usually the segmentation map is 2D but got 3D

[jhaggle]

When I try to train om my own images and segmentation maps I get this:

.../mmsegmentation/mmseg/datasets/transforms/formatting.py:81: UserWarning: Please pay attention your ground truth segmentation map, usually the segmentation map is 2D, but got (209, 286, 3)

The segmentation maps are on the format
.../SegmentationClassPNG/seg_img_34.png

Why does this happen and how do I solve it?