Recent content by GavinCampbell

I have 4 of them. They work. Anything specific you want to know? Some generic notes: They are onvif compliant but don't expose all the capabilities. I think just the stream but not the sensor. Has an open api, can be integrated with things like Home Assistant for light control. Their app...

Does anybody know if the docker GPU tags have changed or are they just delaying updating it? Currently I use the tag GPU to install the GPU version of the docker but that hasn't been updated in 4 months. The documentation still says to use this. I see that there are a bunch of other GPU tags...

Just got the updated docker version this morning. At first I had a few issues but after deleting the old "extra" parameters in the docker and resetting the config folder, it is working perfectly. I get between 30-40ms now (down from 50ms) using YOLO so its getting faster.

Just upgraded to test. No issues here. Maybe just double checked the network settings. Ensure its binded to the right adapter etc.

I have noticed this too and this is why I've been using it now as my primary tool. I just noticed that one of the issues I pointed out with environment variables in linux dockers for disabling modules has been mentioned in the document as being fixed in 1.5.7 (when its released). It was great...

Whenever you want to pass throught he vidio card to the docker you need to add the following variables and extra parameter. NVIDIA_DRIVER_CAPABILITIES = all NVIDIA_VISIBLE_DEVICES = your gpu id like "GPU-abcdefg-abcd-abcd-abcd-abcdefghijk" and add "--runtime=nvidia" under extra parameters in...

For the group as well. I am using the same sample file (pexels-maria-orlova-4947381.jpg). I have it running in an unraid docker that has 7 cores (shared with other dockers) assigned. My GPU is a NVIDIA GeForce GTX 1060 6GB and can see that the docker is using about 3.5GB of memory. 197.6...

I have the same card. Looking to upgrade it though because of the memory. I'm eyeing a 6GB card now. With the older version of deepstack every custom model used ~900MiB of memory. With the latest version of deepstack I noticed it was bumped up to 1400MiB, so I started having problems when...

Happened to one of my cameras. I fixed it by going into the foscam NVR software and then the settings for the camera. Under video -> video adjustments, it hit Default and then save. It reset whatever broke and the video was back to normal. I have 4 of these, but it only happened to 1...

I've seen all these problems trying to get the latest version of deepstack working. Its obviously something specific to our setups causing these problems as others seem to be working. I've seen the "no object detected" error as well as the "timeout" error. With the latest version I noticed...

That sucks. I really hope they figure it out. The whole zwave 700 has been such a mess since its release. I've seen reports from people with issues with just a couple devices. I took me a long time to get my network to run reliable and even still something like a zooz vibration sensor can...

The issue with the 700 series controllers has been finally acknowleged by SiLabs as a bug. The community has been trying to convince them since last year there were issues with it going offline under heavy loads. They released two update to the zwave sticks in January. 7.17.1 was the first...

I noticed that too. It was changed in the latest ios update. I just got used to using that too and it changed.

I know a couple months late.. but I don't think the PIR can trigger anything. I've been trying to figure that out as well. Even when I turn on the PIR setting though it just triggers too much. Its way to sensitive for some reason. I even tried mixing it up with Onvif detection but its not...

Correct. And even more confusing is that the role can jump around based on which of the cameras connected first I guess. As a user, I was just editing the copy and expecting it to work. As a quick fix maybe a note that the setting needs to be applied to all copies for it to work reliably...