Recent content by nmbgeek
-
YOLOv8 Model - Person, Vehicle, and Animal
Yes just put ipcamv8s-pva or ipcamv8n-pva in the custom model field. I have always included the list in the to confirm field. I'm not sure if the docs say leaving it blank will fire on everything or not. Regarding the tiny, small, medium, etc in the main AI settings my understand is that it is... -
YOLOv8 Model - Person, Vehicle, and Animal
ipcamv8s-pva or ipcamv8n-pva is the value that would go in "Custom models" each both contain person, vehicle, and animal. If you only want alerts for people and animals in "To confirm:" just put in person,animal I believe you will need to restart YOLOv8 in Code Project web interface and... -
CodeProject.AI Version 2.5
If they have an RTX3060 6.2 should offer much better performance right? Here is another way to try and install.: Run an administrative command prompt and enter cd C:\Program Files\CodeProject\AI\modules\ObjectDetectionYOLOv5-6.2 (assumes default install location for CodeProject) and press... -
CodeProject.AI Version 2.5
The builtin models are the full pre-trained YOLO models with 80 classes and when you set nano, small, medium, etc that corresponds to the model size used. The links there are for v8, but its the same for v5 regarding model sizes and classes. The larger model sizes use more compute and more... -
AI found license plate number but BI ignored it?
Likely not high enough confidence assigned to the result. What does the AI .dat file indicate for the related alert? Hold Ctrl and double click the alert to see the AI analysis. -
Using different model for day vs night?
This should get you started with profiles and schedules. Regarding the Code Project response times - if you have a 3060 make sure you are using either YOLO v5 6.2 or YOLO v8. With v5 on my 3060ti my times were between 60-80ms and on v8 they are usually 30-60ms. There isn't a dark specific... -
CodeProject.AI Version 2.5
MikeLud's ipcam models: CodeProject.AI-Custom-IPcam-Models/PT Models at main · MikeLud/CodeProject.AI-Custom-IPcam-Models ActionNET: Release DeepStack Action Detection - Custom Model v2 · OlafenwaMoses/DeepStack_ActionNET Place the .pt files in "C:\Program... -
CodeProject.AI Version 2.5
Did you delete everything before reinstalling? Also I do notice in the logs it shows "no cuDNN found" at 0:25. -
Can anyone identify the errors/alerts?
Your screenshots only include a small portion of time which doesn't include any errors. That being said I actually emailed this morning because in the desktop app I have been having it turn red sporadically with no errors in the logs for the latest version. Errors and warnings are a lot easier...- nmbgeek
- Post #2
- Forum: Troubleshooting
-
YOLOv8 Model - Person, Vehicle, and Animal
First, thank you @MikeLud1 for the tips and pointers! In Mike's repo there is an ipcam-general model which works great, but I like being able to have animal notifications on a few of my cameras. My model along with the training results can be found here: GitHub - nmbgeek/ipcam-yolo-models... -
CodeProject.AI Version 2.5
Update = From what I can tell whatever setting you start the training with is used for any resumes. yolo task=detect mode=train model=runs/detect/train3/weights/last.pt data=data.yaml epochs=200 imgsz=640 batch=50 patience=10 device=0 cache=disk resume=True Ultralytics YOLOv8.2.92... -
CodeProject.AI Version 2.5
I added the patience=10 previously. When I do batch=-1 it is only using around 60% of my GPU memory. I need 50GB of available RAM to turn on cache so I am going to fill the other 2 slots and that will hopefully be here Saturday. I donated 64GB of RAM from this computer to a proxmox host and... -
CodeProject.AI Version 2.5
Yes GPU Utilization is 100%. I was using a custom yaml basically equivalent to large model with 800 image size because I had some larger pictures. Using the yolov8m.yaml and going back to 640 image size lets me set batch size to 50 and that appears to be using 20GB of 24 and brings the epoch... -
CodeProject.AI Version 2.5
It is python ultralytics. I did bump the image size to 800 since my images are 1280x720 and most of my substreams are the same resolution as well. My batch size is 22 which uses around 22GB of RAM. Ultralytics YOLOv8.2.40 Python-3.12.6 torch-2.4.1+cu121 CUDA:0 (NVIDIA GeForce RTX 3090... -