PolarMask icon indicating copy to clipboard operation
PolarMask copied to clipboard

Train with own dataset.

Open AmberrrLiu opened this issue 4 years ago • 3 comments

How to train with your own dataset? I converted the data to coco format; Some file configuration changes were made following mmdetection. But the training result label is still coco's.

AmberrrLiu avatar May 31 '20 06:05 AmberrrLiu

Hi, I cannot understand your meanings, please provide more details.

xieenze avatar Jun 01 '20 13:06 xieenze

Hi, I cannot understand your meanings, please provide more details.

There is no training record(eg. loss) during training my own data set. During visualization, the picture is not well recognized, and the label is still the data label of coco, instead of self-labeling.

AmberrrLiu avatar Jun 07 '20 02:06 AmberrrLiu

Hi, I cannot understand your meanings, please provide more details.

There is no training record(eg. loss) during training my own data set. During visualization, the picture is not well recognized, and the label is still the data label of coco, instead of self-labeling.

Make sure you set correct num_classes in config & CLASSES in mmdet/datasets/coco_seg.py. It seems that the num_classes should have background included. Hope this helps : )

kaiyux avatar Dec 15 '20 02:12 kaiyux