Fully-convolutional-neural-network-FCN-for-semantic-segmentation-Tensorflow-implementation icon indicating copy to clipboard operation
Fully-convolutional-neural-network-FCN-for-semantic-segmentation-Tensorflow-implementation copied to clipboard

Published 20 hours ago • verified publisher icon sagieppel

Loss Nan

Open gauthamnandakumar opened this issue 6 years ago • 1 comments

My loss is Nan in all iterations. I am training on my own dataset. The labels are 0 for background and 1 for the ROI i am intending to segment. Any idea why? Thank you

gauthamnandakumar avatar Jun 27 '18 00:06 gauthamnandakumar

Do you solve this problem? I happen to the same trouble.

leishi2018 avatar Dec 18 '18 12:12 leishi2018