[tool] [tutorial] Free AI Person Detection for Blue Iris

i have big problems with clone cams ...

Only 1 from 5 clones cams working ..
4 clone cams lost the "clone setting" no star in the cameraname and i see bitrate in stats .. can i manual set a cam to clone ?? Or need to create a new clone cam ans set up alle settings ??


other problem ip cange from clone master .. when i cahange ip in "clone Master" not changing the clone cam. When i edit the clone cam... the clone cam lost clone setting and i see bitrate


Okay:
Export and Import kill clone cams ..
 
Last edited:
When running the latest fork build... is there any need to run cloned cameras or can you get away with using non-cloned? what is the pros and cons of not running cloned? thanks!
 
joshwah said:
Oh wow, amazing! I wish the first post would be updated to reflect that... i would have had no idea unless i browsed through heaps of pages etc...
Click to expand...

What does one do with the contents in the zip file? Do you literally just delete the existing files in the AITools directory, keep "cameras", and copy the files from the git zip into the existing AITool directory?
 
Getting that weird "[13.11.2020, 06:27:41]: ERROR: Can't write to cameras/history.csv!" error again. Not sure if it's related to the fact that I updated docker yesterday as it seems to have been happening since.

Trying out the GPU version, any issues with this command that folks see?

docker run --restart=always -e MODE=Low -e VISION-DETECTION=True -v localstorage:/datastore -p 81:5000 --name deepstack deepquestai/deepstack:gpu-x4-beta
 
pbc said:
Getting that weird "[13.11.2020, 06:27:41]: ERROR: Can't write to cameras/history.csv!" error again. Not sure if it's related to the fact that I updated docker yesterday as it seems to have been happening since.

Trying out the GPU version, any issues with this command that folks see?

docker run --restart=always -e MODE=Low -e VISION-DETECTION=True -v localstorage:/datastore -p 81:5000 --name deepstack deepquestai/deepstack:gpu-x4-beta
Click to expand...

I think I had the same issue and my solution was to wipe out AIuser folder and start over. Now I only have 5 cams, so was not that bad.
 
First what I want to occur. When Deepstack detects a object per AIuser filter I want Blueiris to trigger push out notification to the blueirs android app and store an alert image in the alert folder. What is not working. the alert image from AIuser in the alert folder. In blue iris if I enable capture alert image, then blue will store an image for every single alert it finds (that is a lot). i would prefer to only store images with objects in them in the alert image. So in AIUser I have the following configured.

but if I disable capture alert image in blue iris, I no longer get images in that folder. Do I have some configured wrong in the screenshot below? Or do you think its some other place? Or maybe I have the wrong expection of this feature.


1605278832475.png

1605278891884.png
1605318285185.png
 

Attachments

  • 1605277673370.png
    1605277673370.png
    25.7 KB · Views: 92
Last edited:
I am currently using deepstack CPU version and want to switch to GPU. I installed an NVIDIA card and drivers, unloaded the docker CPU version and pulled the GPU, but now AItools does not get back a response from deepstack. Do I have to install NVIDIA drivers into docker or do some other form of configuration in addition to just installing the GPU version.
 
@setchells
Code: 
curl -s -L https://nvidia.github.io/nvidia-container-runtime/gpgkey | sudo apt-key add -
distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
curl -s -L https://nvidia.github.io/nvidia-container-runtime/$distribution/nvidia-container-runtime.list |\
    sudo tee /etc/apt/sources.list.d/nvidia-container-runtime.list
sudo apt-get update
sudo apt-get install nvidia-container-runtime

Also make sure you include --gpus all in the docker command.
 
setchells said:
I am currently using deepstack CPU version and want to switch to GPU. I installed an NVIDIA card and drivers, unloaded the docker CPU version and pulled the GPU, but now AItools does not get back a response from deepstack. Do I have to install NVIDIA drivers into docker or do some other form of configuration in addition to just installing the GPU version.
Click to expand...

Are you getting this same error I am (I just did the same thing)?

[13.11.2020, 15:58:57]: ERROR: Processing the following image 'D:\aiinput\Driveway.20201113_155405209.jpg' failed. Can't reach DeepQuestAI Server at .
 
kosh42efg said:
@setchells
Code: 
curl -s -L https://nvidia.github.io/nvidia-container-runtime/gpgkey | sudo apt-key add -
distribution=$(. /etc/os-release;echo $ID$VERSION_ID)
curl -s -L https://nvidia.github.io/nvidia-container-runtime/$distribution/nvidia-container-runtime.list |\
    sudo tee /etc/apt/sources.list.d/nvidia-container-runtime.list
sudo apt-get update
sudo apt-get install nvidia-container-runtime

Also make sure you include --gpus all in the docker command.
Click to expand...

Where does one run linux commands on a windows docker implementation? Powershell doesn't understand curl and sudo commands.

BTW, is there an "idiots guide" to installing from the git? I have 1.67 installed in an AITools directory. The git says to download the zip, unblock it, then "extract it into this directory". I assume "this directory" is the AITools directory. But if I do that, all it does is create a new directory in AITools called "bi-aidetection-master", and doesn't actually overwrite anything.
 
pbc said:
Where does one run linux commands on a windows docker implementation? Powershell doesn't understand curl and sudo commands.
Click to expand...
My bad. To use GPU at all from Docker you'll need to be using WSL with the Cuda build toolkit.

I tried this but failed a while back. My current solution is that I'm running Proxmox with Docker on bare metal, with BI running in a Windows virtual machine. Unfortunately Proxmox doesn't like Nvidia drivers, so I'm working on trying to get it working with Deepstack:GPU. I'll let you know if I succeed.

Windows Subsystem for Linux (WSL) is a Windows 10 feature that enables users to run native Linux command-line tools directly on Windows. WSL is a containerized environment within which users can run Linux native applications from the command line of the Windows 10 shell without requiring the complexity of a dual boot environment. Internally, WSL is tightly integrated with the Microsoft Windows operating system, which allows it to run Linux applications alongside traditional Windows desktop and modern store apps.
Click to expand...
 
kosh42efg said:
My bad. To use GPU at all from Docker you'll need to be using WSL with the Cuda build toolkit.

I tried this but failed a while back. My current solution is that I'm running Proxmox with Docker on bare metal, with BI running in a Windows virtual machine. Unfortunately Proxmox doesn't like Nvidia drivers, so I'm working on trying to get it working with Deepstack:GPU. I'll let you know if I succeed.
Click to expand...

Thanks, pretty sure I installed the WSL with Cuda driver some time ago when I first tried the Deepstack GPU back when it wasn't working so well.
 
  • Like
Reactions: kosh42efg
No idea what's going on at this stage, but nothing seems to be working.

[13.11.2020, 20:22:59]: ERROR: Can't clean the cameras/history.csv!

Is the most recent error I'm getting. If I wanted to start AITools from a clean slate, how do I install something from that git zip file? I.e., if I just deleted my 1.67 AITools directory, do I simply extract the zip file and fine the AITools executable in whatever new directory that extracted folder has it in, and start from scratch setting up cameras?
 
You must log in or register to reply here.
Top Bottom