You will need to configure your network to allow your BobPC 192.168.1.202 see BI machine 192.168.50.10. I do not use dual nics so you need to find out how to do that.
CodeProject.AI Version 2.0
- Thread starter MikeLud1
- Start date
Mike,
Ive reinstalled CUDA 11.8 and updated cuDNN to v8.9
I got GPU now working for YOLOv5 6.2, but LPR 2.7.5 has no option for GPU.
I tried clearing the browser cache and same.
EDIT: Under LPR info there is a line that says CanUseGPU False. Is there a way to edit this to say true? maybe that would work
Ive reinstalled CUDA 11.8 and updated cuDNN to v8.9
I got GPU now working for YOLOv5 6.2, but LPR 2.7.5 has no option for GPU.
I tried clearing the browser cache and same.
EDIT: Under LPR info there is a line that says CanUseGPU False. Is there a way to edit this to say true? maybe that would work
No it doesn't show on the dashboard. I go to the Install Modules tab and it won't install manually... "Call Failed" error. BTW, "Mesh" doesn't show up either. Maybe my GPU or CPU is too old?
fenderman
Staff member
- Mar 9, 2014
- 36,892
- 21,407
Threw 2.4.5 RC1 onto a BI system (previously running Deepstack)..basic setup with only cpu...working fine so far.
The whole idea of dual NIC is that the main net shouldn't see the cameras network, other than BI itself, I think? BI is on the 192.168.1.xxx network, the cameras are on .50.xxx Both pc's see each other in explorer on the .1.xxx net. CPAI says "active address" is the .50, but no idea why or how to change that... hopefully someone can chime in and advise... thanks
Are you using the current version of CP.AI v2.4.5 and if so did you follow the steps in the below post.
CodeProject.AI Version 2.0
I learned this lesson a long time ago but threw caution to the wind today. Yolo!!! Looking forward to hearing if this new 2.4.5 RC1 works out for you, as it seemed from your previous post that you were having trouble with the 2.3.4 release.
Yes.Are you using the current version of CP.AI v2.4.5 and if so did you follow the steps in the below post.
CodeProject.AI Version 2.0
I learned this lesson a long time ago but threw caution to the wind today. Yolo!!! Looking forward to hearing if this new 2.4.5 RC1 works out for you, as it seemed from your previous post that you were having trouble with the 2.3.4 release.ipcamtalk.com
I updated cuDNN to v8.9 and got Yolo to recognize GPU but not LPR
Try using the Object Detection (YOLOv5 .NET) module instead of the Object Detection (YOLOv5 6.2) 1.7.5 module. The Object Detection (YOLOv5 .NET) module will use the iGPU.
I notice under LPR Info there is a line that says CanUseGPU False
GPU: NVIDIA GeForce GTX 1070 Ti (8 GiB) (NVIDIA)
Here is install log:
2023-12-16 18:56:25: ======================================================================
2023-12-16 18:56:25: CodeProject.AI Installer
2023-12-16 18:56:25: ======================================================================
2023-12-16 18:56:26: General CodeProject.AI setup
2023-12-16 18:56:26: Creating Directories...Done
2023-12-16 18:56:26: GPU support
2023-12-16 18:56:26: CUDA Present...Yes (version 11.8)
2023-12-16 18:56:26: ROCm Present...No
2023-12-16 18:56:27: Reading ALPR settings.......Done
2023-12-16 18:56:27: Installing module License Plate Reader 2.7.5
2023-12-16 18:56:27: Installing Python 3.7
2023-12-16 18:56:27: Python 3.7 is already installed
2023-12-16 18:56:31: Creating Virtual Environment (Local)...Done
2023-12-16 18:56:31: Confirming we have Python 3.7 in our virtual environment...present
2023-12-16 18:56:35: Downloading ALPR models...Expanding...Done.
2023-12-16 18:56:35: Copying contents of paddleocr-models.zip to paddleocr...done
2023-12-16 18:56:35: Installing Python packages for License Plate Reader
2023-12-16 18:56:35: [0;Installing GPU-enabled libraries: If available
2023-12-16 18:56:36: Ensuring Python package manager (pip) is installed...Done
2023-12-16 18:56:42: Ensuring Python package manager (pip) is up to date...Done
2023-12-16 18:56:42: Python packages specified by requirements.windows.cuda11_8.txt
2023-12-16 18:57:09: - Installing PaddlePaddle, Parallel Distributed Deep Learning...(âœ”ï¸ checked) Done
2023-12-16 18:57:45: - Installing PaddleOCR, the OCR toolkit based on PaddlePaddle...(âœ”ï¸ checked) Done
2023-12-16 18:57:48: - Installing imutils, the image utilities library...(âœ”ï¸ checked) Done
2023-12-16 18:57:48: - Installing Pillow, a Python Image Library...Already installed
2023-12-16 18:57:49: - Installing OpenCV, the Computer Vision library for Python...Already installed
2023-12-16 18:57:50: - Installing NumPy, a package for scientific computing...Already installed
2023-12-16 18:57:50: Installing Python packages for the CodeProject.AI Server SDK
2023-12-16 18:57:52: Ensuring Python package manager (pip) is installed...Done
2023-12-16 18:57:54: Ensuring Python package manager (pip) is up to date...Done
2023-12-16 18:57:54: Python packages specified by requirements.txt
2023-12-16 18:57:55: - Installing Pillow, a Python Image Library...Already installed
2023-12-16 18:57:56: - Installing Charset normalizer...Already installed
2023-12-16 18:58:00: - Installing aiohttp, the Async IO HTTP library...(âœ”ï¸ checked) Done
2023-12-16 18:58:02: - Installing aiofiles, the Async IO Files library...(âœ”ï¸ checked) Done
2023-12-16 18:58:04: - Installing py-cpuinfo to allow us to query CPU info...(âœ”ï¸ checked) Done
2023-12-16 18:58:05: - Installing Requests, the HTTP library...Already installed
2023-12-16 18:58:10: Self test: Self-test passed
2023-12-16 18:58:10: Setup complete
Installer exited with code 0
The install log look all normal for CUDA11.8 install. What happens if you try Enable GPU.
