Open MasterXin2020 opened 2 years ago
I have found that the input channels and output channels of the last two deconvolutional layer were wrong according to the 2D AE network parameters in the paper.Please check it again and have it corrected.
Hi, we set the input channels and output channels in train_utils_ae.py (define the model)
fmodel=getattr(models, args.model_name) self.encoder = getattr(fmodel, 'encoder')(in_channel=Dataset.inputchannel, out_channel=Dataset.num_classes)
self.decoder = getattr(fmodel, 'decoder')(in_channel=Dataset.inputchannel, out_channel=Dataset.num_classes) self.classifier = getattr(fmodel, 'classifier')(in_channel=Dataset.inputchannel, out_channel=Dataset.num_classes)
I have found that the input channels and output channels of the last two deconvolutional layer were wrong according to the 2D AE network parameters in the paper.Please check it again and have it corrected.