Sweet!

I don’t have an external GPU either, just the onboard Intel graphics is what I use now. Also worth mentioning to use integrated graphics your Docker Compose needs:

devices:
      - /dev/dri/renderD128:/dev/dri/renderD128

I’m not using substreams. I have 2 cameras and the motion detection doesn’t stress the CPU too much. If I add more cameras I’d consider using substreams for motion detection to reduce the load.

Your still frames in Home Assistant are the exact problem I was having. If your cameras really do need go2rtc to reduce connections (my wifi camera doesn’t seem to care), you might try changing your Docker container to network_mode: host and see if that fixes it.

Here’s my config. Most of the notations were put there by Frigate and I’ve de-identified everything. Notice at the bottom go2rtc is all commented out, so if I want to add it back in I can just remove the #s. Hope it helps.

mqtt:
  enabled: true
  host: <ip of Home Assistant>
  port: 1883
  topic_prefix: frigate
  client_id: frigate
  user: mqtt username
  password: mqtt password
  stats_interval: 60
  qos: 0

cameras:     # No cameras defined, UI wizard should be used
  baby_cam:
    enabled: true
    friendly_name: Baby Cam
    ffmpeg:
      inputs:
        - path: 
            rtsp://user:pw@<ip-addr>:554/cam/realmonitor?channel=1&subtype=0&unicast=true&proto=Onvif
          roles:
            - detect
            - record
      hwaccel_args: preset-vaapi
    detect:
      enabled: true # <---- disable detection until you have a working camera feed
      width: 1920 # <---- update for your camera's resolution
      height: 1080 # <---- update for your camera's resolution
    record:
      enabled: true
      continuous:
        days: 150
      sync_recordings: true
      alerts:
        retain:
          days: 150
          mode: all
      detections:
        retain:
          days: 150
          mode: all
    snapshots:
      enabled: true
    motion:
      mask: 0.691,0.015,0.693,0.089,0.965,0.093,0.962,0.019
      threshold: 14
      contour_area: 20
      improve_contrast: true
    objects:
      track:
        - person
        - cat
        - dog
        - toothbrush
        - train

  front_cam:
    enabled: true
    friendly_name: Front Cam
    ffmpeg:
      inputs:
        - path: 
            rtsp://user:pw@<ip-addr>:554/cam/realmonitor?channel=1&subtype=0&unicast=true&proto=Onvif
          roles:
            - detect
            - record
      hwaccel_args: preset-vaapi
    detect:
      enabled: true # <---- disable detection until you have a working camera feed
      width: 2688 # <---- update for your camera's resolution
      height: 1512 # <---- update for your camera's resolution
    record:
      enabled: true
      continuous:
        days: 150
      sync_recordings: true
      alerts:
        retain:
          days: 150
          mode: all
      detections:
        retain:
          days: 150
          mode: all
    snapshots:
      enabled: true
    motion:
      mask:
        - 0.765,0.003,0.765,0.047,0.996,0.048,0.992,0.002
        - 0.627,0.998,0.619,0.853,0.649,0.763,0.713,0.69,0.767,0.676,0.819,0.707,0.839,0.766,0.869,0.825,0.889,0.87,0.89,0.956,0.882,1
        - 0.29,0,0.305,0.252,0.786,0.379,1,0.496,0.962,0.237,0.925,0.114,0.879,0
        - 0,0,0,0.33,0.295,0.259,0.289,0
      threshold: 30
      contour_area: 10
      improve_contrast: true
    objects:
      track:
        - person
        - cat
        - dog
        - car
        - bicycle
        - motorcycle
        - airplane
        - boat
        - bird
        - horse
        - sheep
        - cow
        - elephant
        - bear
        - zebra
        - giraffe
        - skis
        - sports ball
        - kite
        - baseball bat
        - skateboard
        - surfboard
        - tennis racket
      filters:
        car:
          mask:
            - 0.308,0.254,0.516,0.363,0.69,0.445,0.769,0.522,0.903,0.614,1,0.507,1,0,0.294,0.003
            - 0,0.381,0.29,0.377,0.284,0,0,0
    zones:
      Main_Zone:
        coordinates: 0,0,0,1,1,1,1,0
        loitering_time: 0

detectors: # <---- add detectors
  ov:
    type: openvino
    device: GPU

model:
  model_type: yolo-generic
  width: 320 # <--- should match the imgsize set during model export
  height: 320 # <--- should match the imgsize set during model export
  input_tensor: nchw
  input_dtype: float
  path: /config/model_cache/yolov9-t-320.onnx
  labelmap_path: /labelmap/coco-80.txt

version: 0.17-0


#go2rtc:
#  streams:
#    front_cam:
#      - ffmpeg:rtsp://user:pw@<ip-addr>:554/cam/realmonitor?channel=1&subtype=0&unicast=true&proto=Onvif
#    baby_cam:
#      - ffmpeg:rtsp://user:pw@<ip-addr>:554/cam/realmonitor?channel=1&subtype=0&unicast=true&proto=Onvif

That CPU has UHD Graphics 750 which is newer than mine which has 730. Should work quite nicely.

Are you using Proxmox, too?

Sounds like LXC is the way to go to pass a Coral through. Not sure why it’s so flaky with the Debian VM.

I’ll keep an eye out for that. So far the Inference Speed is holding stead at 8.47ms.

Are you using OpenVINO with the onboard GPU, or CPU? I think it works with both so you need to make sure it’s using the GPU if possible.

That’s good to hear. That reinforces my suspicion that my problems were caused by passing it through to the virtual machine using Proxmox.

You might be interested in trying to enable the YOLOv9 models. The developer claims they are more accurate, and so far I’m tempted to agree.

You seem a bit more network savvy than me. All I could figure is the Frigate integration (also HACS for me) talks to Frigate and asks it where to get the video from. If go2rtc is enabled in Frigate, the integration tries to stream from go2rtc. Without my Docker stack being in host network mode, it wouldn’t work for me.

With no go2rtc, the Frigate integration asks Frigate where to get the stream, and it’s told to get it from the camera from what I can tell.

All just guesses on my end. Hopefully I don’t sound too sure of myself because I’m not really sure.

You’re right. I’ve always just typed two hyphens and called it good but technically it should be one long dash.

An em dash is --, two dashes. It’s a way to break up a sentence – sort of like a comma.

Apparently AI uses them a lot.

I had a similar progression except I haven’t heard of Dockhand until now. I’ll give it a look.

1. Portainer is practical, but I switched to Dockge and have been much happier with it. It doesn’t have all of the bells and whistles, but the simplicity makes the workflow much better for me. Give both a try!
2. FreshRSS for RSS feeds, Lubelogger for tracking car (other other things) maintenance, Nginx Proxy Manager for a reverse proxy (or Caddy which is also popular). Whatever you fancy!
3. Not sure.

Regarding domain name, use what you have. It’s super easy to change domain names, and some people do it regularly to take advantage of 1st year sales. Basically all you have to do is transfer your DNS entries to the new domain, and update your reverse proxy entries.

Definitely put everything behind a reverse proxy. I followed this advice so I don’t even have to expose ports using Docker. Everything runs through the reverse proxy, and Dockge makes it trivial add each container to the same network.

I’ve been in a similar chamber (Hypobaric instead of nitrogen). I remember everything because I was a chicken and put my mask back on at the very first sign something was off. One of the other participants couldn’t /wouldn’t put their own mask back on. It’s interesting to witness.

Yeah… I hesitated to hit “submit”, but figured the courts would rule in our favor because courts have a good sense of humor!

They are also very noisy, so a basement location might not be enough to suppress the humming and yelling from reaching your living areas.

There’s also no accountability for companies and it has been like that for way too long. Look at Starbucks… some stores unionized so they just closed the stores and fired everyone. Completely illegal, but no consequences for the company. They succeeded in scaring the rest of the baristas, though, so mission accomplished.

This is a meme community, so it’s time to get serious!

This happened around 6 or 7 years ago. The company in question only has two work groups that are unionized – Pilots and Dispatchers. Mechanics, Flight Attendants, Ground Service, etc. are not unionized.

Flight Attendants have attempted to unionize many times, but the vote always fails.

The poster included in this post was for Ramp workers – the people who load baggage, marshal the planes into the gate, fill the potable water, etc. That vote ultimately failed, but these posters were only a small reason why. In my opinion, the biggest reason that other work groups don’t want to unionize (they absolutely can, nothing is stopping them) is profit sharing.

Years ago the pilot union negotiated an extremely excellent profit sharing agreement, and it was negotiated for pilots only. Depending on the amount of profit for the year, employees can expect 10%-%20 of their yearly income paid in a lump sum. The company in question is typically very profitable (I can already see the “profit should be illegal” type of comments coming, but please spare me. I’m just trying to explain how it works).

Over time, other work groups started to catch wind of how much profit sharing pilots were getting. Naturally this sparked talk of unionizing in other work groups, so in order to calm things down the company extended the same profit sharing to all workers, not just the pilots.

This sort of reversed the desire to unionize for a lot of people (I disagree with them, but this is their thinking)… Now if the ramp personnel do unionize, they’d have to negotiate their own profit sharing as they would be excluded from the company wide payout. That’s not to say they couldn’t negotiate to keep the profit sharing, but the fear is real and people don’t want to lose the big fat checks that come almost every year.

In summary, the workers aren’t unionized but the company pays a lot of money to them to keep it that way. Would they be better off long term if they unionized? Yes, of course. But this poster, as ridiculous as it is, is not the only reason that work groups aren’t voting in unions.

Here’s a link to the AFA page talking about it a little bit https://deltaafa.org/news/profit-sharing-2025

Ah, maybe the max was 20GB for zip. I’d just do the max available for zip.

Do it again, but select 50GB chunks. This will produce fewer files.

Use immich-go to do the importing.

I’ve never had to restore a backup (yet), but to me this is the best feature of Restic.

I used Duplicati for a while (I think it was Duplicati, not Duplicacy) and although the backups seemed to work, I kept reading about people having trouble during the restore process.

Restic is a slight chore to get set up with the environmental variables, figuring out which directories to “–ignore”, etc… but man once it’s set up it’s just great.

I’m not sure I fully grasp what you want, but Restic is excellent. I use a cronjob to back up on a schedule. It’s command line only. I think there’s a tool to make it a GUI but I haven’t tried it. They have a Docker image available but it’s weird, you have to pass commands to it, it runs, then shuts down when it’s done. I love Docker but that didn’t quite work for me.

I use Backblaze B2 for storage, but any S3 will do. Restic supports all sorts of storage targets.

Credentials and things go in an .env file, or you can put everything into the command line every time.

When it’s time to restore things, you can fricken mount the whole backup you want and browse the files, copy and paste what you need, etc. That part is really cool to me.

Backblaze is $5 or $6 USD per TB per month, so 500GB will be about $36USD a year.