I know this is not related in this issue but i need help. I am using the keras version segnet from https://github.com/0bserver07/Keras-SegNet-Basic and build on my own dataset. The classes changed from 12 to 2 which are crack and background. I am now facing problem of class weight does not work, the accuracy and loss remain the same no matter what value i changed. Code and dataset can be found at here : https://drive.google.com/open?id=1wK-non5bMkpApMshtCHXIqLXZOJ9jUxU . Can anyone provide some insight on the possible error that cause this problem?
I know this is not related in this issue but i need help. I am using the keras version segnet from https://github.com/0bserver07/Keras-SegNet-Basic and build on my own dataset. The classes changed from 12 to 2 which are crack and background. I am now facing problem of class weight does not work, the accuracy and loss remain the same no matter what value i changed. Code and dataset can be found at here : https://drive.google.com/open?id=1wK-non5bMkpApMshtCHXIqLXZOJ9jUxU . Can anyone provide some insight on the possible error that cause this problem?