ZoneMinder Forums

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.

This is an interesting one. You're right, the new model goes all over the place. Interestingly when I first ran it, it came out perfectly as a dog, but then I realized I had my config as: a) First run TPU at 0.6 confidence b) Then run YoloV4 at 0.3 confidence So this filtered out all the boxes in yo...

Can you link to the original image without the boxes so I can test?

VicThor wrote: ↑Thu Jan 07, 2021 11:55 pm It seems to work much better than previous library and models.
However it creates way too many polygons for the same object.

Can you post an example? I'm not seeing that issue of multiple polygons compared to the old model.

default config for new detection sequence makes it to analyse faces all the time, so my cpu utilization sky-rocketed, i've added to face model config of ml_sequence "pre_existing_labels": person and now it's back to normal The default config is a sample. If you don't want face, simply rem...

Hello - I updated to ES 6.1.5 and seem to be having some struggle with object detection. This was working fine previous to 6.1.5 and I understand the structure of objectconfig.ini has changes but believe I've made correct/updated changes leveraging ml_sequence. For object detection; using: object, ...

Magic919 wrote: ↑Wed Jan 06, 2021 11:38 am Contradition regarding the default for use_sequence. The config file says

Code: Select all

 NEW: If enabled (default = no), we will use ml_sequence and stream_sequence

Readthedocs says

Code: Select all

When use_sequence is set to yes (default)

fixed.

You seem to be using an old version. The new stable versions use the new libraries.
And I just switched to the new model - It seems to be faster, but not sure it is any better

That would usually mean your iPhone cgi-bin settings are wrong (zmninja settings). Compare closely to android.

whoops - fixed in 0.3.19 pyzm

I'm in. Have pulled and installed latest. No othe changes, just a restart of ZMES. Thanks! I've added the following note to Part I - when you test with no changes: Specifically, make sure all your objectconfig changes you might have implemented earlier, like monitor specific waits, detection_patter...