ZoneMinder Forums

lb-140-82-112-5-iad.github.com (and similar) seems to be a load balancer node of GH. When zmNinja starts, it connects to https://api.github.com/repos/pliablepixels/zmNinja/releases/latest to get the latest zmNinja version available. It looks like this TCP connection is made when that HTTP GET is cal...

Read the logs you posted. There are multiple errors. If you don't want tpu/face, remove them

delete /var/lib/zmeventnotification/zm_login.json

mlapi never had a training command line client. I just added one to master.

Hmm, I'll have to look into this. May not be a quick fix - there is a lot of ugliness in how I handle hidden monitors (this was coded during the days I was learning how to program a mobile app in Angularjs, and I haven't changed it).

Thanks for the note. It's always nice to see folks go the extra mile - source compilation is rife with all sorts of potential issues, mostly around library version mismatches. Glad things worked out for you. If you think there is scope for improving the instructions, I'd welcome a pull request.

zmNinja caches information from monitor list for 24 hours. Try this:

1. zmNinja->Developer Settings: Disable "use API caching"
2.zmNinja->clear API cache
3. kill zmNinja
4. Load zmNinja, go to montage, enable all monitors

As it turns out, this is already enabled. Edited: See https://zmeventnotification.readthedocs.io/en/latest/guides/hooks.html#mlapi-overrides However, I am going to change this - it's messy this way - monitor specific stuff sits in objectconfig while the rest sits in mlapi. I'll have to think of a be...

Fixed in master.

I think I'll have to add per monitor support for mlapi. I'll have to review the code - hope to get to it this weekend

Doing more testing i increased no of processes for cpu and tpu both to 6 (as I got 6 cameras, 3 on mocord) and decreases tpu detection from 0.6 to 0.55 and now it's running mostly coral model, at least during the day. However I noticed some errors in the logs as coral stopped working after a day: /...

You can do that too. Take a look at the docs I linked to above. You can change patterns per model type as well as use most as same model sequence strategy.

Okay. Feel free to post samples.
I have to live life vicariously till I get a new computing environment.

You can inspect the logs for now - that will tell you if Yolo got invoked. In my case, Yolo isn't called much, but your case can be different. show_models worked for me last night - however my server crashed and I can't test till end of Jan (new server will take time to arrive). I don't recall if I ...

Sure. See ml_sequence here https://github.com/pliablepixels/mlapi/blob/master/mlapiconfig.ini whether you use mlapi or not the structure is the same. Also I’ve added more clarifications here https://zmeventnotification.readthedocs.io/en/latest/guides/hooks.html#vs-previous-versions on how this works.