ZoneMinder Forums

Yes, read the docs.

I had read all the guides I could find and they were very helpful but a time a little confusing / contradictory - however I now seem to have face recognition working based on these results: If you have time, please specifically point out which parts are contradictory and I'll see if it needs fixing...

1. Don't know if you are missing anything. You've posted logs for training, not for detection. Is face recognition being invoked for detection?
2. Make sure you have read this completely and are using use_sequence=yes. ml_sequence is key here.

Answer to question 2 - tried that no joy Then you need to solve that problem. If you can't access it using your web user acct. then it won't work. chown it 2. In the secrets.ini I get confused by what is meant by PORTAL - is this the external FQDN or the internal IP address of the server ? I actual...

mlapi doesn't come with a generic service activation. You'll have to write or customize your own. The mlapi.service file I provide is one that works for me (Ubuntu 20) and the install_as_service.sh script set its up (which explains the disclaimer in the script). So I am not sure how you have defined...

Sounds good, if it works, please post details on what you did to make things work so I can add it to the FAQ
If it doesn't work, please go back to my questions and answer them precisely (questions 1-3).

That's fine.

I've committed a fix, if you'd like to test.
https://github.com/pliablepixels/zmeven ... f3ae2a3803

1. Does /etc/letsencrypt/live/PORTAL/fullchain.pem exist? 2. If it does exist, does sudo -u www-data ls -l /etc/letsencrypt/live/PORTAL/fullchain.pem work? (replace www-data with your web user) 3. What is the exact command you used to start the ES manually and does it work in daemon mode? (i.e. when...

OR, we could do the smart thing and look at the code that draws the polygons, where we see that: a) there is no relevant logging around the code that draws the polygons on the image (pyzm/helpers/utils.py draw_bbox, or the place in zm_detect.py it is called from) b) you get the newh,neww of the ima...

Yup so it seems. As always, logs.

For future reference, when you install Ubuntu 20, it automatically enables LVM unless you choose to disable it. When it is enabled, it is by default not configured to take up full disk space. In your case, it is 200G and that is then where ZM is installed, so it sees a total of 200GB. I found out th...

Meeko wrote: ↑Sat May 29, 2021 8:11 am
Where do I start looking?

The logs files when this issue occurs. Both in zmNinja and ZM logs.
https://zmninja.readthedocs.io/en/lates ... ort-errors

Okay, I think I've fixed it now - I did a few runs by invoking zm_detect with and without '--reason' as well as different values - and looks like the original polygons are being reset now at each invocations on the mlapi side. (https://github.com/pliablepixels/mlapi/commit/845cf704a2f3ba221cd6a2bd09...

Thanks for the detailed logs. I think I know what is going on. When your reason is "Motion porch" and your zone name is "porch", I am replacing the reason with "Motion_porch" and then looking for a whole word "porch" in it, which will fail (as I just removed t...

Compare mlapi debug logs between the version that reports nothing vs. the one that does.