Phil Wang b494ed81d4 take care of backwards within trainer classes for diffusion prior and decoder, readying to take care of gradient accumulation as well (plus, unsure if loss should be backwards within autocast block)

2022-05-14 15:49:24 -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

dataloaders

Add a dataloader for training the decoder (#57)

2022-05-05 07:08:45 -07:00

__init__.py

some cleanup

2022-05-09 16:50:21 -07:00

cli.py

add missing import (#56)

2022-05-04 07:42:20 -07:00

dalle2_pytorch.py

normalize conditioning tokens outside of cross attention blocks

2022-05-14 14:23:52 -07:00

optimizer.py

be able to customize adam eps

2022-05-14 13:55:04 -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_vqgan_vae.py

make sure vqgan-vae trainer supports mixed precision

2022-05-06 10:44:16 -07:00

train.py

take care of backwards within trainer classes for diffusion prior and decoder, readying to take care of gradient accumulation as well (plus, unsure if loss should be backwards within autocast block)

2022-05-14 15:49:24 -07:00

vqgan_vae.py

remove convnext blocks, they are illsuited for generative work, validated by early experimental results at https://github.com/lucidrains/video-diffusion-pytorch

2022-05-05 07:07:21 -07:00