CodeProject.AI Version 2.0

This would get triggered a lot at my place LOL. I notice if I test a sound on BI machine it will use the Mesh Office machine and vice versa.

154.jpg241.jpg
 
  • Like
Reactions: fenderman
I also tested my shop alarm, worked great. I shut off my Mesh server this time and it processed the file on the BI machine. This sound will be very handy once AI sounds are added to BI. Hats off to the CPAI team !

157.jpg
 
Is the new sound classifier able to take a video clip and analyze the sound or would it have to be a sound file?

In other words, could someone export a video clip and run it thru it outside of BI?
 
For people using CPAI and around an i5-6500 era cpu, what kind of system usage are you seeing?
 
So I installed cpu-2.5.0 on my Linux box under Docker. Went great. ALPR and object detection work fine.

On Windows, I installed 2.5 RC4 after removing my old version. I removed the Codeproject.ai directory completely and installed the new one.

I then added the Coral lib and the ALPR one.

When I run the ALPR in the explorer, I add a picture with a place-- it says it finished but the GUI says it timed out initially and now it is says "nothing found".

08:22:14:Object Detection (Coral): Rec'd request for Object Detection (Coral) command 'custom' (...161469) took 74ms
08:20:30:License Plate Reader: Rec'd request for License Plate Reader command 'alpr' (...2d7caf) took 131ms

I am thinking about building a new server running Ubuntu and moving my Coral TPU and maybe getting a newer NVIDIA accelerator and use Docker. I have seen people getting 40 ms for their plate reads.... I'd love to get my setup down to those times.
 
New Release CodeProject.AI v2.5-RC4

v2.5-RC4 Updates

  • Dynamic Explorer UI: Each module now supplies its own UI for the explorer
  • Support for sound audition modules in the explorer
  • Improved dashboard
  • Updated module settings schema that includes module author and original project acknowledgement
  • Installer fixes
  • Improved Jetson support
  • Windows on Arm support

What a breath of fresh air this install is. I've been fighting 2
2.4.6 for the last 2 hours and gave 2.5 a go. Installer worked flawlessly. Instantly receiving request from BI after modules installed. Detection in BI working again.
Very happy customer
 
Hi folks, I'm having trouble getting the delivery and package models to work.

Here are my settings, what am I missing here?

Screenshot 2024-01-16 161449.pngScreenshot 2024-01-16 161529.pngScreenshot 2024-01-16 161548.png

View from inside the AI docker container showing where the .pt files are:

Screenshot 2024-01-16 162625.png

Docker compose for AI

YAML:
version: '3.3'
services:
  ai-server:
    network_mode: host
#    ports:
#      - '32168:32168'
    container_name: CodeProject.AI-Server
    volumes:
      - '/opt/senseai/ai:/etc/codeproject/ai'
      - '/opt/senseai/modules:/app/AnalysisLayer/ObjectDetectionYolo/custom-models'
    image: 'codeproject/ai-server:cuda12_2-2.5.0'
    restart: always
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              capabilities: [gpu]


I've restarted both AI and BI and then testing with a recent clip where a DHL truck was in frame I only get tags for 'ipcam-general' and 'ipcam-animal' with no attempt for delivery.
Screenshot 2024-01-16 162946.png

Is my config incorrect somewhere?
 
Hi folks, I'm having trouble getting the delivery and package models to work.

Here are my settings, what am I missing here?

View attachment 182995View attachment 182996View attachment 182998

View from inside the AI docker container showing where the .pt files are:

View attachment 182997

Docker compose for AI

YAML:
version: '3.3'
services:
  ai-server:
    network_mode: host
#    ports:
#      - '32168:32168'
    container_name: CodeProject.AI-Server
    volumes:
      - '/opt/senseai/ai:/etc/codeproject/ai'
      - '/opt/senseai/modules:/app/AnalysisLayer/ObjectDetectionYolo/custom-models'
    image: 'codeproject/ai-server:cuda12_2-2.5.0'
    restart: always
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              capabilities: [gpu]


I've restarted both AI and BI and then testing with a recent clip where a DHL truck was in frame I only get tags for 'ipcam-general' and 'ipcam-animal' with no attempt for delivery.
View attachment 182999

Is my config incorrect somewhere?
What version of Blue Iris are you on? The current version does not need to find the custom models in a folder it will pull the list from CodeProject.AI API
 
What version of Blue Iris are you on? The current version does not need to find the custom models in a folder it will pull the list from CodeProject.AI API

I'm on 5.8.4.2....

going to be 5.8.4.3 in a few minutes because I live on the edge :headbang:

I removed the file path, but no change in what model BI is using

Screenshot 2024-01-16 181248.pngScreenshot 2024-01-16 181322.png
 
Last edited:
@MikeLud1

Made a few changes based on your recommendations and more details from the code project installation steps.

I realized my path in the docker config was wrong for the custom modules, I've updated it as below
YAML:
version: '3.3'
services:
  ai-server:
    network_mode: host
#    ports:
#      - '32168:32168'
    container_name: CodeProject.AI-Server
    volumes:
      - '/opt/senseai/ai:/etc/codeproject/ai'
      - '/opt/senseai/modules:/app/preinstalled-modules/ObjectDetectionYOLOv5-6.2/custom-models'
    image: 'codeproject/ai-server:cuda12_2-2.5.0'
    restart: always
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              capabilities: [gpu]

I also updated the names of all the models to be lowercase, I pulled these directly from git and moved them over, would you be able to update the names to be lower case in the git repo please?
Screenshot 2024-01-16 193314.png

I have restarted BI a couple of times, including after renaming the files and restarting AI.

Still no change when analyzing the clip with a DHL truck

Screenshot 2024-01-16 193402.png


Whats the URL for the explorer you're using? According to the documentation it should be at /vision but that's not working for me