Search results
-
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... -
-
CodeProject.AI Version 2.5
It is certainly going a little slower than I thought it would. Each epoch was taking approximately 54-55 minutes. Since the COCO dataset has so many person instances compared to anything else I have pruned 50% of their images that only contained a person object (after pruning out all of the... -
CodeProject.AI Version 2.5
@MikeLud1 I have taken the COCO2017 train/val datasets and pared it down to only images and labels with car, truck, motorcycle, bicycle, person, cat, dog, animal. Then added about 400 images from my cameras with those items labeled plus trashcan for garbage day reminders from Home Assistant... -
A Plead for Help With Random App (BI) Crashing
Also did you do the Windows 10 download directly from Microsoft using the Media Creation Tool? You don't want to use a version from torrent or third party that could have been altered.- nmbgeek
- Post #11
- Forum: Troubleshooting
-
A Plead for Help With Random App (BI) Crashing
If there is a monitor connected and turned on then that should be fine. You had just mentioned you were running it headless which means no display. Regarding the Windows activation, not being activated isn't an actual problem. There is a difference between being licensed and activated. Your...- nmbgeek
- Post #10
- Forum: Troubleshooting
-
A Plead for Help With Random App (BI) Crashing
If you have a spare monitor I would leave it connected and see if you notice improvements. If you do see improvement and you don't want to be powering a monitor 24/7 you can use a dummy plug which essentially emulates a screen being connected. Some consumer motherboards will essentially all but...- nmbgeek
- Post #8
- Forum: Troubleshooting
-
A Plead for Help With Random App (BI) Crashing
You mentioned that you are running headless. Do you have an HDMI/DP dummy plug connected? If not I would highly recommend one as sometimes GPU tasks need to think a display is detected. Edit: also did you happen to install Dell Command Update and make sure all of the latest Dell Drivers and...- nmbgeek
- Post #6
- Forum: Troubleshooting
-
Graphics card recommentation
Tesla P4s are really cheap now but in a regular desktop you will need a fan as they don't have a dedicated fan. There are a few variations of fan shrouds if you or a friend have a 3d printer it can be made really easily - Tesla P4/T4 fan shroud by Crazybonze -
CPAI 2.80 Changelog?
I don't think there is one yet. I brought this up a while back in this thread because they can kind of be all over the place in this thread. Chris's response was to basically rely on the changelog on the main page. I wish they would develop in their public github so that others could... -
CodeProject.AI Version 2.5
It isn't necessarily unused it is my main home office PC for when I feel like PC gaming, playing with automatic1111, or other compute intensive tasks. It's got a 5950x with 64GB of RAM and hooked up to an Alienware 38" OLED. I'm pretty sure GPU mining hasn't been profitable since ETH went to... -
CodeProject.AI Version 2.5
@MikeLud1 - Thanks for the great work on PyTorch models. Is there any chance of getting an ipcam-combined model for yolov8? I have a 3090 sitting around that is relatively unused and I wouldn't mind training if I had a decent data set. -
EmpireTech 9th Anniversary (Summer)Sales
Just to be clear - If we want to buy tickets outright purchase them now, if we want tickets for cameras purchased we need to wait until the Start Time on 07/15 to make the purchase?- nmbgeek
- Post #38
- Forum: EmpireTech Andy
-
2024 EmpireTech Active Deterrence PTZ Camera Release
Any chance of adding any of the X-spans style PTZ cameras to your lineup? I would like a nice fixed with PTZ capability.- nmbgeek
- Post #6
- Forum: EmpireTech Andy