SohailS Posted February 14, 2023 Share Posted February 14, 2023 19 minutes ago, yayitazale said: So please read the docs first: https://docs.frigate.video/configuration/hardware_acceleration ok so added the below line ffmpeg: hwaccel_args: -c:v h264_cuvid however its still not using it this is from the container but my dashboard on Unraid reports some activity but my CPU usage has not dropped. Quote Link to comment
yayitazale Posted February 17, 2023 Author Share Posted February 17, 2023 On 2/14/2023 at 1:43 PM, SohailS said: ok so added the below line ffmpeg: hwaccel_args: -c:v h264_cuvid however its still not using it this is from the container but my dashboard on Unraid reports some activity but my CPU usage has not dropped. Are you launching the nvidia-smi inside or outside the container? Launch it on unraid's console. Quote Link to comment
chrispcrust Posted February 20, 2023 Share Posted February 20, 2023 (edited) Hey there, I'm using the beta8 Frigate docker, MQTT in docker, run HA in a VM also on unraid, and using Nvidia GPU for hardware acceleration. All is working fine, couple of minor issues, but really liking this and dropped Shinobi, finally (!) I'm curious if there are any additional steps or instructions to enable object detection using Nvidia GPU as opposed to CPU? I don't have Coral but my vintage Xeons seem to be doing fine, would be great to offload to GPU though. I see this in the docker: - If you want to use the NVidia TensorRT Detector, you have to add the tag suffix "-tensorrt" to the repository link, and create the models using the "tensorrt-models" app from the CA app. So would the steps be more or less as follows? 1) Get the tensorrt-models and follow the instructions as listed there 2) Change repository on Frigate from ghcr.io/blakeblackshear/frigate:0.12.0-beta8 to ghcr.io/blakeblackshear/frigate:0.12.0-beta8-tensorrt (note - is it beta8 or beta2?) Is that it? Do I need to add anything else to my Frigate config? In this link it states "Note: There is no support for Nvidia GPUs to perform object detection with tensorflow. It can be used for ffmpeg decoding, but not object detection." Thanks very much! Edited February 20, 2023 by chrispcrust Quote Link to comment
yayitazale Posted February 20, 2023 Author Share Posted February 20, 2023 5 hours ago, chrispcrust said: Hey there, I'm using the beta8 Frigate docker, MQTT in docker, run HA in a VM also on unraid, and using Nvidia GPU for hardware acceleration. All is working fine, couple of minor issues, but really liking this and dropped Shinobi, finally (!) I'm curious if there are any additional steps or instructions to enable object detection using Nvidia GPU as opposed to CPU? I don't have Coral but my vintage Xeons seem to be doing fine, would be great to offload to GPU though. I see this in the docker: - If you want to use the NVidia TensorRT Detector, you have to add the tag suffix "-tensorrt" to the repository link, and create the models using the "tensorrt-models" app from the CA app. So would the steps be more or less as follows? 1) Get the tensorrt-models and follow the instructions as listed there 2) Change repository on Frigate from ghcr.io/blakeblackshear/frigate:0.12.0-beta8 to ghcr.io/blakeblackshear/frigate:0.12.0-beta8-tensorrt (note - is it beta8 or beta2?) Is that it? Do I need to add anything else to my Frigate config? In this link it states "Note: There is no support for Nvidia GPUs to perform object detection with tensorflow. It can be used for ffmpeg decoding, but not object detection." Thanks very much! Steps are almost correct but you also need to add the extra parameter "--runtime=nvidia", then fill the Nvidia entries of the template. You can also delete the intel/amd gpu entries if you are also going to use the nvidia card itself for hardware accel (but you can split the load and let the nvidia card only do the detections). Anyway, I just pushed a new version for the template to avoid mistakes on the step 2 of your list so for now on there will be a brach selector to make a easier deployment for regular/nvidia branches. The docs are you refering are only for frigate 11. Frigate 12 betas docs are here: https://deploy-preview-4055--frigate-docs.netlify.app/ (this is also refered on the description of the template). 1 Quote Link to comment
SohailS Posted February 20, 2023 Share Posted February 20, 2023 On 2/17/2023 at 3:12 PM, yayitazale said: Are you launching the nvidia-smi inside or outside the container? Launch it on unraid's console. you are right i was looking in the container. looking at unraid it is using it I think i was expecting it to stop using CPU but for some reason its still using CPU too. Quote Link to comment
chrispcrust Posted February 21, 2023 Share Posted February 21, 2023 19 hours ago, yayitazale said: Steps are almost correct but you also need to add the extra parameter "--runtime=nvidia", then fill the Nvidia entries of the template. You can also delete the intel/amd gpu entries if you are also going to use the nvidia card itself for hardware accel (but you can split the load and let the nvidia card only do the detections). Anyway, I just pushed a new version for the template to avoid mistakes on the step 2 of your list so for now on there will be a brach selector to make a easier deployment for regular/nvidia branches. The docs are you refering are only for frigate 11. Frigate 12 betas docs are here: https://deploy-preview-4055--frigate-docs.netlify.app/ (this is also refered on the description of the template). Thank you so much! I did get it set up on my one (test) camera, only going to be using it for 2 total, so shouldn't overload my 1060 3gb too bad Really great documentation! I can't say I know the first thing about object detection models, so I'm using default everything.. I'll report back with any feedback on performance. 1 Quote Link to comment
yayitazale Posted February 21, 2023 Author Share Posted February 21, 2023 (edited) 3 hours ago, chrispcrust said: Thank you so much! I did get it set up on my one (test) camera, only going to be using it for 2 total, so shouldn't overload my 1060 3gb too bad Really great documentation! I can't say I know the first thing about object detection models, so I'm using default everything.. I'll report back with any feedback on performance. Nice. I only maintain the unraid templates, if you want to give some cheers to the developers you can do it here: https://github.com/blakeblackshear/frigate/discussions/5453 Edited February 21, 2023 by yayitazale 1 Quote Link to comment
yayitazale Posted February 21, 2023 Author Share Posted February 21, 2023 14 hours ago, SohailS said: you are right i was looking in the container. looking at unraid it is using it I think i was expecting it to stop using CPU but for some reason its still using CPU too. There are still a lot of processes going on behind the scenes that cannot be carried out by the GPU. You can test the CPU % difference between using or not the Hard Accel. Obviously you will see a difference but where there really is a substantial difference is in detection. Quote Link to comment
SohailS Posted February 21, 2023 Share Posted February 21, 2023 9 hours ago, yayitazale said: There are still a lot of processes going on behind the scenes that cannot be carried out by the GPU. You can test the CPU % difference between using or not the Hard Accel. Obviously you will see a difference but where there really is a substantial difference is in detection. Thanks for the info suppose something is better then nothing I have a coral for my detection so i guess its the best it will get Quote Link to comment
yayitazale Posted February 21, 2023 Author Share Posted February 21, 2023 1 hour ago, SohailS said: Thanks for the info suppose something is better then nothing I have a coral for my detection so i guess its the best it will get I have a similar setup than yours (7 cameras, tpu and hard accel) and I have 20% of cpu usage more or less. Quote Link to comment
SohailS Posted February 22, 2023 Share Posted February 22, 2023 23 hours ago, yayitazale said: I have a similar setup than yours (7 cameras, tpu and hard accel) and I have 20% of cpu usage more or less. in that case mine is the same about 20% cpu makes me happy to know its all working correctly 1 Quote Link to comment
morethanenough Posted February 24, 2023 Share Posted February 24, 2023 Hi all, I seem to have a strange problem with the WebUI. I don't know when this started because I hadn't connected to it for a while, but the WebUI is not loading at all. The strange thing is that I have set Frigate to create RTMP feeds and these work perfectly fine. Also, recordings are being made as normal. The only thing that is not working is the WebUI. I have a Home Assistant instance on a different machine, and initially I thought there was some problem with that, but when I checked the WebUI on Unraid, I realised that's where the problem actually lies. I had installed the blakeblackshear frigate app quite a while ago, but I remember seeing somewhere that there were some breaking changes, so I removed it and installed the new version (for some reason the old one wasn't showing as installed in the Community Apps). Again, after setting everything up, everything works except the WebUI. The logs are below: Plus API Key is not formatted correctly. [2023-02-24 19:08:44] frigate.app INFO : Starting Frigate (0.11.1-2eada21) [2023-02-24 19:08:44] frigate.config WARNING : The 'retain_days' config option has been DEPRECATED and will be removed in a future version. Please use the 'days' setting under 'retain' [2023-02-24 19:08:44] frigate.config WARNING : The 'retain_days' config option has been DEPRECATED and will be removed in a future version. Please use the 'days' setting under 'retain' [2023-02-24 19:08:44] frigate.config WARNING : The 'retain_days' config option has been DEPRECATED and will be removed in a future version. Please use the 'days' setting under 'retain' [2023-02-24 19:08:44] frigate.config WARNING : The 'retain_days' config option has been DEPRECATED and will be removed in a future version. Please use the 'days' setting under 'retain' [2023-02-24 19:08:44] frigate.config WARNING : The 'retain_days' config option has been DEPRECATED and will be removed in a future version. Please use the 'days' setting under 'retain' Starting migrations [2023-02-24 19:08:44] peewee_migrate INFO : Starting migrations There is nothing to migrate [2023-02-24 19:08:44] peewee_migrate INFO : There is nothing to migrate [2023-02-24 19:08:44] detector.coral INFO : Starting detection process: 216 [2023-02-24 19:08:44] frigate.app INFO : Output process started: 218 [2023-02-24 19:08:44] frigate.app INFO : Camera processor started for FrontGarden: 226 [2023-02-24 19:08:44] frigate.edgetpu INFO : Attempting to load TPU as pci [2023-02-24 19:08:44] frigate.edgetpu INFO : TPU found [2023-02-24 19:08:44] ws4py INFO : Using epoll [2023-02-24 19:08:44] frigate.app INFO : Camera processor started for Driveway: 237 [2023-02-24 19:08:44] frigate.app INFO : Camera processor started for BackGarden: 238 [2023-02-24 19:08:44] frigate.app INFO : Camera processor started for Kitchen: 240 [2023-02-24 19:08:44] frigate.app INFO : Camera processor started for TVRoom: 242 [2023-02-24 19:08:44] frigate.app INFO : Capture process started for FrontGarden: 243 [2023-02-24 19:08:44] frigate.app INFO : Capture process started for Driveway: 246 [2023-02-24 19:08:44] frigate.app INFO : Capture process started for BackGarden: 250 [2023-02-24 19:08:44] frigate.app INFO : Capture process started for Kitchen: 253 [2023-02-24 19:08:44] frigate.app INFO : Capture process started for TVRoom: 257 [2023-02-24 19:08:44] ws4py INFO : Using epoll [2023-02-24 19:08:54] frigate.video ERROR : Driveway: Unable to read frames from ffmpeg process. [2023-02-24 19:08:54] frigate.video ERROR : Driveway: ffmpeg process is not running. exiting capture thread... [2023-02-24 19:08:54] frigate.video ERROR : Kitchen: Unable to read frames from ffmpeg process. [2023-02-24 19:08:54] frigate.video ERROR : Kitchen: ffmpeg process is not running. exiting capture thread... [2023-02-24 19:08:54] frigate.video ERROR : BackGarden: Unable to read frames from ffmpeg process. [2023-02-24 19:08:54] frigate.video ERROR : BackGarden: ffmpeg process is not running. exiting capture thread... [2023-02-24 19:08:54] frigate.video ERROR : TVRoom: Unable to read frames from ffmpeg process. [2023-02-24 19:08:54] frigate.video ERROR : TVRoom: ffmpeg process is not running. exiting capture thread... [2023-02-24 19:08:54] frigate.video ERROR : FrontGarden: Unable to read frames from ffmpeg process. [2023-02-24 19:08:54] frigate.video ERROR : FrontGarden: ffmpeg process is not running. exiting capture thread... Plus API Key is not formatted correctly. [2023-02-24 19:09:05] frigate.app INFO : Starting Frigate (0.11.1-2eada21) [2023-02-24 19:09:05] frigate.config WARNING : The 'retain_days' config option has been DEPRECATED and will be removed in a future version. Please use the 'days' setting under 'retain' [2023-02-24 19:09:05] frigate.config WARNING : The 'retain_days' config option has been DEPRECATED and will be removed in a future version. Please use the 'days' setting under 'retain' [2023-02-24 19:09:05] frigate.config WARNING : The 'retain_days' config option has been DEPRECATED and will be removed in a future version. Please use the 'days' setting under 'retain' [2023-02-24 19:09:05] frigate.config WARNING : The 'retain_days' config option has been DEPRECATED and will be removed in a future version. Please use the 'days' setting under 'retain' [2023-02-24 19:09:05] frigate.config WARNING : The 'retain_days' config option has been DEPRECATED and will be removed in a future version. Please use the 'days' setting under 'retain' Starting migrations [2023-02-24 19:09:05] peewee_migrate INFO : Starting migrations There is nothing to migrate [2023-02-24 19:09:05] peewee_migrate INFO : There is nothing to migrate [2023-02-24 19:09:05] detector.coral INFO : Starting detection process: 216 [2023-02-24 19:09:05] frigate.app INFO : Output process started: 218 [2023-02-24 19:09:05] ws4py INFO : Using epoll [2023-02-24 19:09:05] frigate.edgetpu INFO : Attempting to load TPU as pci [2023-02-24 19:09:05] frigate.edgetpu INFO : TPU found [2023-02-24 19:09:05] frigate.app INFO : Camera processor started for FrontGarden: 236 [2023-02-24 19:09:05] frigate.app INFO : Camera processor started for Driveway: 238 [2023-02-24 19:09:05] frigate.app INFO : Camera processor started for BackGarden: 239 [2023-02-24 19:09:05] frigate.app INFO : Camera processor started for Kitchen: 241 [2023-02-24 19:09:05] frigate.app INFO : Camera processor started for TVRoom: 242 [2023-02-24 19:09:05] frigate.app INFO : Capture process started for FrontGarden: 243 [2023-02-24 19:09:05] frigate.app INFO : Capture process started for Driveway: 247 [2023-02-24 19:09:05] frigate.app INFO : Capture process started for BackGarden: 251 [2023-02-24 19:09:05] frigate.app INFO : Capture process started for Kitchen: 258 [2023-02-24 19:09:05] frigate.app INFO : Capture process started for TVRoom: 262 [2023-02-24 19:09:05] ws4py INFO : Using epoll [cont-finish.d] executing container finish scripts... [cont-finish.d] done. [s6-finish] waiting for services. [s6-finish] sending all processes the TERM signal. [s6-finish] sending all processes the KILL signal and exiting. [s6-init] making user provided files available at /var/run/s6/etc...exited 0. [s6-init] ensuring user provided files have correct perms...exited 0. [fix-attrs.d] applying ownership & permissions fixes... [fix-attrs.d] done. [cont-init.d] executing container initialization scripts... [cont-init.d] done. [services.d] starting services [services.d] done. [cont-finish.d] executing container finish scripts... [cont-finish.d] done. [s6-finish] waiting for services. [s6-finish] sending all processes the TERM signal. [s6-finish] sending all processes the KILL signal and exiting. [s6-init] making user provided files available at /var/run/s6/etc...exited 0. [s6-init] ensuring user provided files have correct perms...exited 0. [fix-attrs.d] applying ownership & permissions fixes... [fix-attrs.d] done. [cont-init.d] executing container initialization scripts... [cont-init.d] done. [services.d] starting services [services.d] done. Any ideas? Quote Link to comment
yayitazale Posted February 24, 2023 Author Share Posted February 24, 2023 8 minutes ago, morethanenough said: Hi all, I seem to have a strange problem with the WebUI. I don't know when this started because I hadn't connected to it for a while, but the WebUI is not loading at all. The strange thing is that I have set Frigate to create RTMP feeds and these work perfectly fine. Also, recordings are being made as normal. The only thing that is not working is the WebUI. I have a Home Assistant instance on a different machine, and initially I thought there was some problem with that, but when I checked the WebUI on Unraid, I realised that's where the problem actually lies. I had installed the blakeblackshear frigate app quite a while ago, but I remember seeing somewhere that there were some breaking changes, so I removed it and installed the new version (for some reason the old one wasn't showing as installed in the Community Apps). Again, after setting everything up, everything works except the WebUI. The logs are below: Plus API Key is not formatted correctly. [2023-02-24 19:08:44] frigate.app INFO : Starting Frigate (0.11.1-2eada21) [2023-02-24 19:08:44] frigate.config WARNING : The 'retain_days' config option has been DEPRECATED and will be removed in a future version. Please use the 'days' setting under 'retain' [2023-02-24 19:08:44] frigate.config WARNING : The 'retain_days' config option has been DEPRECATED and will be removed in a future version. Please use the 'days' setting under 'retain' [2023-02-24 19:08:44] frigate.config WARNING : The 'retain_days' config option has been DEPRECATED and will be removed in a future version. Please use the 'days' setting under 'retain' [2023-02-24 19:08:44] frigate.config WARNING : The 'retain_days' config option has been DEPRECATED and will be removed in a future version. Please use the 'days' setting under 'retain' [2023-02-24 19:08:44] frigate.config WARNING : The 'retain_days' config option has been DEPRECATED and will be removed in a future version. Please use the 'days' setting under 'retain' Starting migrations [2023-02-24 19:08:44] peewee_migrate INFO : Starting migrations There is nothing to migrate [2023-02-24 19:08:44] peewee_migrate INFO : There is nothing to migrate [2023-02-24 19:08:44] detector.coral INFO : Starting detection process: 216 [2023-02-24 19:08:44] frigate.app INFO : Output process started: 218 [2023-02-24 19:08:44] frigate.app INFO : Camera processor started for FrontGarden: 226 [2023-02-24 19:08:44] frigate.edgetpu INFO : Attempting to load TPU as pci [2023-02-24 19:08:44] frigate.edgetpu INFO : TPU found [2023-02-24 19:08:44] ws4py INFO : Using epoll [2023-02-24 19:08:44] frigate.app INFO : Camera processor started for Driveway: 237 [2023-02-24 19:08:44] frigate.app INFO : Camera processor started for BackGarden: 238 [2023-02-24 19:08:44] frigate.app INFO : Camera processor started for Kitchen: 240 [2023-02-24 19:08:44] frigate.app INFO : Camera processor started for TVRoom: 242 [2023-02-24 19:08:44] frigate.app INFO : Capture process started for FrontGarden: 243 [2023-02-24 19:08:44] frigate.app INFO : Capture process started for Driveway: 246 [2023-02-24 19:08:44] frigate.app INFO : Capture process started for BackGarden: 250 [2023-02-24 19:08:44] frigate.app INFO : Capture process started for Kitchen: 253 [2023-02-24 19:08:44] frigate.app INFO : Capture process started for TVRoom: 257 [2023-02-24 19:08:44] ws4py INFO : Using epoll [2023-02-24 19:08:54] frigate.video ERROR : Driveway: Unable to read frames from ffmpeg process. [2023-02-24 19:08:54] frigate.video ERROR : Driveway: ffmpeg process is not running. exiting capture thread... [2023-02-24 19:08:54] frigate.video ERROR : Kitchen: Unable to read frames from ffmpeg process. [2023-02-24 19:08:54] frigate.video ERROR : Kitchen: ffmpeg process is not running. exiting capture thread... [2023-02-24 19:08:54] frigate.video ERROR : BackGarden: Unable to read frames from ffmpeg process. [2023-02-24 19:08:54] frigate.video ERROR : BackGarden: ffmpeg process is not running. exiting capture thread... [2023-02-24 19:08:54] frigate.video ERROR : TVRoom: Unable to read frames from ffmpeg process. [2023-02-24 19:08:54] frigate.video ERROR : TVRoom: ffmpeg process is not running. exiting capture thread... [2023-02-24 19:08:54] frigate.video ERROR : FrontGarden: Unable to read frames from ffmpeg process. [2023-02-24 19:08:54] frigate.video ERROR : FrontGarden: ffmpeg process is not running. exiting capture thread... Plus API Key is not formatted correctly. [2023-02-24 19:09:05] frigate.app INFO : Starting Frigate (0.11.1-2eada21) [2023-02-24 19:09:05] frigate.config WARNING : The 'retain_days' config option has been DEPRECATED and will be removed in a future version. Please use the 'days' setting under 'retain' [2023-02-24 19:09:05] frigate.config WARNING : The 'retain_days' config option has been DEPRECATED and will be removed in a future version. Please use the 'days' setting under 'retain' [2023-02-24 19:09:05] frigate.config WARNING : The 'retain_days' config option has been DEPRECATED and will be removed in a future version. Please use the 'days' setting under 'retain' [2023-02-24 19:09:05] frigate.config WARNING : The 'retain_days' config option has been DEPRECATED and will be removed in a future version. Please use the 'days' setting under 'retain' [2023-02-24 19:09:05] frigate.config WARNING : The 'retain_days' config option has been DEPRECATED and will be removed in a future version. Please use the 'days' setting under 'retain' Starting migrations [2023-02-24 19:09:05] peewee_migrate INFO : Starting migrations There is nothing to migrate [2023-02-24 19:09:05] peewee_migrate INFO : There is nothing to migrate [2023-02-24 19:09:05] detector.coral INFO : Starting detection process: 216 [2023-02-24 19:09:05] frigate.app INFO : Output process started: 218 [2023-02-24 19:09:05] ws4py INFO : Using epoll [2023-02-24 19:09:05] frigate.edgetpu INFO : Attempting to load TPU as pci [2023-02-24 19:09:05] frigate.edgetpu INFO : TPU found [2023-02-24 19:09:05] frigate.app INFO : Camera processor started for FrontGarden: 236 [2023-02-24 19:09:05] frigate.app INFO : Camera processor started for Driveway: 238 [2023-02-24 19:09:05] frigate.app INFO : Camera processor started for BackGarden: 239 [2023-02-24 19:09:05] frigate.app INFO : Camera processor started for Kitchen: 241 [2023-02-24 19:09:05] frigate.app INFO : Camera processor started for TVRoom: 242 [2023-02-24 19:09:05] frigate.app INFO : Capture process started for FrontGarden: 243 [2023-02-24 19:09:05] frigate.app INFO : Capture process started for Driveway: 247 [2023-02-24 19:09:05] frigate.app INFO : Capture process started for BackGarden: 251 [2023-02-24 19:09:05] frigate.app INFO : Capture process started for Kitchen: 258 [2023-02-24 19:09:05] frigate.app INFO : Capture process started for TVRoom: 262 [2023-02-24 19:09:05] ws4py INFO : Using epoll [cont-finish.d] executing container finish scripts... [cont-finish.d] done. [s6-finish] waiting for services. [s6-finish] sending all processes the TERM signal. [s6-finish] sending all processes the KILL signal and exiting. [s6-init] making user provided files available at /var/run/s6/etc...exited 0. [s6-init] ensuring user provided files have correct perms...exited 0. [fix-attrs.d] applying ownership & permissions fixes... [fix-attrs.d] done. [cont-init.d] executing container initialization scripts... [cont-init.d] done. [services.d] starting services [services.d] done. [cont-finish.d] executing container finish scripts... [cont-finish.d] done. [s6-finish] waiting for services. [s6-finish] sending all processes the TERM signal. [s6-finish] sending all processes the KILL signal and exiting. [s6-init] making user provided files available at /var/run/s6/etc...exited 0. [s6-init] ensuring user provided files have correct perms...exited 0. [fix-attrs.d] applying ownership & permissions fixes... [fix-attrs.d] done. [cont-init.d] executing container initialization scripts... [cont-init.d] done. [services.d] starting services [services.d] done. Any ideas? Those logs are saying that the service has shut down and it looks like you have some issues with ffmpeg configuration. I can't say why are you seeing the rtmp streams. Is the container still running? Quote Link to comment
Xxharry Posted February 26, 2023 Share Posted February 26, 2023 I have moved to i5-13600k and tried to enable hardware acceleration. However, I get the below error. I have tried repliacing qsv with vaapi but no luck. I am passing through the device /dev/dri/renderD128 to the container. My config is in here https://pastebin.com/RcNE9dff I have 4 cameras but the config file has been truncated and only shows one. Any help is appreciated Quote Link to comment
yayitazale Posted February 27, 2023 Author Share Posted February 27, 2023 On 2/26/2023 at 6:34 AM, Xxharry said: I have moved to i5-13600k and tried to enable hardware acceleration. However, I get the below error. I have tried repliacing qsv with vaapi but no luck. I am passing through the device /dev/dri/renderD128 to the container. My config is in here https://pastebin.com/RcNE9dff I have 4 cameras but the config file has been truncated and only shows one. Any help is appreciated This is out of my knowledge, please as this looks like something related with configuration of frigate itself and not the container on unraid, open a issue on github. https://github.com/blakeblackshear/frigate/issues Quote Link to comment
macmanluke Posted March 7, 2023 Share Posted March 7, 2023 Having an issue with my docker crashing about once a week, looked at the log today but it does not seem to be anything helpful Any suggestions? [2023-03-06 23:12:50] frigate.watchdog INFO : Detection appears to be stuck. Restarting detection process... [2023-03-06 23:12:50] root INFO : Waiting for detection process to exit gracefully... [2023-03-06 23:13:20] root INFO : Detection process didnt exit. Force killing... [2023-03-06 23:13:20] detector.coral INFO : Starting detection process: 8443 [2023-03-06 23:13:20] frigate.edgetpu INFO : Attempting to load TPU as usb Process detector:coral: [2023-03-06 23:13:45] frigate.edgetpu ERROR : No EdgeTPU was detected. If you do not have a Coral device yet, you must configure CPU detectors. Traceback (most recent call last): File "/usr/lib/python3/dist-packages/tflite_runtime/interpreter.py", line 160, in load_delegate delegate = Delegate(library, options) File "/usr/lib/python3/dist-packages/tflite_runtime/interpreter.py", line 119, in __init__ raise ValueError(capture.message) ValueError During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/usr/lib/python3.9/multiprocessing/process.py", line 315, in _bootstrap self.run() File "/usr/lib/python3.9/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/opt/frigate/frigate/edgetpu.py", line 135, in run_detector object_detector = LocalObjectDetector( File "/opt/frigate/frigate/edgetpu.py", line 43, in __init__ edge_tpu_delegate = load_delegate("libedgetpu.so.1.0", device_config) File "/usr/lib/python3/dist-packages/tflite_runtime/interpreter.py", line 162, in load_delegate raise ValueError('Failed to load delegate from {}\n{}'.format( ValueError: Failed to load delegate from libedgetpu.so.1.0 [2023-03-06 23:13:50] frigate.watchdog INFO : Detection appears to have stopped. Exiting frigate... Quote Link to comment
yayitazale Posted March 7, 2023 Author Share Posted March 7, 2023 4 hours ago, macmanluke said: Having an issue with my docker crashing about once a week, looked at the log today but it does not seem to be anything helpful Any suggestions? [2023-03-06 23:12:50] frigate.watchdog INFO : Detection appears to be stuck. Restarting detection process... [2023-03-06 23:12:50] root INFO : Waiting for detection process to exit gracefully... [2023-03-06 23:13:20] root INFO : Detection process didnt exit. Force killing... [2023-03-06 23:13:20] detector.coral INFO : Starting detection process: 8443 [2023-03-06 23:13:20] frigate.edgetpu INFO : Attempting to load TPU as usb Process detector:coral: [2023-03-06 23:13:45] frigate.edgetpu ERROR : No EdgeTPU was detected. If you do not have a Coral device yet, you must configure CPU detectors. Traceback (most recent call last): File "/usr/lib/python3/dist-packages/tflite_runtime/interpreter.py", line 160, in load_delegate delegate = Delegate(library, options) File "/usr/lib/python3/dist-packages/tflite_runtime/interpreter.py", line 119, in __init__ raise ValueError(capture.message) ValueError During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/usr/lib/python3.9/multiprocessing/process.py", line 315, in _bootstrap self.run() File "/usr/lib/python3.9/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/opt/frigate/frigate/edgetpu.py", line 135, in run_detector object_detector = LocalObjectDetector( File "/opt/frigate/frigate/edgetpu.py", line 43, in __init__ edge_tpu_delegate = load_delegate("libedgetpu.so.1.0", device_config) File "/usr/lib/python3/dist-packages/tflite_runtime/interpreter.py", line 162, in load_delegate raise ValueError('Failed to load delegate from {}\n{}'.format( ValueError: Failed to load delegate from libedgetpu.so.1.0 [2023-03-06 23:13:50] frigate.watchdog INFO : Detection appears to have stopped. Exiting frigate... Look like your USB stack is crashing. Are you using a external USB hub? Are you using a USB 3.0 port? Quote Link to comment
macmanluke Posted March 7, 2023 Share Posted March 7, 2023 Plugged into the back of the server with the little extension it came with Likely USB3.0 as i dont think i even have any 2.0 ports Quote Link to comment
yayitazale Posted March 8, 2023 Author Share Posted March 8, 2023 (edited) 9 hours ago, macmanluke said: Plugged into the back of the server with the little extension it came with Likely USB3.0 as i dont think i even have any 2.0 ports Can be a faulty device... Did you see the TPU in the list of devices on unraid (tools -> System devices)? You have to see something like "Bus 002 Device 002 Port 2-4 ID 18d1:9302 Google Inc" Can you show how are you mapping the device and how did you configured the device on the config file? You can try also in another USB port. Edited March 8, 2023 by yayitazale Quote Link to comment
morethanenough Posted March 8, 2023 Share Posted March 8, 2023 On 2/24/2023 at 7:18 PM, yayitazale said: Those logs are saying that the service has shut down and it looks like you have some issues with ffmpeg configuration. I can't say why are you seeing the rtmp streams. Is the container still running? Yes, it is. Somehow it started working on the next day. Anyway, thank you for replying, all sorted now. Quote Link to comment
macmanluke Posted March 8, 2023 Share Posted March 8, 2023 16 hours ago, yayitazale said: Can be a faulty device... Did you see the TPU in the list of devices on unraid (tools -> System devices)? You have to see something like "Bus 002 Device 002 Port 2-4 ID 18d1:9302 Google Inc" Can you show how are you mapping the device and how did you configured the device on the config file? You can try also in another USB port. Yea it shows in system devices. It also works fine once i start frigate again each time after i notice its stopped. mapped to the docker with /dev/bus/usb config is: detectors: coral: type: edgetpu device: usb Will try another USB port see if there is any difference Quote Link to comment
Ironcurtain Posted March 10, 2023 Share Posted March 10, 2023 Hi, i switches the hardware today for my unraid server. Not i frigate does not work. The error: docker: Error response from daemon: error gathering device information while adding custom device "/dev/dri/renderD128": no such file or directory. But the driver is installed and i see this: But und /dev/dri i see only this: Someone has an idea? tower-diagnostics-20230310-2254.zip Quote Link to comment
ich777 Posted March 11, 2023 Share Posted March 11, 2023 9 hours ago, Ironcurtain said: /dev/dri/renderD128 This is the iGPU, but it is not activated, are you sure it's enabled in the BIOS and set to the first Display Device? I only see your onboard Aspeed graphics in your Diagnostics and this is the card what you see in /dev/dri If you want to pass through your Coral TPU you have to use in your specific use case (PCI based Coral TPU) this device path: /dev/apex_0 Quote Link to comment
Ironcurtain Posted March 11, 2023 Share Posted March 11, 2023 I have an Asus P10S-I Board which has an integrated graphi controller from Aspeed. There is an i3 7100 on the board. In the bios i can only enable vt-d and set the VGA Priority to Offboard or Onboard Device. But it makes no difference. When i understand this threat correct, it is not possible to use the igpu with this board. But im pretty sure, that it worked in the past. This is my output unter system devices: Quote Link to comment
SohailS Posted March 11, 2023 Share Posted March 11, 2023 so after getting everything up and running I have added another GPU into my server to use with a VM. so i have changed the config of my docker I have added the below and then the following two parameters I have added the correct ID for the GPU but for some reason its using the other GPU what have i done wrong? Quote Link to comment
Recommended Posts
Join the conversation
You can post now and register later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.