A simple, binary classification using Xception model which was pretrained and of which the weights file can be fetched from Keras
Samples with surface defects are merged into a single category (folder) call MT_Defects.
Cleaned-up dataset is stored in folder data
Call: python data_prep.py after modifying corresponding folders and split percentages for train/val/test.
Call: python defect_classify.py
For parameters see inside the code.