Phil Wang fb8a66a2de just in case latent diffusion performs better with prediction of x0 instead of epsilon, open up the research avenue

2022-04-24 10:04:22 -07:00

..

data

bring in the simple tokenizer released by openai, but also plan on leaving room for custom tokenizer with yttm

2022-04-12 09:23:17 -07:00

__init__.py

refactor blurring training augmentation to be taken care of by the decoder, with option to downsample to previous resolution before upsampling (cascading ddpm). this opens up the possibility of cascading latent ddpm

2022-04-22 11:09:17 -07:00

cli.py

some outlines to the eventual CLI endpoint

2022-04-24 09:27:15 -07:00

dalle2_pytorch.py

just in case latent diffusion performs better with prediction of x0 instead of epsilon, open up the research avenue

2022-04-24 10:04:22 -07:00

tokenizer.py

bring in the simple tokenizer released by openai, but also plan on leaving room for custom tokenizer with yttm

2022-04-12 09:23:17 -07:00

train.py

get ready for all the training related classes and functions

2022-04-12 09:54:50 -07:00

vqgan_vae.py

prepare for turning off gradient penalty, as shown in GAN literature, GP needs to be only applied 1 out of 4 iterations

2022-04-23 07:52:10 -07:00