morethanenough Posted April 13, 2022 Share Posted April 13, 2022 Hi @ich777 Ok, it seems the issue was indeed with the TPU reaching high temperatures. shutdowntemp0=104800 shutdown_en0=1 shutdowntemp1=104800 shutdown_en1=1 shutdowntemp2=104800 shutdown_en2=1 shutdowntemp3=104800 shutdown_en3=1 Now it's much better as I allowed some more ventilation in the case. 2022-04-13 09:19:44 Coral Temp: 45.80C 2022-04-13 09:19:59 Coral Temp: 45.55C 2022-04-13 09:20:14 Coral Temp: 45.55C 2022-04-13 09:20:29 Coral Temp: 46.80C 2022-04-13 09:20:44 Coral Temp: 47.55C 2022-04-13 09:20:59 Coral Temp: 48.30C 2022-04-13 09:21:14 Coral Temp: 48.55C 2022-04-13 09:21:29 Coral Temp: 49.05C 2022-04-13 09:21:44 Coral Temp: 49.30C 2022-04-13 09:21:59 Coral Temp: 49.55C 2022-04-13 09:22:14 Coral Temp: 49.80C 2022-04-13 09:22:29 Coral Temp: 49.80C 2022-04-13 09:22:44 Coral Temp: 49.80C 2022-04-13 09:22:59 Coral Temp: 50.30C 2022-04-13 09:23:14 Coral Temp: 50.05C 2022-04-13 09:23:29 Coral Temp: 50.05C 2022-04-13 09:23:44 Coral Temp: 49.80C 2022-04-13 09:23:59 Coral Temp: 49.80C 2022-04-13 09:24:14 Coral Temp: 50.05C 2022-04-13 09:24:29 Coral Temp: 49.80C 2022-04-13 09:24:44 Coral Temp: 49.55C 2022-04-13 09:24:59 Coral Temp: 50.05C 2022-04-13 09:25:14 Coral Temp: 49.80C 2022-04-13 09:25:29 Coral Temp: 49.55C 2022-04-13 09:25:44 Coral Temp: 49.80C 2022-04-13 09:25:59 Coral Temp: 49.80C 2022-04-13 09:26:14 Coral Temp: 50.05C 2022-04-13 09:26:29 Coral Temp: 50.05C 2022-04-13 09:26:44 Coral Temp: 49.80C 2022-04-13 09:26:59 Coral Temp: 49.80C 2022-04-13 09:27:14 Coral Temp: 50.05C 2022-04-13 09:27:29 Coral Temp: 49.80C 2022-04-13 09:27:44 Coral Temp: 49.80C 2022-04-13 09:27:59 Coral Temp: 49.80C 2022-04-13 09:28:14 Coral Temp: 50.05C 2022-04-13 09:28:29 Coral Temp: 49.80C 2022-04-13 09:28:44 Coral Temp: 50.30C 2022-04-13 09:28:59 Coral Temp: 49.80C 2022-04-13 09:29:14 Coral Temp: 49.80C 2022-04-13 09:29:29 Coral Temp: 49.80C 2022-04-13 09:29:44 Coral Temp: 50.05C The script works great. I will monitor how things go and get back to you. Thank you for your assistance! 1 Quote Link to comment
Jack8COke Posted April 26, 2022 Share Posted April 26, 2022 Hi, i have the coral b+m key. Do someone has an usb to m.2 adapter where the coral woks? I dont wont to lose an m.2 slot for the coral. But the usb and a+e variant is not available. Quote Link to comment
yayitazale Posted April 27, 2022 Author Share Posted April 27, 2022 18 hours ago, Jack8COke said: Hi, i have the coral b+m key. Do someone has an usb to m.2 adapter where the coral woks? I dont wont to lose an m.2 slot for the coral. But the usb and a+e variant is not available. Not sure if it is going to work but you can try with one like this: https://www.amazon.com/-/es/Adaptador-RIITOP-tarjeta-lector-compatible/dp/B08FWZXT2N/ref=sr_1_3?keywords=usb+to+m2+adapter&qid=1651043207&sr=8-3 Some time ago @ich777 said this, maybe is useful for you. 1 Quote Link to comment
ich777 Posted April 27, 2022 Share Posted April 27, 2022 4 minutes ago, yayitazale said: Not sure if it is going to work but you can try with one like this: https://www.amazon.com/-/es/Adaptador-RIITOP-tarjeta-lector-compatible/dp/B08FWZXT2N/ref=sr_1_3?keywords=usb+to+m2+adapter&qid=1651043207&sr=8-3 Really curious if those adapters will work too... Quote Link to comment
Jack8COke Posted May 3, 2022 Share Posted May 3, 2022 On 4/27/2022 at 9:17 AM, ich777 said: Really curious if those adapters will work too... i ordered 3 variants and will give you a feedback. I hope it will work *cross fingers* 🙂 2 Quote Link to comment
Jack8COke Posted May 4, 2022 Share Posted May 4, 2022 2 variants arrived and i think it will not work. They both have a realtek chipsat on it. Under Tools -> System devices i can not see anything about "Coral Edge TPU" anymore. There is only unde r usb devices: Bus 001 Device 002:ID 0bda:9210 Realtek Semiconductor Corp. LM915 Im not nerdy enough to try a few terminal commands but i think if it does not recognize it as a Coral it will not work, or what is your opinion? Quote Link to comment
luixmod Posted May 5, 2022 Share Posted May 5, 2022 hello i have frigate install and two cameras one is a hikvision but i have a problem, frigate detects the camera shows the feed, but dont record. give alot of erros on the logs but i dont understand what it is! am i missing something on the config? [2022-05-05 11:48:28] ffmpeg.jardim.detect ERROR : av_interleaved_write_frame(): Connection reset by peer [2022-05-05 11:48:28] ffmpeg.jardim.detect ERROR : [flv @ 0x55a660aa3840] Failed to update header with correct duration. [2022-05-05 11:48:28] ffmpeg.jardim.detect ERROR : [flv @ 0x55a660aa3840] Failed to update header with correct filesize. [2022-05-05 11:48:28] ffmpeg.jardim.detect ERROR : Error writing trailer of rtmp://127.0.0.1/live/jardim: Connection reset by peer [2022-05-05 11:48:29] frigate.video ERROR : jardim: Unable to read frames from ffmpeg process. [2022-05-05 11:48:29] frigate.video ERROR : jardim: ffmpeg process is not running. exiting capture thread... [2022-05-05 11:48:29] frigate.video ERROR : jardim: Unable to read frames from ffmpeg process. [2022-05-05 11:48:29] frigate.video ERROR : jardim: ffmpeg process is not running. exiting capture thread... [2022-05-05 11:48:38] watchdog.jardim ERROR : Ffmpeg process crashed unexpectedly for jardim. [2022-05-05 11:48:38] watchdog.jardim ERROR : The following ffmpeg logs include the last 100 lines prior to exit. [2022-05-05 11:48:38] ffmpeg.jardim.detect ERROR : av_interleaved_write_frame(): Connection reset by peer [2022-05-05 11:48:38] ffmpeg.jardim.detect ERROR : [swscaler @ 0x55b6da4832c0] deprecated pixel format used, make sure you did set range correctly [2022-05-05 11:48:38] ffmpeg.jardim.detect ERROR : Finishing stream 1:0 without any data written to it. [2022-05-05 11:48:38] ffmpeg.jardim.detect ERROR : [flv @ 0x55b6da999980] Failed to update header with correct duration. [2022-05-05 11:48:38] ffmpeg.jardim.detect ERROR : [flv @ 0x55b6da999980] Failed to update header with correct filesize. [2022-05-05 11:48:38] ffmpeg.jardim.detect ERROR : Error writing trailer of rtmp://127.0.0.1/live/jardim: Connection reset by peer Quote Link to comment
yayitazale Posted May 5, 2022 Author Share Posted May 5, 2022 (edited) 2 minutes ago, luixmod said: hello i have frigate install and two cameras one is a hikvision but i have a problem, frigate detects the camera shows the feed, but dont record. give alot of erros on the logs but i dont understand what it is! am i missing something on the config? [2022-05-05 11:48:28] ffmpeg.jardim.detect ERROR : av_interleaved_write_frame(): Connection reset by peer [2022-05-05 11:48:28] ffmpeg.jardim.detect ERROR : [flv @ 0x55a660aa3840] Failed to update header with correct duration. [2022-05-05 11:48:28] ffmpeg.jardim.detect ERROR : [flv @ 0x55a660aa3840] Failed to update header with correct filesize. [2022-05-05 11:48:28] ffmpeg.jardim.detect ERROR : Error writing trailer of rtmp://127.0.0.1/live/jardim: Connection reset by peer [2022-05-05 11:48:29] frigate.video ERROR : jardim: Unable to read frames from ffmpeg process. [2022-05-05 11:48:29] frigate.video ERROR : jardim: ffmpeg process is not running. exiting capture thread... [2022-05-05 11:48:29] frigate.video ERROR : jardim: Unable to read frames from ffmpeg process. [2022-05-05 11:48:29] frigate.video ERROR : jardim: ffmpeg process is not running. exiting capture thread... [2022-05-05 11:48:38] watchdog.jardim ERROR : Ffmpeg process crashed unexpectedly for jardim. [2022-05-05 11:48:38] watchdog.jardim ERROR : The following ffmpeg logs include the last 100 lines prior to exit. [2022-05-05 11:48:38] ffmpeg.jardim.detect ERROR : av_interleaved_write_frame(): Connection reset by peer [2022-05-05 11:48:38] ffmpeg.jardim.detect ERROR : [swscaler @ 0x55b6da4832c0] deprecated pixel format used, make sure you did set range correctly [2022-05-05 11:48:38] ffmpeg.jardim.detect ERROR : Finishing stream 1:0 without any data written to it. [2022-05-05 11:48:38] ffmpeg.jardim.detect ERROR : [flv @ 0x55b6da999980] Failed to update header with correct duration. [2022-05-05 11:48:38] ffmpeg.jardim.detect ERROR : [flv @ 0x55b6da999980] Failed to update header with correct filesize. [2022-05-05 11:48:38] ffmpeg.jardim.detect ERROR : Error writing trailer of rtmp://127.0.0.1/live/jardim: Connection reset by peer Can you attach or paste your config of the cameras section? Does your camera accept two connections to same rstp endpoint at the same time? Edited May 5, 2022 by yayitazale Quote Link to comment
luixmod Posted May 5, 2022 Share Posted May 5, 2022 19 minutes ago, yayitazale said: Can you attach or paste your config of the cameras section? mqtt: # Required: host name host: 9.9.9.10 # Optional: port (default: shown below) port: 1883 # Optional: topic prefix (default: shown below) # NOTE: must be unique if you are running multiple instances topic_prefix: frigate # Optional: client id (default: shown below) # NOTE: must be unique if you are running multiple instances client_id: frigate # Optional: user user: mqtt_user # Optional: password # NOTE: MQTT password can be specified with an environment variables that must begin with 'FRIGATE_'. # e.g. password: '{FRIGATE_MQTT_PASSWORD}' password: password # Optional: tls_ca_certs for enabling TLS using self-signed certs (default: None) #tls_ca_certs: /path/to/ca.crt # Optional: tls_client_cert and tls_client key in order to use self-signed client # certificates (default: None) # NOTE: certificate must not be password-protected # do not set user and password when using a client certificate #tls_client_cert: /path/to/client.crt #tls_client_key: /path/to/client.key # Optional: tls_insecure (true/false) for enabling TLS verification of # the server hostname in the server certificate (default: None) #tls_insecure: false # Optional: interval in seconds for publishing stats (default: shown below) stats_interval: 60 detectors: coral: type: edgetpu device: pci database: path: /media/frigate/frigate.db birdseye: enabled: True width: 640 height: 480 quality: 8 mode: motion cameras: cozinha: # <------ Name the camera ffmpeg: inputs: - path: rtsp://admin:[email protected]:554/stream1 roles: - detect - rtmp detect: enabled: true width: 1980 height: 1080 fps: 20 snapshots: enabled: true timestamp: true bounding_box: true crop: False retain: default: 10 objects: person: 30 objects: track: - person jardim: # <------ Name the camera ffmpeg: inputs: - path: rtsp://admin:[email protected]:554/Streaming/Channels/101 roles: - detect - rtmp detect: enabled: true width: 1980 height: 1080 fps: 20 snapshots: enabled: true timestamp: true bounding_box: true crop: False retain: default: 10 objects: person: 30 objects: track: - person - cat - dog - car - bicycle rtmp: enabled: true 19 minutes ago, yayitazale said: Does your camera accept two connections to same rstp endpoint at the same time? yes, the hikvison have mutli stream Quote Link to comment
yayitazale Posted May 5, 2022 Author Share Posted May 5, 2022 Did you add record config? https://docs.frigate.video/configuration/record The errors maybe are related with ffmpeg configurations, please ask for help on github https://github.com/blakeblackshear/frigate Quote Link to comment
takkischitt Posted May 12, 2022 Share Posted May 12, 2022 When I install this container, I get the following error: [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. ************************************************************* ************************************************************* *** Your config file is not valid! *** *** Please check the docs at *** *** https://docs.frigate.video/configuration/index *** ************************************************************* ************************************************************* *** Config Validation Errors *** ************************************************************* [Errno 2] No such file or directory: '/config/config.yml' [2022-05-12 22:28:49] frigate.app INFO : Starting Frigate (0.10.1-83481af) Traceback (most recent call last): File "/opt/frigate/frigate/app.py", line 312, in start self.init_config() File "/opt/frigate/frigate/app.py", line 77, in init_config user_config = FrigateConfig.parse_file(config_file) File "/opt/frigate/frigate/config.py", line 896, in parse_file with open(config_file) as f: FileNotFoundError: [Errno 2] No such file or directory: '/config/config.yml' ************************************************************* *** End Config Validation Errors *** ************************************************************* [cmd] python3 exited 1 [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. When I checked the /appdata/frigate path, there is nothing in there, so I created a folder called 'config' and added the minimal config, but I'm still getting the above error. Can anyone advise? I thought containers always installed into 'appdata'? Quote Link to comment
yayitazale Posted May 13, 2022 Author Share Posted May 13, 2022 14 hours ago, takkischitt said: When I install this container, I get the following error: [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. ************************************************************* ************************************************************* *** Your config file is not valid! *** *** Please check the docs at *** *** https://docs.frigate.video/configuration/index *** ************************************************************* ************************************************************* *** Config Validation Errors *** ************************************************************* [Errno 2] No such file or directory: '/config/config.yml' [2022-05-12 22:28:49] frigate.app INFO : Starting Frigate (0.10.1-83481af) Traceback (most recent call last): File "/opt/frigate/frigate/app.py", line 312, in start self.init_config() File "/opt/frigate/frigate/app.py", line 77, in init_config user_config = FrigateConfig.parse_file(config_file) File "/opt/frigate/frigate/config.py", line 896, in parse_file with open(config_file) as f: FileNotFoundError: [Errno 2] No such file or directory: '/config/config.yml' ************************************************************* *** End Config Validation Errors *** ************************************************************* [cmd] python3 exited 1 [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. When I checked the /appdata/frigate path, there is nothing in there, so I created a folder called 'config' and added the minimal config, but I'm still getting the above error. Can anyone advise? I thought containers always installed into 'appdata'? You don't need to create a config folder, just add the config file in the root folder of appdata/frigate Quote Link to comment
ingus16 Posted June 8, 2022 Share Posted June 8, 2022 (edited) No offence to maintainer, just about the product overall. I completely gave up with this. Configuration in style of 90s and are the real pain . Zillions issues. Not recommend at all unless you have powerful hardware, few cameras and no need to use hw accell flags , optimizing etc. Was quite promising because of MQTT support . To complicated stuff for 21st century if software has web interface with no configuration/settings at all Edited June 8, 2022 by ingus16 Quote Link to comment
Soulflyzz Posted June 10, 2022 Share Posted June 10, 2022 Hello, Generic question, I am running blakeblackshear/frigate:stable-amd64nvidia and everything is working as I want it to with Frigate. But in homeassistantcore (Docker), when I try to Set up a new integration, i add the Frigate info IP address http://***.***.***.***:5000/ which i use to view Frigate and it comes up with "Failed to connect". I have read that the integration requires Version 10.*.* and this docker image is Version 9.*.* has anyone else ran into this issue or is it just me? Is there a known solution? Also i will add this integration did work at one time before that big update the broke frigate and I had to update the .yaml. Sorry if this was long winded but I wanted to supply as much info as I could. Quote Link to comment
Todd Swanson Posted June 11, 2022 Share Posted June 11, 2022 Could someone help me figure out why my recordings are being stored until the drive fills up? I want to record 24/7 for 20 days. This was working at one time. cameras: Front_Door: ffmpeg: inputs: - path: rtsp://xyz/cam/realmonitor?channel=1&subtype=0 roles: - detect - record detect: width: 2688 height: 1520 fps: 5 objects: track: - person - dog filters: person: threshold: 0.65 snapshots: enabled: true timestamp: false bounding_box: true retain: default: 20 record: enabled: true expire_interval: 120 retain: days: 20 mode: all events: retain: default: 20 Quote Link to comment
sillywalks Posted June 21, 2022 Share Posted June 21, 2022 I just got a mini cpie coral and installed it in unraid. Downloaded the driver and the unraid system page shows the device: [1ac1:089a] 01:00.0 System peripheral: Global Unichip Corp. Coral Edge TPU I have the frigate config setup with the mapping for /dev/apex_0 The frigate config.yml looks like this: detectors: coral_pci: type: edgetpu device: pci But when starting the container it crashes with the following errors: [2022-06-21 23:35:18] detector.coral_pci INFO : Starting detection process: 218 [2022-06-21 23:35:18] frigate.edgetpu INFO : Attempting to load TPU as pci Process detector:coral_pci: [2022-06-21 23:35:30] 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/python3.8/multiprocessing/process.py", line 315, in _bootstrap self.run() File "/usr/lib/python3.8/multiprocessing/process.py", line 108, in run self._target(*self._args, **self._kwargs) File "/opt/frigate/frigate/edgetpu.py", line 136, in run_detector object_detector = LocalObjectDetector( File "/opt/frigate/frigate/edgetpu.py", line 44, 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 [2022-06-21 23:35:38] frigate.watchdog INFO : Detection appears to have stopped. Exiting frigate... [cont-finish.d] executing container finish scripts... [cont-finish.d] done. [s6-finish] waiting for services. [2022-06-21 23:35:38] frigate.video ERROR : front: Unable to read frames from ffmpeg process. [2022-06-21 23:35:38] frigate.video ERROR : front: ffmpeg process is not running. exiting capture thread... [2022-06-21 23:35:38] frigate.video ERROR : drive: Unable to read frames from ffmpeg process. [2022-06-21 23:35:38] frigate.video ERROR : drive: ffmpeg process is not running. exiting capture thread... [s6-finish] sending all processes the TERM signal. [s6-finish] sending all processes the KILL signal and exiting. [s6-finish] sending all processes the KILL signal and exiting. Any idea whats going on here? Must I restart the server after installing the driver? Quote Link to comment
Mlatx Posted June 22, 2022 Share Posted June 22, 2022 iOS Notifications Hi All, I finally have Frigate setup with Home Assistant Core. I am using this blueprint for notifications, https://community.home-assistant.io/t/frigate-mobile-app-notifications/311091. I trigger an alert, and I am not getting the notification on my Home Assistant app. Am I missing something in the configuration? Is there a better suited blueprint or notification method? Quote Link to comment
ich777 Posted June 22, 2022 Share Posted June 22, 2022 On 5/4/2022 at 6:53 PM, Jack8COke said: Im not nerdy enough to try a few terminal commands but i think if it does not recognize it as a Coral it will not work, or what is your opinion? No, will not work... Quote Link to comment
sillywalks Posted June 26, 2022 Share Posted June 26, 2022 (edited) @ich777 any idea whats going on? when I reboot my unraid machine the driver shows the coral as working: as soon as I start frigate the coral seems to crash and stays in shutdown mode until next reboot. might be related to this github issue which never got resolved properly https://github.com/blakeblackshear/frigate/issues/3283 Edited June 26, 2022 by sillywalks mention Quote Link to comment
ich777 Posted June 26, 2022 Share Posted June 26, 2022 1 hour ago, sillywalks said: as soon as I start frigate the coral seems to crash and stays in shutdown mode until next reboot. Yes, it is most likely that the shutdown temperature of 104.80 °C was triggered and that the module shut itself off. What module do you own? Are you sure that you have enough airflow over the module? I've also posted a tutorial how you can write the temperature readings to a file to see what it actually does: Quote Link to comment
sillywalks Posted June 26, 2022 Share Posted June 26, 2022 13 minutes ago, ich777 said: Yes, it is most likely that the shutdown temperature of 104.80 °C was triggered and that the module shut itself off. What module do you own? Are you sure that you have enough airflow over the module? I've also posted a tutorial how you can write the temperature readings to a file to see what it actually does: Thanks for taking the time to answer! I'm using the mini pcie module inside a pci converter (everything else is unavailable atm) I restarted the container and for the first time it actually ran for a while and didn't crash immediately. As soon as I walked out and around the cameras (actually giving the coral something to do) it again crashed. [2022-06-26 20:27:11] detector.coral_pci INFO : Starting detection process: 216 [2022-06-26 20:27:11] frigate.edgetpu INFO : Attempting to load TPU as pci [2022-06-26 20:27:11] frigate.edgetpu INFO : TPU found [2022-06-26 20:27:11] ws4py INFO : Using epoll [2022-06-26 20:27:16] frigate.record WARNING : Discarding a corrupt recording segment: front-20220626202713.mp4 [2022-06-26 20:27:16] frigate.record WARNING : Discarding a corrupt recording segment: front-20220626202713.mp4 [2022-06-26 20:27:25] ws4py INFO : Managing websocket [Local => 127.0.0.1:5002 | Remote => 127.0.0.1:39598] [2022-06-26 20:28:21] frigate.watchdog INFO : Detection appears to be stuck. Restarting detection process... [2022-06-26 20:28:21] root INFO : Waiting for detection process to exit gracefully... [2022-06-26 20:28:51] root INFO : Detection process didnt exit. Force killing... [2022-06-26 20:29:04] detector.coral_pci INFO : Starting detection process: 354 [2022-06-26 20:29:04] frigate.edgetpu INFO : Attempting to load TPU as pci [2022-06-26 20:29:17] frigate.edgetpu ERROR : No EdgeTPU was detected. If you do not have a Coral device yet, you must configure CPU detectors. Process detector:coral_pci: 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 [2022-06-26 20:29:19] ws4py INFO : Terminating websocket [Local => 127.0.0.1:5002 | Remote => 127.0.0.1:39598] [2022-06-26 20:29:19] ws4py INFO : Managing websocket [Local => 127.0.0.1:5002 | Remote => 127.0.0.1:58352] [2022-06-26 20:29:24] frigate.watchdog INFO : Detection appears to have stopped. Exiting frigate... [2022-06-26 20:29:24] ws4py INFO : Terminating websocket [Local => 127.0.0.1:5002 | Remote => 127.0.0.1:58352] [2022-06-26 20:29:24] frigate.video ERROR : drive: Unable to read frames from ffmpeg process. [2022-06-26 20:29:24] frigate.video ERROR : drive: ffmpeg process is not running. exiting capture thread... [2022-06-26 20:29:24] frigate.video ERROR : front: Unable to read frames from ffmpeg process. [2022-06-26 20:29:24] frigate.video ERROR : front: ffmpeg process is not running. exiting capture thread... [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. The temp readings from your script don't make a lot of sense. -89.7*C sound wrong. But I highly doubt it jumped from 40*C to 100*c in 15 seconds to cause a temperature crash. See here: 2022-06-26 20:26:03 Coral Temp: 39.55C 2022-06-26 20:26:18 Coral Temp: 39.55C 2022-06-26 20:26:33 Coral Temp: 39.55C 2022-06-26 20:26:48 Coral Temp: 39.80C 2022-06-26 20:27:03 Coral Temp: 39.80C 2022-06-26 20:27:18 Coral Temp: 39.80C 2022-06-26 20:27:33 Coral Temp: 39.80C 2022-06-26 20:27:48 Coral Temp: 39.80C 2022-06-26 20:28:03 Coral Temp: 39.80C 2022-06-26 20:28:18 Coral Temp: -89.70C 2022-06-26 20:28:33 Coral Temp: -89.70C 2022-06-26 20:28:48 Coral Temp: -89.70C 2022-06-26 20:29:03 Coral Temp: -89.70C 2022-06-26 20:29:18 Coral Temp: -89.70C 2022-06-26 20:29:33 Coral Temp: -89.70C Please let me know what I can do to debug this further. Quote Link to comment
sillywalks Posted June 26, 2022 Share Posted June 26, 2022 @ich777 I might have been an idiot and setup an unasigned drive in the wrong mode (not SLAVE r/w) since changing this all is running smoothly. Will let it run and see if it keeps going. Quote Link to comment
ich777 Posted June 26, 2022 Share Posted June 26, 2022 21 minutes ago, sillywalks said: But I highly doubt it jumped from 40*C to 100*c in 15 seconds to cause a temperature crash. Why not? 22 minutes ago, sillywalks said: The temp readings from your script don't make a lot of sense. -89.7*C sound wrong. These are the redings from the TPU itself and nothing more but if it says -89.7C then ther must be something wrong… What does the Pligin page say? 4 minutes ago, sillywalks said: I might have been an idiot and setup an unasigned drive in the wrong mode (not SLAVE r/w) since changing this all is running smoothly. Will let it run and see if it keeps going. I really can‘t imagine thats related, but it may be if the application itself crashes. Quote Link to comment
sillywalks Posted June 26, 2022 Share Posted June 26, 2022 35 minutes ago, ich777 said: These are the redings from the TPU itself and nothing more but if it says -89.7C then ther must be something wrong… What does the Pligin page say? Plugin page didn't say anything except "shutdown" Currently its been running over an hour without any issues and multiple working detections. Quote Link to comment
ich777 Posted June 26, 2022 Share Posted June 26, 2022 3 minutes ago, sillywalks said: Plugin page didn't say anything except "shutdown" Currently its been running over an hour without any issues and multiple working detections. So Unassigned Devices caused this? What temperature are you currently on? 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.