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: Yolo models trained for object detection. This is a v8 model so make sure you put it in the right directory. It uses yolov8s parameters to be relatively quick but was trained from scratch using primarily the COCO2017 dataset with images containing the very smallest of objects removed. i.e., if the image contained a person object that was less than 200px in area such as 10x20px the entire image was removed from the training and validation data. I have a nano model training now as well that I will add in the coming days if it also seems to give reasonably good results.
Update: A nano version has been added.
Update: A nano version has been added.
Last edited: