Commit Graph

799 Commits

Author SHA1 Message Date
Victor Hall f369e534eb update cog doc 2024-04-02 16:36:26 -04:00
Victor Hall 7ea9676da8 enhance cog caption script 2024-04-02 16:35:49 -04:00
Victor Hall 65bd7b3b92 update windows setup cmd 2024-04-01 14:51:33 -04:00
Victor Hall 45ecb11402 update cog doc with colab link 2024-03-24 10:02:38 -04:00
Victor Hall 87bfe652ce caption cog notebook2 2024-03-24 10:00:00 -04:00
Victor Hall 93659f3eb4 caption cog notebook 2024-03-24 09:30:23 -04:00
Victor Hall 056de840d0 some cleanup/updates to caption stuff 2024-03-22 13:27:01 -04:00
Victor Hall 273ce23c7c update windows setup 2024-03-22 13:17:27 -04:00
Victor Hall 2525b62569 add peft to docker 2024-03-22 12:43:09 -04:00
Victor Hall 3a219e2502 update docker to fix cog 2024-03-22 12:41:14 -04:00
Victor Hall 642a64d5dc generator 2024-03-15 00:20:37 -04:00
Victor Hall 17054c9d10 patch cog to fix issue with transformers 2024-03-15 00:18:55 -04:00
Victor Hall 212d73f127 tiny doc update 2024-03-13 18:45:59 -04:00
Victor Hall d2a7a25da7 update caption_cog.py, transformers, and add peft 2024-03-13 18:38:55 -04:00
Victor Hall 776edcf9d9 update cog doc 2024-03-13 18:38:55 -04:00
Victor Hall 1cf110c6a5 fix caption cog plugin for image json reading 2024-03-13 18:26:13 -04:00
Victor Hall 80a6672b41 title and tags plugin for caption on per image json file basis 2024-03-13 18:03:58 -04:00
Victor Hall d0a979ff9a Merge branch 'main' of https://github.com/victorchall/EveryDream2trainer into main 2024-03-03 16:55:42 -05:00
Victor Hall a90e13a926 cleaner viewing for grounding ui 2024-03-03 16:55:30 -05:00
Victor Hall d2f435eaf1 another minor caption doc update 2024-03-03 16:36:54 -05:00
Victor Hall bd0acb57fd trying a cog colab notebook, and remove flamingo notebook since it is removed from repo 2024-03-03 16:36:54 -05:00
Victor Hall fdf230634e Merge branch 'main' of https://github.com/victorchall/EveryDream2trainer into main 2024-03-03 16:05:57 -05:00
Victor Hall 2a76dd2009 clean up text on bounding box drawing of grounding ui 2024-03-03 16:05:50 -05:00
Victor Hall 91a9b3d898 bugfix and doc fix 2024-03-03 15:47:44 -05:00
Victor Hall aca1867697 update caption docs and remove open flamingo script 2024-03-03 15:39:30 -05:00
Victor Hall 3256f9e33c add phrase grounding to kosmos2 caption script 2024-03-03 15:39:30 -05:00
Victor Hall a55ab816af really dumb ui for looking at grounding files from kosmos2 2024-03-03 15:13:08 -05:00
Victor Hall 8bab958c68 cog doc fix 2024-03-02 17:43:41 -05:00
Victor Hall 7993143022 documentation for new cog stuff 2024-03-02 17:42:25 -05:00
Victor Hall 42ad271261 bug in caption cog if starts_with no there 2024-03-02 01:58:13 -05:00
Victor Hall d098223052 merge conflict 2024-03-02 01:20:03 -05:00
Victor Hall be2cec7d3b
Update Train_Colab.ipynb 2024-02-23 11:33:09 -05:00
BlueBug e1e070ca83 Cough... fixed typo
me not trying to be a grammar villian but a helpful noob
2024-02-06 18:11:20 +09:00
BlueBug eee130d7dd Fixs error when translated caption contains an unusual byte
fixs this
File "D:\EveryDream2trainer\caption_cog.py", line 143, in main
    f.write(caption)
UnicodeEncodeError: 'cp949' codec can't encode character '\xe9' in position 333: illegal multibyte sequence
2024-02-06 17:49:21 +09:00
Victor Hall 5622b55128 fix up cog caption script 2024-02-03 22:01:14 -05:00
Victor Hall 1a8495a706 cleanup on cog caption script 2024-02-03 19:25:20 -05:00
Victor Hall cbc9a2d337
add cog-vlm to citations 2024-02-03 14:52:16 -05:00
Victor Hall f885be56a1 add cog caption script 2024-01-24 22:21:51 -05:00
Victor Hall 18198715b7
Merge pull request #246 from damian0815/patch-2
prevent OOM with disabled unet when gradient checkpointing is enabled
2024-01-15 20:11:52 -05:00
Damian Stewart 9fc6ae7a09
prevent OOM with disabled unet when gradient checkpointing is enabled
unet needs to be in train() mode for gradient checkpointing to work
2024-01-16 10:23:52 +13:00
Victor Hall e08d5ded98
Merge pull request #245 from Enixile/main
BLIP2 and GIT updates
2024-01-10 13:47:08 -05:00
Enixile 817f4169ce BLIP2 was loading into system RAM rather than VRAM for me. I found that adding argument "device_map=device" forces it to load the entire model onto the specified device. I tested it for cuda and cpu successfully.
GIT was failing because its processor returns a BatchEncoding and its method to() only accepts one device parameter, so I removed the second dtype parameter and it worked. I don't see how BLIP2 is different, but it works with both parameters, so I left it to avoid breaking any functionality.
2024-01-06 15:16:59 -05:00
Victor Hall e8f7b6c8b4 fix oopsie 2023-12-22 13:54:20 -05:00
Victor Hall e89ec053c7 fix issue with plugin interaction with validation 2023-12-22 13:52:26 -05:00
Victor Hall 9141710d6e add ps activate script 2023-12-21 14:02:36 -05:00
Victor Hall c7d3064029 error in dataloader plugin 2023-12-21 10:50:11 -05:00
Victor Hall 7a81182220
Update PLUGINS.md
update plugin docs
2023-12-20 16:46:44 -05:00
Victor Hall 1119c2130f
Update PLUGINS.md 2023-12-20 15:39:57 -05:00
Victor Hall 83623929ad
Update PLUGINS.md
add docs for dataloader plugin hooks
2023-12-20 15:29:33 -05:00
Victor Hall d9d2a43804 fix order of running pil image dataloader plugin 2023-12-20 15:24:09 -05:00