Search results
-
Beginning with AI
First, it feels like you are trying to do too much with a single camera. Pick a single purpose and stick with that. You can't expect that angle to get much in the way of detail on the street or the driveway and may be looking down too much to get more than people's heads if they were to walk... -
Blue Iris Long Delay with CodeProject Object Detection
First, you still have the default 'Objects' model enabled so that is running concurrently. I'd go to the global AI settings and turn that off. As for the question about ipcam-general, it only detects two objects: 'vehicle' and 'person' but you are telling it to look for 'car', 'motorcycle'... -
Blue Iris Long Delay with CodeProject Object Detection
Check out the GitHub for the custom ipcam models. GitHub - MikeLud/CodeProject.AI-Custom-IPcam-Models You need to know the specific name of the model you want to use. There isn't an ipcam-objects model. And the dark images have been incorporated in a few others, so you probably don't need it to... -
Blue Iris Long Delay with CodeProject Object Detection
On the global AI settings, turn off the default detection because the default model has too many unnecessary objects. That will get of one unnecessary model check. On your camera, it seems you only want people and vehicles. One option is to use the ipcam-general custom model which has two... -
IP Cam Talk Custom Community DeepStack Model
Another quick question. When you update your models in GitHub, how quickly are they incorporated into the CPAI install? And once in there, what steps would one need to update to your latest custom models? -
5.8.8 - March 4, 2024
I wish Ken would fully clear this up. I have most cameras using "ipcam-general" , some using "ipcam-combined", one using "license-plate" and one using "delivery". I just want to make sure that they aren't going to start using all 4 on all cameras since I've specified the model I want to use for...- VideoDad
- Post #22
- Forum: What's New
-
5.8.8 - March 4, 2024
As I read Ken's note, he's saying that if you only exclude other models in the custom model field means all other custom models will run. Currently I have custom model names set for all my cameras, so I think it means there is no change for me and it'll behave as it did before.- VideoDad
- Post #18
- Forum: What's New
-
5.8.8 - March 4, 2024
I haven't updated, nor have plans to update. I'm just asking if I've set a specific custom model (say ipcam-general) this seems to imply a change is being made to run all the other custom models regardless of what I intended for each specific camera.- VideoDad
- Post #9
- Forum: What's New
-
5.8.8 - March 4, 2024
So I'm still confused. I'm only using custom models (not the default objects model). If I have a camera dedicated to license plates (for example) this seems to imply that all the other custom models (ipcam-general, ipcam-animal, ipcam-general combined, etc.) will fire, even if I've only listed a...- VideoDad
- Post #5
- Forum: What's New
-
5.8.8 - March 4, 2024
Wait... what's the reasoning behind this change?- VideoDad
- Post #3
- Forum: What's New
-
How to train a custom YOLOv5 model using CodeProject.AI Training for YoloV5 6.2 module
If your chosen object looks similar to another, then consider including images that could generate false positives. For example, if you are training a model to recognize horses, you might want include pictures of zebras without labels. That's probably not the best example, but you get the idea... -
How to train a custom YOLOv5 model using CodeProject.AI Training for YoloV5 6.2 module
If you had thousands of pictures of Spot, you could definitely train a model on those pictures and it would be able to find Spot in other pictures you gave it. But the big problem is it may not necessarily know enough to distinguish Spot from a similarly shaped animal. If you want to get a... -
People can mask USPS AI detections
That doesn't match with the hash code for the latest version. What's the file size? -
People can mask USPS AI detections
Can you first verify the checksum on the most recent version of delivery.pt? Type this command in a command window: certutil -hashfile delivery.pt SHA1 b99be438e838b7b811f1477a3532a02aa39821b6 -
AI error 500 how to capture that error
Are you trying to find the cause of the 500 error? If so, the logs are your best bet. I believe you can have BI send you an email when it occurs, if you are just wanting to detect the error but not try to fix it. -
AI error 500 how to capture that error
Assuming you are using CPAI, it maintains a log, usually under C:\Program Files\CodeProject\AI\logs And from the BI side, you can capture those logs too. Click the BI status icon (looks like a graph with a zigzag line) and go to the Log tab and make sure "Log to file" is checked. -
Date/Time overlay - Camera, or Blue Iris, or both?
I am also in the camp that lets BI apply the timestamp. As I understand direct-to-disk and the BVR format, there isn't a re-encoding being done anymore. My initial reasoning for doing that was I found the in camera fonts to be ugly, a pain to synchronize, a pain to configure to look similar...- VideoDad
- Post #19
- Forum: General BI Talk
-
code project ai 2.5.4 thinks everything is a person
Are you using the default object model or a custom model; if custom, which one in particular? Which specific module are you using for object detection? YOLOv5 6.2, YOLOv5 NET or YOLOv8? -
People can mask USPS AI detections
Thanks for the feedback. I'll have to get a Deepstack instance running and see if I can reproduce your issues. What is it you see when you say it doesn't work? -
People can mask USPS AI detections
@MikeLud1, thanks for proposing this to @ChrisMaunder. I'd love them to get included in the CPAI install. Let me know if there is anything you need from me. Also, if I update the GitHub repository in the future, do I need to notify someone or will the install pull the latest each time? Mike... -
People can mask USPS AI detections
Just to reiterate, when I'm talking about case, I'm talking about the possible objects (not the filename). In the USPS.pt model, the only object was "USPS". In mine, all the objects are lowercase (e.g. amazon, fedex, usps, etc.). As for updates, I uploaded each of the versions from before as... -
People can mask USPS AI detections
I didn't create the USPS.pt model; I only used many of the images in the training of my delivery models. And yes, I did improve it with more images especially from actual security cameras and with doors open. I was using the YOLOv5 6.2 model on Deepstack prior to switching to CPAI. I believe it... -
People can mask USPS AI detections
The delivery model is now on Github along with exported models for YOLOv5 6.2, YOLOv5 NET, YOLOv8 and YOLOv8 NET Link: Custom delivery models on VideoDad's Github -
People can mask USPS AI detections
The delivery model is now on Github along with exported models for YOLOv5 6.2, YOLOv5 NET, YOLOv8 and YOLOv8 NET Link: Custom delivery models on VideoDad's Github -
I need a Ethernet/power cable pigtail...
It should come with a pigtail for both Ethernet and separate power. But is there a reason you aren't just connecting it with PoE (Power over Ethernet) so you don't need a separate power connection at the camera? If you don't already have a PoE switch, but just want to power this one camera, you...- VideoDad
- Post #2
- Forum: IP Cameras
-
DS-2CD2032-I Motion Not being Triggered
Can you post your trigger settings for this camera? Are you using the built-in motion detection of the camera to trigger Blue Iris? Or are you using BI to detect the motion based on changed pixels? -
People can mask USPS AI detections
Interesting thought and maybe Ken is already thinking of optimizations that could be made. I know @MikeLud1 is doing some pre-processing of a plate (cropping, straightening) before sending it off to OCR. I don't know if he's got recommendations in improvements that Ken could add directly to BI... -
People can mask USPS AI detections
Ack! No wonder it was taking so long. Somehow in resetting my environment to work with YOLOv8, updating Python to 3.11, etc. it looks like pyTorch is NOT using the GPU. I'm figuring it out now. Thanks for the offer but I'd like to resolve this locally first. Update: It's processing now using... -
People can mask USPS AI detections
Just to give you an update... previously I could train a YOLOv5 model overnight. But though I think I've set up YOLOv8 similarly, it's taking quite a lot longer. When I started with the medium model (yolov8m.pt) it was upwards of an hour per epoch. Now, I've switched it to the small model... -
People can mask USPS AI detections
Got it... So basically just switching to the yolov8m model. Let me give that a go.