wanginwang

It seems that in all your models such as dch.py, dhn.py, you first load model and pretrained model weights and then run global initializer, ``` self.img_last_layer, self.deep_param_img, self.train_layers, self.train_last_layer =...

Hi, thanks for your work, but I'm concerned about why there is no dropout in your model? Dropout improves the performance of consistent loss largely as a data augmentation policy....