DeepFaceLab/models/Model_Quick96
Colombo 71ebf06c89 SAEHD,Quick96:
improved model generalization, overall accuracy and sharpness
by using new 'Learning rate dropout' technique from paper https://arxiv.org/abs/1912.00144
An example of a loss histogram where this function is enabled after the red arrow:
https://i.imgur.com/3olskOd.jpg
2019-12-15 15:53:06 +04:00
..
__init__.py added Quick96 model 2019-11-09 19:24:31 +04:00
Model.py SAEHD,Quick96: 2019-12-15 15:53:06 +04:00