tensorflow-object-contour-detection icon indicating copy to clipboard operation
tensorflow-object-contour-detection copied to clipboard

Published 20 hours ago • verified publisher icon Raj-08

new labels

Open manutom opened this issue 6 years ago • 4 comments

GT[GT!=255]=0 in create_labels.py practically makes all pixels with value 0 which is weird

manutom avatar Feb 13 '19 17:02 manutom

Yeah you are right. Any leads on solving the matter so far? I didn't run create_labels.py to generate enhanced labels for training. Instead I trained with the ground-truth labels of PASCAL-VOC dataset.

rubeea avatar Jan 14 '20 08:01 rubeea

For me it happened because the labels from the dataset have their countours in a yellowish colour, not white. By changing it to GT[GT!=220]=0, I now obtain only the contours. Also added GT[GT==220]=255 to make them white. Hope this helps!

itziarrr avatar Feb 28 '20 19:02 itziarrr

GT [GT！= 220] = 0 GT [GT == 220] = 255 What do these two lines of code mean?

对我而言，发生这种情况是因为数据集中的标签的计数是淡黄色而不是白色。 通过将其更改为GT [GT！= 220] = 0，我现在仅获得轮廓。 还添加了GT [GT == 220] = 255使它们变为白色。 希望这可以帮助！

keepgoing365 avatar May 13 '20 12:05 keepgoing365

220 in my case was the intensity of the pixels of the contours. Therefore, GT [GT！= 220] = 0 means 'make all that is not contour black' (pixel level = 0) And GT [GT == 220] = 255 makes the contours truly white.

itziarrr avatar May 19 '20 21:05 itziarrr