[Detector Support]: Creation of Openvino models with integrated intel GPU fails on latest Linux kernel 6.8.2 #10785
-
Describe the problem you are havingAfter updating my system (Arch), the kernel got updated to 6.8.2, and frigate is not able anymore to compile the openvino detector model for my integrated intel gpu, failing with the message logs shown below. My specs: CPU intel i3 6100T with integrated GPU HD Graphics 530. This issue in intel compute-runtime might be related: intel/compute-runtime#710 Version0.13.2-6476f8a Frigate config filemqtt:
enabled: True
host: mosquitto
detectors:
ov:
type: openvino
device: GPU
model:
path: /openvino-model/ssdlite_mobilenet_v2.xml
model:
width: 300
height: 300
input_tensor: nhwc
input_pixel_format: bgr
labelmap_path: /openvino-model/coco_91cl_bkgr.txt
go2rtc:
streams:
cam_salotto: # this needs to be named exactly as the camera, if you want this stream to be the live stream in frigate integration
- rtsp:https://frigate:[email protected]:554/stream1
- "ffmpeg:cam_salotto#audio=aac"
cam_salotto_sub: #used only to detect movement and audio
- rtsp:https://frigate:[email protected]:554/stream2
- "ffmpeg:cam_salotto_sub#audio=aac"
cam_terrazzo: # this needs to be named exactly as the camera, if you want this stream to be the live stream in frigate integration
- rtsp:https://frigate:[email protected]:554/stream1
- "ffmpeg:cam_terrazzo#audio=aac"
cam_terrazzo_sub: #used only to detect movement and audio
- rtsp:https://frigate:[email protected]:554/stream2
- "ffmpeg:cam_terrazzo_sub#audio=aac"
ffmpeg:
hwaccel_args: preset-vaapi
record:
enabled: True
retain:
days: 0
mode: all
events:
retain:
default: 30
mode: motion
# Include all cameras by default in Birdseye view
birdseye:
enabled: True
mode: continuous
cameras:
cam_salotto:
ffmpeg:
output_args:
record: preset-record-generic-audio-copy
inputs:
- path: rtsp:https://127.0.0.1:8554/cam_salotto_sub
input_args: preset-rtsp-restream
roles:
- detect
- audio
- path: rtsp:https://127.0.0.1:8554/cam_salotto
input_args: preset-rtsp-restream
roles:
- record
onvif: # this enables camera features control like object movement tracking
host: 192.168.1.22
port: 2020
user: frigate
password: xxx
audio:
enabled: True
min_volume: 5
record:
enabled: True
detect:
enabled: True
objects:
track:
- person
filters:
person:
threshold: 0.75
live:
stream_name: cam_salotto
cam_terrazzo:
ffmpeg:
output_args:
record: preset-record-generic-audio-copy
inputs:
- path: rtsp:https://127.0.0.1:8554/cam_terrazzo_sub
input_args: preset-rtsp-restream
roles:
- detect
- audio
- path: rtsp:https://127.0.0.1:8554/cam_terrazzo
input_args: preset-rtsp-restream
roles:
- record
onvif: # this enables camera features control like object movement tracking
host: 192.168.1.25
port: 2020
user: frigate
password: xxx
audio:
enabled: True
min_volume: 5
record:
enabled: True
detect:
enabled: True
objects:
track:
- person
filters:
person:
threshold: 0.75
mask:
- 0,69,348,0,0,0
- 597,0,588,29,532,0
live:
stream_name: cam_terrazzodocker-compose file or Docker CLI commandfrigate:
container_name: frigate
cap_add:
- PERFMON # to see gpu stats
restart: unless-stopped
image: ghcr.io/blakeblackshear/frigate:stable
shm_size: ${FRIGATE_SHM_SIZE} # update for your cameras based on calculation above
devices:
- /dev/bus/usb:/dev/bus/usb
- ${FRIGATE_DRI_CARD} # this is /dev/dri/card0
- ${FRIGATE_DRI_RENDER} # this is /dev/dri/renderD128
volumes:
- /etc/localtime:/etc/localtime:ro
- ${BASE_STORAGE_DIR}/${HASS_DATA_DIR}/${FRIGATE_DATA_DIR}/${FRIGATE_CONFIG_DIR}:/config
- ${FRIGATE_STORAGE_DEVICE}:/media/frigate
- type: tmpfs # Optional: reduces SSD/SD Card wear
target: /tmp/cache
tmpfs:
size: ${FRIGATE_TMPFS_SIZE}
ports:
- "5000:5000"
- "8554:8554" # RTSP feeds
- "8555:8555/tcp" # WebRTC over tcp
- "8555:8555/udp" # WebRTC over udp
networks:
- homeassistant-netRelevant log outputfrigate | 2024-04-02 08:57:44.141725869 Process detector:ov:
frigate | 2024-04-02 08:57:44.143750259 Traceback (most recent call last):
frigate | 2024-04-02 08:57:44.143842791 File "/usr/lib/python3.9/multiprocessing/process.py", line 315, in _bootstrap
frigate | 2024-04-02 08:57:44.143846325 self.run()
frigate | 2024-04-02 08:57:44.143848743 File "/usr/lib/python3.9/multiprocessing/process.py", line 108, in run
frigate | 2024-04-02 08:57:44.143850429 self._target(*self._args, **self._kwargs)
frigate | 2024-04-02 08:57:44.143856204 File "/opt/frigate/frigate/object_detection.py", line 102, in run_detector
frigate | 2024-04-02 08:57:44.143886819 object_detector = LocalObjectDetector(detector_config=detector_config)
frigate | 2024-04-02 08:57:44.143889641 File "/opt/frigate/frigate/object_detection.py", line 53, in __init__
frigate | 2024-04-02 08:57:44.143908891 self.detect_api = create_detector(detector_config)
frigate | 2024-04-02 08:57:44.143912045 File "/opt/frigate/frigate/detectors/__init__.py", line 18, in create_detector
frigate | 2024-04-02 08:57:44.143914599 return api(detector_config)
frigate | 2024-04-02 08:57:44.143968297 File "/opt/frigate/frigate/detectors/plugins/openvino.py", line 32, in __init__
frigate | 2024-04-02 08:57:44.143971237 self.interpreter = self.ov_core.compile_model(
frigate | 2024-04-02 08:57:44.143974192 File "/usr/local/lib/python3.9/dist-packages/openvino/runtime/ie_api.py", line 399, in compile_model
frigate | 2024-04-02 08:57:44.143976497 super().compile_model(model, device_name, {} if config is None else config),
frigate | 2024-04-02 08:57:44.144153790 RuntimeError: Failed to create plugin /usr/local/lib/python3.9/dist-packages/openvino/libs/libopenvino_intel_gpu_plugin.so for device GPU
frigate | 2024-04-02 08:57:44.144156352 Please, check your environment
frigate | 2024-04-02 08:57:44.144158442 Check 'error_code == 0' failed at src/plugins/intel_gpu/src/runtime/ocl/ocl_device_detector.cpp:194:
frigate | 2024-04-02 08:57:44.144160354 [GPU] No supported OCL devices found or unexpected error happened during devices query.
frigate | 2024-04-02 08:57:44.144162338 [GPU] Please check OpenVINO documentation for GPU drivers setup guide.
frigate | 2024-04-02 08:57:44.144163985 [GPU] clGetPlatformIDs error code: -1001Operating systemOther Linux Install methodDocker Compose Coral versionCPU (no coral) Any other information that may be helpfulNo response |
Beta Was this translation helpful? Give feedback.
Replies: 3 comments 35 replies
-
|
Any reason why this has been ignored? Especially considering that kernel 6.7 has been declared EOL, I think it is important for frigate to work as expected on 6.8 and greater. |
Beta Was this translation helpful? Give feedback.
-
|
None of the maintainers use openvino and building your own model has even more variables to it. If the built in model doesn't work then that's very concerning, building your own model is a lot more specific and any number of things could be the reason that it doesn't work You're asking a very specific and specialized question that few people can give an informed answer to Edit: looks like the title wasn't correct and it is the default model being used. |
Beta Was this translation helpful? Give feedback.
-
|
It looks like this issue is outside of Frigate intel/compute-runtime#710 (comment) |
Beta Was this translation helpful? Give feedback.
-
|
@NickM-27 As mentioned below by @alexeynl, it seems that updating Intel compute package might be required as well. It seems Jellyfin also updated (jellyfin/jellyfin-packaging#15) to address the issue. Not saying a kernel fix isn't also necessary, but if Intel compute is part of Frigate, I'd just like to +1 requesting it get updated. |
Beta Was this translation helpful? Give feedback.
-
|
I use image Docker images from documentation ghcr.io/blakeblackshear/frigate:stable. I have migrated Docker host to Ubuntu 24.04 with 6.8 kernel and faced with the same issue.
This is just workaround. For permanent fix Docker image mainteiner must build and push image with latest intel compute-runtime. |
Beta Was this translation helpful? Give feedback.
-
|
I don't think that supports openvino https://www.intel.com/content/www/us/en/products/sku/128984/intel-pentium-silver-j5005-processor-4m-cache-up-to-2-80-ghz/specifications.html |
Beta Was this translation helpful? Give feedback.
-
|
Yeah I think officially it is not on the supported HW list, but me and others have been using it just fine on older kernels. J4105 is also on a similar boat, but you'll find plenty of people here successfully getting J4105/4125 to work with OpenVINO GPU acceleration. Are there confirmed cases of the latest OpenVINO runtime/Frigate working on Gemini-lake chips (J41x5 - J5xx5)? I have been searching on here, but have not found confirmations. |
Beta Was this translation helpful? Give feedback.
-
|
Not sure, but we've updated to the latest stable Intel packages so I don't think there's anything more we can do to fix it |
Beta Was this translation helpful? Give feedback.
-
|
Yep I appreciate the reply! I agree, in case I wasn't clear earlier, I am saying that there is still an open issue over at the Intel repo. So this needs to be fixed either in the kernel or with an OpenVINO runtime update by Intel in the future. |
Beta Was this translation helpful? Give feedback.
-
|
I'm experiencing a similar issue on all versions above frigate:1234003. The error is as follows. I've checked all kernels from 6 to 6.11, and there are no changes. Hardware: i5-8259U/Iris Plus Graphics 655 |
Beta Was this translation helpful? Give feedback.
-
|
A simpler, temporary fix, as suggested in the intel-compute-runtime repo is to set the following env variables (in the case of frigate, I guess this should be enough in the docker configuration): Anyway, since the frigate image contains the intel-compute-runtime, I also believe it is frigate's responsibility to update it, to properly fix the bug. |
Beta Was this translation helpful? Give feedback.
-
|
If the workaround isn't working, are you sure it's the same issue? We've had quite a few users saying this is the issue they're seeing but it turned out to be unrelated. |
Beta Was this translation helpful? Give feedback.
-
|
not absolutely sure. I have a J4125 and I'm seeing this error when enabling openvino; decode hw acceleration works. |
Beta Was this translation helpful? Give feedback.
-
I have the same issue (clwaitforevents error -14), on hardware where it used to be working previously - however when it first started appearing I made multiple changes (new os underlying docker, newer frigate version) due to changin the whole system on the same hardware, so unclear if it is an issue with the undelyin os (openmediavault based on debian bookworm) or the frigate container, or a setting somewhere.... If you have the issue starting from a certain container or firgate version you may be best placed to open an issue on it, as there are less variables... |
Beta Was this translation helpful? Give feedback.
-
|
I'm pretty sure is related to a kernel update: intel/compute-runtime#679 |
Beta Was this translation helpful? Give feedback.
-
|
I was still having issues after trying this fix on a privileged LXC set up using the tteck script on Proxmox 8.2.7 Kernel 6.8.12-2-pve on a i5 8500T. Turned out the path in the default config:
needed to be:
Probably something I should have checked when moving over from my Synology setup and might be not be an issue for anyone else, but figured I'd post it here just in case it saves anyone else the time troubleshooting it. Inference speed now down to 10ms from the 60ms when it was stuck with only CPU. |
Beta Was this translation helpful? Give feedback.
I use image Docker images from documentation ghcr.io/blakeblackshear/frigate:stable. I have migrated Docker host to Ubuntu 24.04 with 6.8 kernel and faced with the same issue.
To get rid from this error I have installed latest compute-runtime deb packages inside Docker container according installation steps from https://github.com/intel/compute-runtime/releases.