374 commits

Author	SHA1	Message	Date
zhengzangw	771100ed88	Merge branch 'dev/v1.2' of github.com:hpcaitech/Open-Sora-dev into dev/v1.2	2024-05-20 09:40:36 +00:00
zhengzangw	bdc67a3933	[wip] debug extract feat	2024-05-20 09:40:28 +00:00
Zheng Zangwei (Alex Zheng)	9cf394884c	Dev/load batch (#105) ... * add train_load_batch * update train_load_batch --------- Co-authored-by: pxy <pexure@gmail.com>	2024-05-20 17:40:05 +08:00
zhengzangw	5b9e753039	[feat] unify dataloader api	2024-05-20 08:40:45 +00:00
zhengzangw	5aad90acaf	[feat] extract feature	2024-05-17 09:53:48 +00:00
zhengzangw	a016325a8e	[feat] enable freezing y_embedder	2024-05-17 06:40:44 +00:00
zhengzangw	9fd4554f55	[fix] vae dtype	2024-05-16 08:50:24 +00:00
zhengzangw	137d0ac223	[fix] t5 dtype	2024-05-16 08:33:01 +00:00
zhengzangw	0592723022	[feat] update bs search and loss eval	2024-05-15 13:05:53 +00:00
zhengzangw	bb3c23577c	[wip] eval loss and search bs	2024-05-15 12:21:07 +00:00
ChangeFWorld	811ac1055b	Add Eval loss (#99) ... * evaluation half complete * eval loss finish * refine config --------- Co-authored-by: Tianyi <aicfw.li@gmail.com>	2024-05-15 16:17:19 +08:00
zhengzangw	f489cb0915	[feat] accelerate search batch size	2024-05-15 08:07:49 +00:00
zhengzangw	9188b75bc5	Merge branch 'dev/v1.2' of github.com:hpcaitech/Open-Sora-dev into dev/v1.2	2024-05-14 07:25:07 +00:00
zhengzangw	a36f80f847	[feat] notebook for inference	2024-05-14 07:24:56 +00:00
Frank Lee	d1b73a7c9f	handled erroneous data (#101)	2024-05-14 14:27:46 +08:00
zhengzangw	e1e379d898	[feat] update inference config	2024-05-14 05:40:17 +00:00
zhengzangw	3a01cb440d	[feat] inference for rf	2024-05-13 11:39:16 +00:00
zhengzangw	ff34f2bdaf	Merge branch 'dev/v1.2' of github.com:hpcaitech/Open-Sora-dev into dev/v1.2	2024-05-13 06:33:23 +00:00
zhengzangw	6194da6504	[fix] update inference and datautil	2024-05-13 06:33:12 +00:00
Shen Chenhui	b8d99d7a8b	fixed (#98) ... Co-authored-by: Shen-Chenhui <shen_chenhui@u.nus.edu>	2024-05-13 11:58:06 +08:00
zhengzangw	11faae8db6	[fix] exception handling for dataset	2024-05-12 14:08:37 +00:00
zhengzangw	74dfaa879c	[fix] ema ckpt save	2024-05-12 05:15:06 +00:00
zhengzangw	e870139f8f	Merge branch 'dev/v1.2' of github.com:hpcaitech/Open-Sora-dev into dev/v1.2	2024-05-10 03:19:48 +00:00
zhengzangw	1db24970d5	updated	2024-05-10 03:19:38 +00:00
Zangwei Zheng	4f27cb51fc	Merge branch 'main' into dev/v1.2	2024-05-09 16:49:24 +08:00
zhengzangw	2a55d672a7	[feat] update logging and bucket	2024-05-09 08:07:56 +00:00
Shen Chenhui	89a90e6b3d	Hotfix/latent size calc std (#96) ... * save progress * format * clean config --------- Co-authored-by: Shen-Chenhui <shen_chenhui@u.nus.edu>	2024-05-09 14:12:29 +08:00
zhengzangw	e9db7b3af1	update training script	2024-05-09 05:53:19 +00:00
zhengzangw	31228fe9c8	[refactor] fix train warnings	2024-05-09 03:10:26 +00:00
zhengzangw	322e566aed	update	2024-05-09 03:10:26 +00:00
Zangwei Zheng	eb5ff82fc5	quick update	2024-05-09 11:09:52 +08:00
zhangyongshun	2ec756a240	fix ar defination inconsistency (#375)	2024-05-08 19:48:56 +08:00
Shen Chenhui	dc7b7fd64a	fix bug (#95) ... Co-authored-by: Shen-Chenhui <shen_chenhui@u.nus.edu>	2024-05-08 17:39:21 +08:00
ChangeFWorld	338bd83f24	mask added, no test due to occupation of gpus (#90) ... * mask added, no test due to occupation of gpus * mask fix --------- Co-authored-by: ChangeFWorld <aicfw.li@gmail.com>	2024-05-08 16:32:36 +08:00
Zheng Zangwei (Alex Zheng)	f047d5786a	[refactor] clean train.py code (#94)	2024-05-08 16:07:57 +08:00
Frank Lee	82f15b30f9	fixed checkpoint (#92)	2024-05-07 18:34:22 +08:00
Frank Lee	fe19568a49	fixed race condition in exp workspace (#91)	2024-05-07 17:17:43 +08:00
Zangwei Zheng	fea2541c70	[docs] update readme	2024-05-07 16:27:21 +08:00
Zangwei Zheng	8564074229	[exp]	2024-05-07 15:41:52 +08:00
Frank Lee	06693a8187	fixed v3 train config (#89)	2024-05-07 15:13:20 +08:00
Zangwei Zheng	917643d5bd	[wip]	2024-05-07 14:51:11 +08:00
Shen-Chenhui	8e37e7d76e	Merge branch 'vae-clean-new' into dev/v1.2	2024-05-07 06:39:57 +00:00
FrankLeeeee	ec88d2d54e	resolved conflicts	2024-05-07 03:08:41 +00:00
Frank Lee	d599fd75b3	adapted pretrained model to training (#371)	2024-05-07 10:37:06 +08:00
Zangwei Zheng	10657621ef	[fix] random mask may have nothing to learn	2024-05-06 17:34:08 +08:00
Zangwei Zheng	c863c1d5e9	[exp] complete config	2024-05-06 16:56:46 +08:00
Shen-Chenhui	1522f683b8	fix padding	2024-05-06 07:49:56 +00:00
Shen-Chenhui	041b14f138	fix padding error;add chunck inference script	2024-05-06 07:47:12 +00:00
Zangwei Zheng	eefb351333	[exp] update config bucket	2024-05-06 14:32:28 +08:00
Frank Lee	19911b99b8	converted model to hf format (#366)	2024-05-06 14:15:04 +08:00