic 1000ms, that means the Coral interpreter (whatever that is) is locked up and is not actually doing analysis anymore.
|
|
|
|
|