Recent content by Tygunn
-
Blue Iris and CodeProject.AI ALPR
This is the exact same problem I ran into. First, stop CP.AI. Open an administrator windows shell and navigate to this directory in your CPAI installation: C:\Program Files\CodeProject\AI\modules\ALPR\bin\windows\python39\venv\Scripts\ For background as to what this next step is... -
Blue Iris and CodeProject.AI ALPR
Thanks Mike; downgrading to CUDA 11.8 got YOLOv5 6.2 running with the GPU, but now it seems the LPR module won't install. This is back to the state I was previously. 2024-09-28 15:05:39: Preparing to install module 'ALPR' 2024-09-28 15:05:39: Downloading module 'ALPR' 2024-09-28 15:05:40... -
Blue Iris and CodeProject.AI ALPR
The GPU version of LPR never did work for me; it works quite well on the CPU. The object detection (YOLOv5 6.2) worked quite well on my GPU in the past, but it seems to not like it any more. I am running CUDA 12.4 now though even though I was using the CUDA 11 version in the past. The 2.8... -
Blue Iris and CodeProject.AI ALPR
Is an NVIDIA 1080 too old of a GPU? I've been using CPAI 2.8 and I can't get it to be used for inferences for LPR and general object detection using YOLO. 2.6.5 stopped working for some reason; despite repeated re-installs I could not get LPR to work at all under 2.6.5. -
2.6.5 - can't get the License Plate Reader module to install
To follow up on this. I installed the latest CUDA drivers and installed Cp.ai 2.8. I can now install the license plate module no issue. However as before I can't use the GPU for the license plate module. . I'll take it. At least it works. -
2.6.5 - can't get the License Plate Reader module to install
So, I've tried completely uninstalling CPAI 2.6.5 a few times now and I can't seem to get the ALPR module to install. Here's the install logs for the module: Reading ALPR settings.......done Installing module License Plate Reader 3.2.2 Installing Python 3.9 Python 3.9 is already installed... -
Where did the option in the windows UX to filter for zones go?
Never mind; found it. Right click in clips list.- Tygunn
- Post #2
- Forum: Troubleshooting
-
Where did the option in the windows UX to filter for zones go?
The BI help shows this: I thought it used to be here, but I can't seem to find it. Lol, I must be missing something?- Tygunn
- Thread
- Replies: 1
- Forum: Troubleshooting
-
Codeproject AI and false positives
The dogs have taken flight! I've always wondered by the base image models included parking meters of all things... -
Codeproject AI and false positives
CP.AI seems to think the trees at the sides of my house are people all the time. :) I guess I should train my own model, or just accept it is more creative in seeing faces in the leaves than I am. Ha ha. -
Blue Iris and CodeProject.AI ALPR
How long is your system taking to process the 50 images you're sending to CPAI? As Actran pointed out to me, if the AI is taking too long to process, you may be losing frames in the processing pipeline. The BI manual actually covers this; I bumped up my pre-trigger record time and found things... -
Blue Iris and CodeProject.AI ALPR
Worth a shot I guess. :) I've also considered 24 hr time and a smaller font size. I think I'll still set up my tracking app to pull all inferences not just the first one. Then I can clearly see if I'm getting odd patterns. -
Blue Iris and CodeProject.AI ALPR
Does everyone remove the timestamp from their LPR camera? I recently noticed that the car with plate "PM" was passing by quite a lot and finally figured out what was up: I did notice that the license plate model in YOLO v8 doesn't seem to capture the timestamps. For now I'll just disable... -
Blue Iris and CodeProject.AI ALPR
I'm going to cross-post this from my other thread. I've been unable to use the license plate CP.AI with the GPU since it just stops for no reason. Works GREAT with the CPU only. So I reinstalled the CUDA 11.8 drivers (I guess I hadn't done that and was running 12.X). GPU inference now... -
CodeProject LPR not detecting car because pre-trigger frames don't seem to exist.
I realized I didn't have the CUDA 11.8 drivers/toolkit installed. So I did that; and the GPU does get used: However, the AI sure is hallucinating.. { "api":"alpr", "found":{ "success":true, "processMs":882, "inferenceMs":840...