This GitHub Repository was produced to share material relevant to the Journal paper "Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning" by D. Dais, İ. E. Bal, E. Smyrou, and V. Sarhosis published in "Automation in Construction".
Could you summarize the process for making a prediction on a new set of images?
Is it possible to do this without having the corresponding masks?
Thanks
Do you plan to release the data used for the part on crack image classification, i.e. classification of images into crack/non-crack classes?
It would be very useful to have it in addition to the segmentation data set. Thank you!
Hello, I am learning the crack detection, and I have run your code of Unet, but I want to run the code of deeplabv3, and there is an error as following:
File "D:\crack\network_class.py", line 111, in define_Network
from model import Deeplabv3
ImportError: cannot import name 'Deeplabv3' from 'model' (D:\crack\model.py)
could you help me? I really want to run your code.