|
YOLOv8 medium is only 100 MB in size, so VRAM shouldn’t be a huge issue until you’re training a new model or running more than a handful of models at a time.
At least in theory. Mike is gonna have better advice in practice.
|
|
|
|
|
I run 25 4-8 megapixel cams on a RTX A5000 VM with 8GB. The card is bored out of its RAm at 1%-5% utilization.
|
|
|
|
|
I have settled on an RTX 3050 6GB. Basically I have come to the conclusion that a modern GPU is better then an old GPU and any GPU is better then no GPU. Go figure. It's kind of self evident.
Thanks for all the info.
|
|
|
|
|
I have not had any success in creating a 2nd instance on my unraid from the app store yet.
Even after giving it a unique name, ports 32170 udp/tcp, paths etc.
Still seems to overide to 32168 and not create any files in data and modules folders.
Even though it is up and running as a second container under docker it seems to be just a duplicate of the 1st instance.
webui does not open
Where am I going wrong?
Thanks
|
|
|
|
|
I see on a second thread you created a second instance on your Windows machine. Is this working for you now? Mesh is intended for multiple servers, not containers on the same server.
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
Hi, I use CP.AI with Blue Iris and after updating to the latest version today, the object detection modules will not load in the dashboard. The error message from the server logs on the dashboard are below. I get the same error if I try YOLO .NET, YOLO 3.1 and YOLOv8.
19:06:59:Error trying to start Object Detection (YOLOv5 6.2) (detect_adapter.py)
19:06:59:Error is: An error occurred trying to start process 'C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\Scripts\python' with working directory 'C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-6.2'. The system cannot find the file specified.
19:06:59: at System.Diagnostics.Process.StartWithCreateProcess(ProcessStartInfo startInfo) at CodeProject.AI.Server.Modules.ModuleProcessServices.StartProcess(ModuleConfig module, String installSummary)
19:06:59:Please check the CodeProject.AI installation completed successfully
Here is the System Info:
Server version: 2.6.2
System: Windows
Operating System: Windows (Microsoft Windows 10.0.19045)
CPUs: Intel(R) Core(TM) i7-6700 CPU @ 3.40GHz (Intel)
1 CPU x 4 cores. 8 logical processors (x64)
GPU (Primary): NVIDIA T600 (4 GiB) (NVIDIA)
Driver: 552.22, CUDA: 12.4 (up to: 12.4), Compute: 7.5, cuDNN:
System RAM: 16 GiB
Platform: Windows
BuildConfig: Release
Execution Env: Native
Runtime Env: Production
Runtimes installed:
.NET runtime: 7.0.18
.NET SDK: Not found
Default Python: Not found
Go: Not found
NodeJS: Not found
Rust: Not found
Video adapter info:
NVIDIA T600:
Driver Version 31.0.15.5222
Video Processor NVIDIA T600
Microsoft Remote Display Adapter:
Driver Version 10.0.19041.3636
Video Processor
System GPU info:
GPU 3D Usage 0%
GPU RAM Usage 576 MiB
Global Environment variables:
CPAI_APPROOTPATH = <root>
CPAI_PORT = 32168
modified 2 days ago.
|
|
|
|
|
Thanks very much for the report. Out of curiosity, what version were you upgrading from?
What happens if you un-install and re-install and of the modules that get these errors?
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
I was using 2.0.8 previously. I get the same error when I uninstall and reinstall any of the modules. I have also tried totally uninstalling and reinstalling the 2.6.2.
|
|
|
|
|
Please try uninstalling 2.0.8 (if you haven't already), then deleting C:\ProgramData\CodeProject and C:\Program Files\CodeProject, then installing 2.6.4.
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
I have uninstalled 2.0.8 already. I'll delete those directories. Do you mean install 2.6.2 or is there a newer version now?
|
|
|
|
|
Apologies, yes. Windows is currently on 2.6.2.
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
Thanks, I tried this and I get the same error.
The message as shown above says: An error occurred trying to start process C:\Program Files\CodeProject\AI\runtimes\bin\windows\python37\venv\Scripts\python
That folder, python37, doesnt contain any files. Is this the issue?
|
|
|
|
|
Yes, it seems CodeProject.AI Server didn't install properly. Let's try this.
- Uninstall the Object Detection YOLOv5 6.2
- Stop the server
- Delete the C:\Program Files\CodeProject\AI\runtimes\bin\windows folder
- Open a command line and navigate to C:/Program Files/CodeProject/AI/modules/ObjectDetectionYOLOv5-6.2 then type
..\..\setup.bat
- Open a command line and navigate to C:/Program Files/CodeProject/AI/modules/FaceProcessing then type
..\..\setup.bat
- Restart the server
- Reinstall modules
Also, there's a switch on the Install modules tab that says, "Do not use download cache." Please make sure that is toggled on. And there's an install verbosity dropdown, please make sure it is set to info.
Thanks,
Sean Ewington
CodeProject
modified yesterday.
|
|
|
|
|
THanks again. When I run the setup.bat this is what I get:
|
|
|
|
|
Thank you. If you remembered to change the verbosity to loud first, can you please share your log for this, from C:/Program Files/CodeProject/AI/logs?
Thanks,
Sean Ewington
CodeProject
|
|
|
|
|
My set up was CPAI on unraid as a container.
Windows on a sff dedicated pc (lenovo thinkcenter i5-3470T)
GPU GTX970 on unraid passed through to the container.
I had a few coral devices, A+E, M2 wifi and usb. Used on frigate
Tried the tpu on cpai last year and it failed miserably.
I have now a set up utilising the tpu with cpai and blueiris very well.
1- windows 10 X-Lite on the i5-3470T. 8GB ram. sata SSD
2- CPAI container on unraid (this can be CPAI on the windows pc also) - my sff has an A+E slot so may experiment.
3- Coral tpu m2 wifi on the asrock B550m board that hosts unraid. Used for my NAS.
4- AITool on the windows pc
5- BI Alert Tab - Confirm Alert with AI UNticked.
6- BI Record Tab - save jpegs to local folder on windows pc
7- AIool server pointing to unraid CPAI
8- AItool folder from the BI path for record jpegs
CPAI_CORAL_MODEL_NAME = YOLOv8
Size: Medium
Inference speeds: 8.6ms
round trips: 15-22ms
All sent to telegram and MQTT for nodered.
Removed my old GPU to reduce power consumption.
So far so good.
AITool was necessary here to finely tune each object (% image size etc)
Hope this helps someone struggling and wants to use a tpu.
12 cameras - 6 recording 24/7
CPU utilizes just 10-12%!
modified 3 days ago.
|
|
|
|
|
For what it’s worth, that sounds like it’s running YOLOv8 medium a bit too fast, so there may be a different model loaded up than expected. But if the results are good, no one’s gonna complain! Also, you should be able to plug in all of the TPUs and it’ll use them all simultaneously!
|
|
|
|
|
That's what I thought. It may well be using the MobileNet SSD Medium but the info says yolov8. Maybe a bit buggy still. Anyways it works and works well now.
I do have the USB tpu plugged in but I have that hosted for my frigate as a back up.
But its switched off.
May well play around with the multi-tpu. Thanks for the tip.
It is a bit unstable when you try to change settings, had to reinstall the module a couple of times.
|
|
|
|
|
Yeah. The downside of the USB one is that it may make the whole system less stable. Hard to say without trying it out, though. YOLOv8 medium works better on two than one, though, so I’d suggest giving it a try.
|
|
|
|
|
Nope it didn't play ball at all.
Added both devices to the container
/dev/apex_0
/dev/usb
Failed to work - even after reinstalling everything.
/dev/usb works on its own but it twice as slow but shows multi-tpu which is odd.
Removed that and readded /dev/apex_0 which as the fastest but would not work with the usb unfortunately.
Possibly if your board had slots for 2 pcie/wifi cards that might work but it did not like the usb and m2 adding to the container paths.
|
|
|
|
|
Huh. Weird. I see no reason why that wouldn’t work. I should just buy my own to test it. I currently have two M2 slots filled and three PCIe slots with dual TPU adapters.
|
|
|
|
|
Let me know how it goes if you test with multiple tpus.
May work if i try them on the dedicated windows pc directly rather than on unraid trying to pass them through to the container.
If I get time I'll try them on the windows (it has an A+E slot).
|
|
|
|
|
I have eight TPUs in my machine, just none of them USB. So I know it should work.
|
|
|
|
|
8??? omg. how does the multi-mode work then?
|
|
|
|
|