Hi. Thanks for your excellent research work.
I have a question why training discriminator uses decoder_small, in addition to decoder_big and decoder_part?
In my opinion, reconstruction loss does not use rec_img_small accroding to paper. Maybe I missed important information.
Hi. Thanks for your excellent research work. I have a question why training discriminator uses decoder_small, in addition to decoder_big and decoder_part? In my opinion, reconstruction loss does not use rec_img_small accroding to paper. Maybe I missed important information.
rec_img_big = self.decoder_big(feat_last) rec_img_small = self.decoder_small(feat_small) rec_img_part = self.decoder_part(feat_32[:,:,:8,:8])