Aidan Dempster f97e55ec6b Quality of life improvements for tracker savers (#210) ...

The default save location is now none so if keys are not specified the
corresponding checkpoint type is not saved.

Models and checkpoints are now both saved with version number and the
config used to create them in order to simplify loading.

Documentation was fixed to be in line with current usage.

2022-07-19 17:50:18 -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

Added deepspeed support (#195)

2022-07-08 18:18:08 -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

@jacobwjs reports dynamic thresholding works very well and 0.95 is a better value

2022-07-19 11:31:56 -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

Quality of life improvements for tracker savers (#210)

2022-07-19 17:50:18 -07:00

train_configs.py

offer way to turn off initial cross embed convolutional module, for debugging upsampler artifacts

2022-07-15 17:29:10 -07:00

trainer.py

foolproof sampling for decoder to always use eval mode (and restore training state afterwards)

2022-07-13 10:21:00 -07:00

utils.py

Overhauled the tracker system (#172)

2022-07-01 09:39:40 -07:00

version.py

@jacobwjs reports dynamic thresholding works very well and 0.95 is a better value

2022-07-19 11:31:56 -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