DL-Art-School/codes/data
James Betker eb11a08d1c Enable disjoint feature networks
This is done by pre-training a feature net that predicts the features
of HR images from LR images. Then use the original feature network
and this new one in tandem to work only on LR/Gen images.
2020-07-31 16:29:47 -06:00
..
__init__.py Test modifications 2020-05-19 09:37:58 -06:00
data_sampler.py
Downsample_dataset.py Allow dataset classes to add noise internally 2020-05-23 21:04:24 -06:00
LQ_dataset.py Enable force_multiple in LQ_dataset 2020-07-22 20:51:16 -06:00
LQGT_dataset.py Enable disjoint feature networks 2020-07-31 16:29:47 -06:00
REDS_dataset.py
util.py Allow separate dataset to pushed in for GAN-only training 2020-07-26 21:44:45 -06:00
weight_scheduler.py Add an abstract, configurabler weight scheduling class and apply it to the feature weight 2020-07-23 17:03:54 -06:00