Search results
-
W
License Plate Setup
Just to highlight this a little more-- his codeproject.ai under the "mesh" had vision/alpr but not image/alpr. I think Blue Iris might use that? We just added a route.... { "Name": "License Plate Recognition (YOLO11 .NET)", "Route": "image/alpr", "Method"... -
W
Jetson Orin Super Nano
I am going to keep the Jetson exclusive use for CP.AI. I might get a second for mucking with. I also got a 16 Gb Raspberry pi with a Hailo 10 board. -
W
Jetson Orin Super Nano
How are the speeds? This platform is perfect for CP.AI... -
W
Jetson Orin Super Nano
Ok, I pushed it all to docker hub. If you do a docker pull wpiman/codeprojectai-jetson:latest the face detection will be there. Seems to run pretty fast I guess with the CUDA. -
W
Jetson Orin Super Nano
Yep. It should all be accelerated on there. Does it not default to that? -
W
Jetson Orin Super Nano
Ok, I managed to get it running here too. I was able to use CUDA too.. though not sure how much it actually helps here. I'll put it out later today. -
W
Jetson Orin Super Nano
I don't use it for Face Detection but I will try to add it this week. What sort of object detection times are you getting? Did you upgrade it to the Super Nano? Make sure your power mode in MAXN_SUPER. mike@JetsonOrinNano:~$ nvpmodel -q NV Power Mode: MAXN_SUPER 2 -
W
New CodeProject.AI License Plate Recognition (YOLO11) Module
https://hub.docker.com/repository/docker/wpiman/codeprojectai-jetson/general The Docker file I built starts with a Jetson Image which is ARM only. I tried to start it on my x86 Linux and it died a quick death. So you don't have a CUDA GPU on that system? I actually have a a x86 with Linux... -
W
New CodeProject.AI License Plate Recognition (YOLO11) Module
I don't know how to say this other than "kind of". I took the ONNX file his directory and got it running in docker. What is your setup? -
W
New CodeProject.AI License Plate Recognition (YOLO11) Module
So those changes I made worked for a bit.... and then went to crap. I have 3 clones of the camera-- One -> original ALPR on my Linux NAS-- works great.. but slow on my Linux CPU box. Two -> Mike Lud Yolo 11 ALPR-- windows/CUDA... worked on blue IRIS and then broke. Works fine on the server... -
W
Jetson Orin Super Nano
Ok, so just adding one more thing here. The board comes in 15W mode when shipped. I just learned you can put it in "SUPER" mode which increases the speed and the wattage to 25 Watts. I am now running TWICE the speed of the 3090 at 25 watts Max. My ALPR reads are 67 ms round trip 33 ms... -
W
New CodeProject.AI License Plate Recognition (YOLO11) Module
I tried that... I think I got it working again.. Make a couple of local changes... modulesettings.json (two fixes): - Module ID key renamed ALPRYOLO11 → ALPR — Blue Iris seems only recognizes the standard ALPR module ID - Route command renamed detect → alpr — Blue Iris validates the... -
W
Jetson Orin Super Nano
Ok, so I don't think anyone else is using this-- and probably doesn't care.. but I had the original 3.3.4 ALPR running with the CPU. I took Mike's Yolo11 ONNX file and with the help of my friend Claude, I managed to get the ALPR working with CUDA acceleration. Seems to be beating my 3090 and... -
W
New CodeProject.AI License Plate Recognition (YOLO11) Module
Not sure what is wrong. I can submit some photos and not others??!! Here is the LPR-- old one. Points to my Linux Server. On the clone I point to the local host (unclick override)... Turned off the addition models. If I leave that on, Yolo 5 6.5 complains. -
W
New CodeProject.AI License Plate Recognition (YOLO11) Module
So I have your original ALPR detection running on a Linux server on this camera I call LPR. That works great. I point to that here... It works great. The camera LPROZONE points to the local host which have YOLO 11 for license plates reading. I can read the plates just fine in the explorer... -
W
Jetson Orin Super Nano
So just an update.... I have been playing with this NVIDIA board once again, and I manage to get the CUDA working for the YoloV5 6.2 models. I added the delivery and package models. I tested this photo on a truck in my driveway. The first picture is the Jetson Super Nano. Detects the "bus"... -
W
New CodeProject.AI License Plate Recognition (YOLO11) Module
So I did an uninstall of the plate detector-- reinstalled it and this seemed to go away.. I also installed the Yolo11 object detector but didn't example it. All these modules are supposed to be self contained- correct? 10:27:10:License Plate Recognition (YOLO11): [ValueError] : Error... -
W
New CodeProject.AI License Plate Recognition (YOLO11) Module
Does that method account for the angle? If I set up my camera's for 10 FPS-- can I discount the speed by some amount? Is it linear? So I set this up on my windows machine.. It works maybe 50% or so of the time.. The other half the time I get this message and it says in can't find them... -
W
Acceleration for Built-in AI?
I am not sure getting a different GPU is going to help when 3090 and 5090s aren't cutting it. I think BI uses DirectML which doesn't use CUDA directly so it will bang quite a bit on the CPU. I think I am going to go back to Codeproject which can use Cuda directly. Is it possible to get all the... -
W
Poor AI Detection Speed
Are you enabling certain libraries on some cameras and not others? This was already off for my 3060.- wpiman
- Post #28
- Forum: Troubleshooting
-
W
Poor AI Detection Speed
I am in this exact same boat... Doesn't even seem to touch the NVIDIA card during AI. What is strange is when I replace a video and turn the AI debug on, I do see the GPU usage go up. But during actual running it seems to stay unused. C:\Users\wpima>nvidia-smi Sat Mar 21 20:09:21 2026...- wpiman
- Post #23
- Forum: Troubleshooting
-
W
Blue Iris AI an NVIDIA 3060
I am running Blue Iris 6 with the embedded AI on a Windows Proxmox machine. I have a GeForce 3060 passed through and It was working with codeproject. I can select it in Blue Iris (there are two instance in each). -
W
Blue Iris AI an NVIDIA 3070
I am running Blue Iris 6 with the embedded AI on a Windows Proxmox machine. I have a GeForce 3060 passed through and It was working with codeproject. I can select it in Blue Iris (there are two instance in each). When I get motion, the AI appears to work-- but my CPU usage is skyrocketting... -
W
Full ALPR Database System for Blue Iris!
I am using codeproject AI on a linux docker that does one camera.- wpiman
- Post #1,395
- Forum: Blue Iris Tools
-
W
Blue Iris 6 AI package/delivery
I had an MQTT event that was ONLY firing with the detection of a plate. I removed that-- and this appears to be work?!?! I see it on the alert list. I thought the MQTT event action qualifier applied ONLY to the MQTT action? -
W
Blue Iris 6 AI package/delivery
I have switched over most of my cameras to use BI AI with a 3070. I am able to detect cars and read license plates. I am setting up checking for a "package"... I can see the "package" when I do the AI replay. All is good there. I set the threshold for 71%... This is showing up around 80%... -
W
Full ALPR Database System for Blue Iris!
Those are the post gres commands I wrote. Everything appears to be working with my new command-- just not sure when things got derailed... I like the idea of saving the file. I'll add that and wait for a car.- wpiman
- Post #1,390
- Forum: Blue Iris Tools
-
W
Full ALPR Database System for Blue Iris!
Yeah, I am not sure why the ai_dump stopped working for me. I cloned a camera and one is working with Codeproject and the second ALPR one is working with working with the Blue Iris AI. Both are showing up with that change.- wpiman
- Post #1,387
- Forum: Blue Iris Tools
-
W
Full ALPR Database System for Blue Iris!
So I ran the database command listed above... Still didn't work. I ended up having to change my Blue Iris HTTP alert POST body from: {"ai_dump":&JSON, "Image":"&ALERT_JPEG", "camera":"&CAM", "timestamp":"&ALERT_TIME"}...- wpiman
- Post #1,385
- Forum: Blue Iris Tools