Comparison of Mask RCNN vs Yolov8

The goal of this assignment is train both models on custom annotated dataset.
Take photos of your environment of two or more objects. (at least 100 instances between all objects)
Annotate them on roboflow.
Train a Mask RCNN model using detectron2
Train Yolov8 the smallest size
Evaluate both models based on mAP and speed and size.

Taking pictures

A notebook and airpods were used for segmentation task

Yolov8's significant speed advantage provides numerous benefits, even considering its size.
Training Yolov8 for 20 epochs takes approximately 3-4 minutes, whereas MASK RCNN requires approximately 55-56 minutes.