DL-Art-School/codes
James Betker bdbab65082 Allow optimizers to train separate param groups, add higher dimensional VGG discriminator
Did this to support training 512x512px networks off of a pretrained 256x256 network.
2021-01-02 15:10:06 -07:00
..
.idea IDEA update 2020-05-19 09:35:26 -06:00
data Move discriminators to the create_model paradigm 2021-01-01 15:56:09 -07:00
models Allow optimizers to train separate param groups, add higher dimensional VGG discriminator 2021-01-02 15:10:06 -07:00
scripts Move discriminators to the create_model paradigm 2021-01-01 15:56:09 -07:00
trainer Allow optimizers to train separate param groups, add higher dimensional VGG discriminator 2021-01-02 15:10:06 -07:00
utils Move discriminators to the create_model paradigm 2021-01-01 15:56:09 -07:00
multi_modal_train.py More adjustments to support distributed training with teco & on multi_modal_train 2020-10-27 20:58:03 -06:00
process_video.py More refactoring 2020-12-18 09:18:34 -07:00
requirements.txt Move discriminators to the create_model paradigm 2021-01-01 15:56:09 -07:00
test_image_patch_classifier.py More refactoring 2020-12-18 09:18:34 -07:00
test.py Fix srflow_latent_space_playground bug 2020-12-22 15:42:38 -07:00
train.py Allow optimizers to train separate param groups, add higher dimensional VGG discriminator 2021-01-02 15:10:06 -07:00