Train Single Label Detection

[malik-anhar]

Let's say I wanna train the model only for single label (face), so what is the correct annotation for the train.txt? Is it something like this

path/to/img1.jpg 50,100,150,200,0 30,50,200,120,0
path/to/img2.jpg 120,300,250,600,0

or something like this

path/to/img1.jpg 50,100,150,200,1 30,50,200,120,1
path/to/img2.jpg 120,300,250,600,1

The class_id should be 0 or 1?

[Anyman552]

The class_id should be 0