28 Commits

Author	SHA1	Message	Date
mgz-dev	b29c5a750c	expand optimizer options and refactor ... Refactor code to make it easier to add new optimizers, and support alternate optimizer parameters -move redundant code to train_util for initializing optimizers - add SGD Nesterov optimizers as option (since they are already available) - add new parameters which may be helpful for tuning existing and new optimizers	2023-02-19 17:45:09 -06:00
Kohya S	048e7cd428	add lion optimizer support	2023-02-19 15:26:14 +09:00
Kohya S	ffdfd5f615	fix name of loss for epoch	2023-02-16 22:21:36 +09:00
Kohya S	914d1505df	Merge pull request #189 from shirayu/improve_loss_track ... Show the moving average loss	2023-02-16 22:00:26 +09:00
Kohya S	43c0a69843	Add noise_offset	2023-02-14 21:15:48 +09:00
Yuta Hayashibe	8aed5125de	Removed call of sum()	2023-02-14 21:11:30 +09:00
Yuta Hayashibe	21f5b618c3	Show the moving average loss	2023-02-14 19:46:27 +09:00
Kohya S	3a72e6f003	add tag dropout	2023-02-09 21:35:27 +09:00
Kohya S	e42b2f7aa9	conditional caption dropout (in progress)	2023-02-07 22:28:56 +09:00
forestsource	7db98baa86	Add dropout options	2023-02-07 00:01:30 +09:00
Kohya S	ea2dfd09ef	update bucketing features	2023-02-05 21:37:46 +09:00
hitomi	26a81d075c	add --persistent_data_loader_workers option	2023-02-01 16:02:15 +08:00
forestsource	5e817e4343	Add save_n_epoch_ratio	2023-01-22 03:00:28 +09:00
Kohya S	687044519b	Fix TE training stops at max steps if ecpochs set	2023-01-19 21:43:34 +09:00
Kohya S	aa40cb9345	Add train epochs and max workers option to train	2023-01-15 13:07:47 +09:00
Kohya S	82e585cf01	Fix full_fp16 and clip_skip==2 is not working	2023-01-08 18:49:34 +09:00
Kohya S	80af4c0c42	Set dtype if text encoder is not trained at all	2023-01-07 21:43:27 +09:00
Kohya S	2efced0a9a	fix training starts with debug_dataset	2023-01-07 20:19:25 +09:00
Kohya S	1b222dbf9b	erase using of deleted property	2023-01-06 17:13:56 +09:00
Kohya S	f56988b252	unify dataset and save functions	2023-01-05 08:10:22 +09:00
Kohya S	4c35006731	split common function from train_network to util	2023-01-03 20:22:25 +09:00
Kohya S	e31177adf3	Merge branch 'refactoring_training' of https://github.com/kohya-ss/sd-scripts into refactoring_training	2023-01-02 16:14:45 +09:00
Kohya S	6b522b34c1	move code for xformers to train_util	2023-01-02 16:08:21 +09:00
Yuta Hayashibe	85d8b49129	Fix calculation for the old epoch	2023-01-01 23:36:20 +09:00
Yuta Hayashibe	61a61c51ee	Add --save_last_n_epochs option	2023-01-01 21:46:38 +09:00
Yuta Hayashibe	0f20453997	Fix typos	2022-12-31 14:39:36 +09:00
Kohya S	0a884da984	Fix text encoder training is not stopped #4	2022-12-22 23:34:51 +09:00
bmaltais	c5cca931ab	Proposed file structure rework and required file changes	2022-12-18 15:24:46 -05:00