I am trying to train an YOLO Network with my own data. However, a single image can have multiple bounding boxes that belong to the same class. For instance, one of the text files is
0 0.262346 0.498264 0.002315 0.004630
0 0.293210 0.516204 0.000772 0.001157
0 0.343750 0.679977 0.003086 0.009259
0 0.360725 0.621528 0.001543 0.001157
0 0.437114 0.666667 0.001543 0.001157
0 0.455633 0.214699 0.003086 0.004630
0 0.516204 0.245370 0.002315 0.003472
Is there a way to feed such a structure in the network or is it one bounding box per image?