Phil Wang d1f02e8f49 always use sandwich norm for attention layer

2022-05-14 12:13:41 -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

always use sandwich norm for attention layer

2022-05-14 12:13:41 -07:00

optimizer.py

now completely OpenAI CLIP compatible for training

2022-04-29 13:05:01 -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

align the ema model device back after sampling from the cascading ddpm in the decoder

2022-05-11 19:56:54 -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