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

shannondalebreaux

Getting the hang of it
Joined
Jun 6, 2018
Messages
82
Reaction score
29
Location
louisana
Didn't think so worth a shot. I guess it could work maybe if it could read license plate .

Sent from my SM-G965U using Tapatalk
 

cjowers

Getting the hang of it
Joined
Jan 28, 2020
Messages
107
Reaction score
36
Location
AUS
Is this true for the Docker version? Wouldn't it just create another container that would be visible in the GUI and easily stopped?
I believe you would see it in the GUI, But some of the mentioned methods of running the deepstack server (powershell) don't use the GUI, so worth mentioning, and important for any method really. I didn't even know there was a GUI for some time :)
 
Joined
Jan 22, 2018
Messages
25
Reaction score
14
I believe you would see it in the GUI, But some of the mentioned methods of running the deepstack server (powershell) don't use the GUI, so worth mentioning, and important for any method really. I didn't even know there was a GUI for some time :)
Every time that I have started a Docker container via Powershell it has shown up in the Docker for Windows dashboard GUI.
 

balucanb

Getting the hang of it
Joined
Sep 19, 2020
Messages
146
Reaction score
23
Location
TX
Every time that I have started a Docker container via Powershell it has shown up in the Docker for Windows dashboard GUI.
I know zero about Docker, check my post history , :) but I do know that it will show up in the dashboard as stated. Just did it yesterday and it is also the only time I have done it!
 

balucanb

Getting the hang of it
Joined
Sep 19, 2020
Messages
146
Reaction score
23
Location
TX
:rofl:
Perhaps, but as someone who has not yet summoned the courage to try Deepstack on Docker for Windows, I appreciate your stepping up and flushing out the issues that I surely will face when I get there.
I feel you man. I am old enough to tell stories about the dark ages...(dramatic music playing) BEFORE TECH.DUM, DUM ,DUM. LOL so while I am reasonably literate regarding tech- the DOCKER thing was a total black hole for me, I didn't and still don't really grasp the whole concept of what it is so I did not want to try it. But now that I have it working I feel better. For what it's worth- Everything you need to know is out there as long as you are willing to ask questions and do the 100 Google searches and reading required...I like most people am pretty lazy and impatient. I just want it all to be given to me in a simple to understand format, sometimes I find that ,sometimes I just Bit$% and Whine but ultimately get it figured out. My fall back is to ask one of my kids, I know I failed if I have to stoop to that LMAO. Best advice I can give you is to make sure you take the time first to look at all the steps, ensure you have meet any prerequisites, then read it all a second time before you start and of course make a back up of everything that is currently working so you can always go back to that while you hit the books before your second attempt!
 

johannp02180

Young grasshopper
Joined
Nov 30, 2020
Messages
39
Reaction score
5
Location
USA
Does anyone also use MQTT to implement this? In UI3, going to alerts, it’s showing all the snapshots and clips that are false alerts. Is this a problem only when using MQTT? I wanted to keep secure session keys and login page.
 

balucanb

Getting the hang of it
Joined
Sep 19, 2020
Messages
146
Reaction score
23
Location
TX
Okie dokie. Believe it or not I am trying...trying SO HARD, to do some custom models for deepstack. I KNOW RIGHT- WTH is this guy thinking?! Seriously here is where I am at and hope someone here is already doing this and can help me.
I have fumbled through the following-
Preparing Your Dataset
Step 1: Install LabelIMG
Step 2: Organize Your Dataset
Step 3: Run LabelIMG
Change Annotation to YOLO Format
Step 4: Annotate Your Dataset
Annotate Your Train /Test Dataset
Cloned the Google Caolb
copied it to my GD, mounted it, uploaded and unzipped my dataset folders.

Now I am stuck. Do I need to create a new cell and run some code or something so it "trains"? I am not seeing any model files or pth files so either I just think I did everything right to this point or just don't understand where to go from here.

As always TIA for any help.
 

Tinbum

Pulling my weight
Joined
Sep 5, 2017
Messages
446
Reaction score
126
Location
UK

douglasfl

n3wb
Joined
May 22, 2020
Messages
2
Reaction score
0
Location
Brazil
Hi,
i am using VorlonCD/bi-aidetection and sending alert on Telegram.

But i only recive the image, te caption that i have setting is not sent on telegram.

Someone whit this issue?
 

Attachments

barnyard

n3wb
Joined
Aug 9, 2020
Messages
24
Reaction score
5
Location
United States
Hi,
i am using VorlonCD/bi-aidetection and sending alert on Telegram.

But i only recive the image, te caption that i have setting is not sent on telegram.

Someone whit this issue?
Which version are you running? That latest version on GitHub has that bug

Sent from my Pixel 3 using Tapatalk
 

Village Guy

Pulling my weight
Joined
May 6, 2020
Messages
291
Reaction score
161
Location
UK
Are you running the AWS piece? How is it working out if yes?
Negative, I'm pretty happy with deepstack for my application. Now it is open source I'm betting that it will become more accurate. From what I have read it would seem that AWS is taking around 1500ms per image to analyseo_O
 
Top