yolov5 VS gocv

Ref https://www.youtube.com/watch?v=0GwnxFNfZhM https://github.com/ultralytics/yolov5 https://dev.to/gfstealer666/kaaraich-yolo-alkrithuemainkaartrwcchcchabwatthu-object-detection-3lef https://www.kaggle.com/datasets/devdgohil/the-oxfordiiit-pet-dataset/data

!git clone https://github.com/ultralytics/yolov5.git ## Navigate to the model %cd yolov5/ ## Install requirements !pip install -r requirements.txt ## Download the YOLOv5 model !wget https://github.com/ultralytics/yolov5/releases/download/v6.0/yolov5s.pt

Specifically what I did was take the coco128.yaml, added 6 new classes from Dataset A (which have already been converted to YOLO Darknet TXT), from index 0-5 and subsequently adjusted the indices of the other COCO classes. The I proceeded to train and validate on Dataset A for 20 epochs.

I am using the default YOLOv5m6 model here with sahi/yolov5 library for my object detection project. I want to change just some of labels - for example when YOLO detects a human, I want it to label the human as "threat", not "person". Is there any way I can do it just changing some code, or I should train the model from scratch by just changing labels?

You should add them without annotations. Go through this.

You are correct and if you check the firmware, it's yet another famous 3rd party project without attribution, namely https://github.com/ultralytics/yolov5

On one side, being a Linux user for 24 years now, it annoys me that they rip off code and claiming it as theirs again, thus violating licenses, but on the other thanks to k3d's exploit I'm able to tinker more with the machine and if needed do (selective) updates by hand then with a closed source system. It's not just "klipper", with klipper, fluidd and moonraker, it's also ffmpeg and mjpegstreamer. It's gonna be interesting since they also use a project that isn't just GPL, but APGL (in short "If your software gives service online, you have to publish the source code of it and any library that it borrows functions from.") - they use yolov5 (for AI).

- Updated Docker images with OpenCV

https://github.com/hybridgroup/gocv/releases/tag/v0.36.0

- Installing from source gives me E: Unable to locate package libdc1394-22-dev

Can anyone guess if its possible to e.g. use - https://github.com/hybridgroup/gocv - permanently monitor the network stream via address e.g. http://192.169.178.20/action/stream?subject=mjpeg&user=user&pwd=secret - Generate/Extract a snapshot as image if configured items are detected e.g.: humans, cats, cars, dogs

But if you want to have something to show: I've played around with https://gocv.io/ and was quite impressed what this library can do with the video input from your camera input.

I have just found the gocv package. I have a video analyzer program written in python, however im thinking about rewriting on golang for optimizing the execution time. Its a good idea or its better to just use the phyton one.

https://github.com/hybridgroup/gocv has openCV bindings.

I am working on a custom model, I have been through this example to apply it on my use case but the output I get has random detection from perform detection, how do I work with gocv.Mat structure and is there any example with yolo darknet model? Any help is appreciated if you can direct me to right resources where I can better understand how the output mat is to be parsed to get the box! Thanks in advance!

I think https://github.com/hybridgroup/gocv accepts tensorflow model format, why not use that?

The repo leverages gocv and can be run using CUDA(performance results here). If there's any interest I can create one for YOLO V4 as well.