I know that for calculating mean average precision first we must have ground truth files for each image in dataset. I am following this tutorial to detect whether a person has mask on its image or not. I know that It is a classification problem. I have found one github tutorial which has comprehensive details about how to calculate MAP for object detection. But i am totally confused. Because it says that you need to generate ground truth files for each of the image in dataset. As far as I know ground truth files is original area of the object which we want to detect.
After getting the ground truth files we have to calculate IOU of the images and then take Mean of all classes in this case we have two class
- either a person a mask
- or it does not have a mask.
Kindly clear my confusion and tell me if i am wrong somewhere in my understanding.