iperov 2a8dd788dc SAE: added option 'Pretrain the model?', ... Pretrain the model with large amount of various faces. This technique may help to train the fake with overly different face shapes and light conditions of src/dst data. Face will be look more like a morphed. To reduce the morph effect, some model files will be initialized but not be updated after pretrain: LIAE: inter_AB.h5 DF: both decoders.h5. The longer you pretrain the model the more morphed face will look. After that, save and run the training again.		2019-05-01 19:55:27 +04:00
..
Model_DEV_FANSEG	refactorings	2019-04-24 11:28:58 +04:00
Model_DEV_POSEEST	_	2019-04-30 17:14:02 +04:00
Model_DF	refactorings	2019-04-24 11:28:58 +04:00
Model_H64	refactorings	2019-04-24 11:28:58 +04:00
Model_H128	refactorings	2019-04-24 11:28:58 +04:00
Model_LIAEF128	refactorings	2019-04-24 11:28:58 +04:00
Model_RecycleGAN	refactorings	2019-04-24 11:28:58 +04:00
Model_SAE	SAE: added option 'Pretrain the model?',	2019-05-01 19:55:27 +04:00
__init__.py	removing trailing spaces	2019-03-19 23:53:27 +04:00
archived_models.zip	update == 04.20.2019 == (#242)	2019-04-20 08:23:08 +04:00
ModelBase.py	SAE: added option 'Pretrain the model?',	2019-05-01 19:55:27 +04:00