Aidan Dempster f5760bdb92 Add data flexibility to decoder trainer (#165) ...

* Added the ability to train decoder with text embeddings

* Added the ability to train using on the fly generated embeddings with clip

* Clip now generates embeddings for whatever is not precomputed

2022-06-25 19:05:20 -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 data flexibility to decoder trainer (#165)

2022-06-25 19:05:20 -07:00

__init__.py

fix version

2022-05-30 11:06:34 -07:00

cli.py

add missing import (#56)

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

dalle2_pytorch.py

autoswitch tqdm for notebooks (#171)

2022-06-25 16:37:06 -07:00

optimizer.py

lower beta2 for adam down to 0.99, based on https://openreview.net/forum?id=2LdBqxc1Yv

2022-06-03 10:26:28 -07:00

tokenizer.py

make youtokentome optional package, due to reported installation difficulties

2022-06-01 09:25:35 -07:00

trackers.py

Distributed Training of the Decoder (#121)

2022-06-19 09:25:54 -07:00

train_configs.py

Add data flexibility to decoder trainer (#165)

2022-06-25 19:05:20 -07:00

trainer.py

Add data flexibility to decoder trainer (#165)

2022-06-25 19:05:20 -07:00

utils.py

Distributed Training of the Decoder (#121)

2022-06-19 09:25:54 -07:00

version.py

just make sure decoder learning rate is reasonable and help out budding researchers

2022-06-23 11:29:28 -07:00

vqgan_vae_trainer.py

EMA for vqgan vae comes from ema_pytorch now

2022-06-20 15:29:08 -07:00

vqgan_vae.py

changed str in order to avoid confusions and collisions with Python (#147)

2022-06-15 13:41:16 -07:00