Computing confidence mask about pytorch-yolov3 HOT 3 CLOSED

This should be fixed in 959e0ff. Before this commit the confidence mask was computed as in YOLOv2. With the latest commit the confidence mask is set as in version 3, i.e. where the anchor has an overlap with a target box larger than 0.5 but is not the anchor with the largest overlap the confidence prediction is ignored during training.

from pytorch-yolov3.

I found the part you are refering to in the commit history but I am not sure why this filtering was removed. Can you explain @eriklindernoren ?

from pytorch-yolov3.

I guess because it was redundant / wrong. The mask is computed as:
mask[b, best_anchor_idx, gj, gi] = 1, basically saying that for batch b, the anchor best_anchor_idx of cell (gj, gi) is responsible for predicting some ground truth object.

from pytorch-yolov3.