CodeProject.AI Version 2.0
- Thread starter MikeLud1
- Start date
Is this what you're looking for?
Please let me know if I miss something or not the right screenshots.
Please let me know if I miss something or not the right screenshots.
Attachments
Everything looks fine, try running a test using Explorer and see what detection time you are getting there. You can also run the Benchmark. When running the first test you should see about 300ms to 400ms and the Benchmark at about 10 operations per a second.
Please see below test results. This is using chrome. Not sure if that makes any difference vs IE
When I was performing benchmark test, I sometimes see "Unable to contact AI server"
When I was performing benchmark test, I sometimes see "Unable to contact AI server"
Can you provide this for us/Mike?
Also, make sure your Anti-Virus/Firewall is not causing issues. I have mine Off on my BI PC. You may want to Turn it Off to test...just not sure what Exclusions are needed with CPAI. When mine was running I Excluded my Blue Iris folders...
Last edited:
What Video Card do you have? I notice the GPU is using Intel HD but showing AMD Radeon Processor. Forgive my ignorance, does Intel use AMD GPU Procs?
EDIT: Actually it looks like you have two GPUs...you may need to turn off the Intel Graphics in your BIOS if you have a Radeon Video Card installed...
EDIT2: Are you running BI on a Laptop?
Intel HD Graphics And Radeon Graphics
Hope you can help me with this one, and help me to understand, I'm not really to AMD stuff. I just would like to ask multiple questions regarding with this matter. I have little understanding with ...
superuser.com
Last edited:
What Video Card do you have? I notice the GPU is using Intel HD but showing AMD Radeon Processor. Forgive my ignorance, does Intel use AMD GPU Procs?
EDIT: Actually it looks like you have two GPUs...you may need to turn off the Intel Graphics in your BIOS if you have a Radeon Video Card installed...
EDIT2: Are you running BI on a Laptop?
Intel HD Graphics And Radeon Graphics
Hope you can help me with this one, and help me to understand, I'm not really to AMD stuff. I just would like to ask multiple questions regarding with this matter. I have little understanding with ...
Will having dual video cards, one built in and one "external" cause these types of issues?
No I'm not using a laptop. I have dell 7050
Not sure I am just observing. If it were me I would turn off the Intel HD graphics...
Here is my thought, of your two GPUs, you would want the AMD Radeon to be the one CPAI uses...
Go to Device Manager and see if both GPU show up. I think you can go into the BOIS and disable the Intel GPU or just delete the device.
CodeProject.AI Version 2.0
Thank you for the info. I made the changes like you suggested. This is my current reaction time now AI: [Objects] car:66% [690,334 1095,485] 5667ms This is far from 6.2 and 17ms May I ask if I am doing anything wrong? I have 2 IPC-Color4K-T and a MINI PTZ. I don't think camera models...
@dubber In addition to @MikeLud1 original advice about "unchecking" main stream, make sure you configured the substream for every camera. That way, CP.AI will use substream image for analysis and will be faster. See screenshot below for example---your camera settings may differ from mine.
Also, uncheck "Static object analysis". Unless you need to check for a parked car, turn off this option. If you have this option enabled, you are telling BI5 to send images to CP.AI at regular intervals, increasing load on CP.AI.
There are other ways to increase AI speed like turning off default object detection and using Mike's custom model like ipcam-general for example.
Also, uncheck "Static object analysis". Unless you need to check for a parked car, turn off this option. If you have this option enabled, you are telling BI5 to send images to CP.AI at regular intervals, increasing load on CP.AI.
There are other ways to increase AI speed like turning off default object detection and using Mike's custom model like ipcam-general for example.
Last edited:
AI: [Objects] car:69% [343,380 785,552] 438ms
0 6/15/2023 4:54:17.147 AM DrivewayRight AI: [Objects] car:57% [735,343 1294,456] 438ms
0 6/14/2023 11:24:12.468 PM DrivewayRight AI: [Objects] car:73% [362,378 783,550] 1351ms
0 6/14/2023 11:18:38.607 PM DrivewayRight AI: [Objects] car:66% [363,379 781,551] 3355ms
I don't think it did
0 6/15/2023 4:54:17.147 AM DrivewayRight AI: [Objects] car:57% [735,343 1294,456] 438ms
0 6/14/2023 11:24:12.468 PM DrivewayRight AI: [Objects] car:73% [362,378 783,550] 1351ms
0 6/14/2023 11:18:38.607 PM DrivewayRight AI: [Objects] car:66% [363,379 781,551] 3355ms
I don't think it did
How can i get CPAI to use GPU instead of CPU, do i need to replace my custom models with ones that support GPU?
I do not have a Nvidia GPU and would like to make use of my Intel iGPU.
I do not have a Nvidia GPU and would like to make use of my Intel iGPU.
Code:
24:20:11:
24:20:11:Module 'Object Detection (YOLOv5 .NET)' (ID: ObjectDetectionNet)
24:20:11:Active: True
24:20:11:GPU: Support enabled
24:20:11:Parallelism: 0
24:20:11:Platforms: windows,linux,linux-arm64,macos,macos-arm64
24:20:11:FilePath: ObjectDetectionNet.exe
24:20:11:ModulePath: ObjectDetectionNet
24:20:11:Install: PreInstalled
24:20:11:Runtime: execute
24:20:11:Queue: objectdetection_queue
24:20:11:Start pause: 1 sec
24:20:11:Valid: True
24:20:11:Environment Variables
24:20:11:CPAI_MODULE_SUPPORT_GPU = False
24:20:11:CUSTOM_MODELS_DIR = %CURRENT_MODULE_PATH%\custom-models
24:20:11:MODELS_DIR = %CURRENT_MODULE_PATH%\assets
24:20:11:MODEL_SIZE = MEDIUM
24:20:11:USE_CUDA = False
24:20:11: