I figured it out. Change your docker image to deepquestai/deepstack:noavx (instead of :latest) and it'll then work after you input your key into the web interface.
[tool] [tutorial] Free AI Person Detection for Blue Iris
- Thread starter GentlePumpkin
- Start date
You're correct, as long as you have 'Send Errors and Warnings to Telegram' selected under Settings of AI Tool it should work regardless of Deepstack communication.
A couple questions:
-What's the error you're getting after 2 minutes when putting the Deepstack IP without http://?
-Are you able to send your telegram bot a message manually?
-Like devastator, are you able to reach your DeepQuestAI Server with a web browser? In your case, '192.168.0.113:85'?
Can't get it to run. DeepStack is runing on another host for me. Running this python script (copied the url from the AI tool), runs fine
Code:
import requests
image_data = open("test-image3.jpg","rb").read()
print("test")
response = requests.post("http://192.168.0.145/v1/vision/detection",files={"image":image_data}).json()
print(response)
for object in response["predictions"]:
print(object["label"])
print(response)Ok, I fixed it in the code.
@GentlePumpkin It appears I am not able to create a new branch to publish the fix and create a merge request. Do you need to give me access ?
@GentlePumpkin It appears I am not able to create a new branch to publish the fix and create a merge request. Do you need to give me access ?
motoolfan
Getting the hang of it
I'm very tempted in giving this a try, How's it working for you?
thesleepy_slee
Young grasshopper
- Jan 3, 2016
- 67
- 6
Code:
[29.05.2020, 22:53:05.093]: Starting analysis of C:\BlueIris\aiinput/Z5AI.20200529_225305049.jpg
[29.05.2020, 22:53:05.126]: (1/6) Uploading image to DeepQuestAI Server
[29.05.2020, 22:54:45.151]: System.Threading.Tasks.TaskCanceledException | Une tâche a été annulée. (code: -2146233029 )
[29.05.2020, 22:54:45.158]: ERROR: Processing the following image 'C:\BlueIris\aiinput/Z5AI.20200529_225305049.jpg' failed. Can't reach DeepQuestAI Server at 192.168.0.113:85.
[29.05.2020, 22:54:45.170]: ERROR: Could not send text "[29.05.2020, 22:54:45.158]: ERROR: Processing the following image 'C:\BlueIris\aiinput/Z5AI.20200529_225305049.jpg' failed. Can't reach DeepQuestAI Server at 192.168.0.113:85." to Telegram.
[29.05.2020, 22:54:45.223]: ERROR: Could not upload image C:\BlueIris\aiinput/Z5AI.20200529_225305049.jpg to Telegram.
[29.05.2020, 22:54:45.229]: ERROR: Could not send text "[29.05.2020, 22:54:45.223]: ERROR: Could not upload image C:\BlueIris\aiinput/Z5AI.20200529_225305049.jpg to Telegram." to Telegram.Of course, using the same bot for many other purposes, checked URL multiple times.
Yes, both in the same VM, but also on other PC.
Recently the tool has been working for a while and then stopping. There are no error notices or anything to indicated that something is wrong.
When I start the tool it processes images without issue. After a while I'll notice that there are no recent alerts. When I check the tool I see that it has stopped processing images.
Below is a screenshot of my log. It was processing fine until 06:30 this morning. Then there are 5.5 hours of nothing and then it's "Loading object rectangles".
Any idea why this is happening and how to fix it?
When I start the tool it processes images without issue. After a while I'll notice that there are no recent alerts. When I check the tool I see that it has stopped processing images.
Below is a screenshot of my log. It was processing fine until 06:30 this morning. Then there are 5.5 hours of nothing and then it's "Loading object rectangles".
Any idea why this is happening and how to fix it?
have you tried blue Iris->settings->Web Server->Advanced->
uncheck "Use secure session keys and login page"
the Limit IP Addresses:-> ^127.0.0.1 or +127.0.0.1
is no longer working don't know how long its been broken.
Using an i5-3330, DeepStack is unfortunately a bit too slow for me. I have ordered a Coral USB Accelerator. According to some videos, I should be able to process ~30 FPS with it.
Will keep you posted on the progress !
Will keep you posted on the progress !
Interesting... the documentation I read said to do it, didnt know we didnt need it.
there was no file unrecognized file, it was definitely 3 camera files were corrupt.
pmcross
Pulling my weight
Duplicate cameras are only needed if you don't want to have your BI alert view to be cluttered with false alerts that didn't get triggered. Having duplicate cameras keeps the alert view much cleaner.
There are some perks if you use AI clone camera and the original.
In the AI camera where I can have a lot of false positives, I don't set any Alert actions (on Alert, or on Reset).
The Original camera is triggered by AITool after it meets confidence criteria ,
So I have higher confidence this is a notification I really want to know about
i've setup MQTT and HTTP (for IFTTT) actions in camera settings->Alerts->Actions-> On Alerts On Resets
i've successfully set MQTT Topic, and sometimes even made IFTTT http web request
to communicate directly or in-directly to my Home Assistant there is an actual Alert, the Alert right now
go to an echo DOT announcement via Home Assistant.
The original Cameras via MQTT behave like accurate motion sensors in Home Assistant.
The trick is getting the Motion detection rules just right on the AI camera so it at least fires when there is a real activity
even if it includes some false positives, but that is ongoing.
if you are not planning to use Alerts then you can probably skip Cloned camera's
I had that happen once about a month ago. I had backups so just copied them in to the camera folder. If I recall all the corrupt files were showing as a different size to the ok ones so they were easy to spot.
I've been playing with this and have identified what looks like a bug in the masking implementation. I think occurrs when I create multiple mask areas in close proximity to one another and Deepstack detects an object across the two masks.
When sending a series of test images from BlueIris (Trigger now) some will experience the error and some won't. Those that experience the error won't show in the AI Tool history and will leave an error in the log
Has anyone else had the same error?
When sending a series of test images from BlueIris (Trigger now) some will experience the error and some won't. Those that experience the error won't show in the AI Tool history and will leave an error in the log
[01.06.2020, 21:18:38.356]: System.ArgumentOutOfRangeException | Index was out of range. Must be non-negative and less than the size of the collection.
Parameter name: index (code: -2146233086 Has anyone else had the same error?