I am sorry to reply so late. YOLY is an "untrained" method, which means that YOLY bypasses the conventional training paradigm of deep models on hazy-clean pairs and only need to optimize its parameters on observed ones. Thus, dehazing.py is both training program and verification program, because it optimizes parameters in this file and test the performance as well.
I am sorry to reply so late. YOLY is an "untrained" method, which means that YOLY bypasses the conventional training paradigm of deep models on hazy-clean pairs and only need to optimize its parameters on observed ones. Thus, dehazing.py is both training program and verification program, because it optimizes parameters in this file and test the performance as well.