f90d8e5b53
data loader tweaks
2023-04-18 22:11:51 -04:00
e3e30a5599
fix exif issues
2023-04-16 14:53:34 -04:00
3697b16344
put exif transpose back in preloading to fix bug
2023-04-16 02:19:27 -04:00
b8f637873f
removing the convert_rgb flag for a simpler design
2023-04-14 20:21:48 -05:00
a839180199
set # of data loaders by the min of batch size or cpu count, do not do an rg b conversion when only loading image metadata
2023-04-14 14:59:28 -05:00
2bb35eaa0a
Use filenames for caption if no main prompt in yaml
2023-04-14 00:59:26 +02:00
dd98ebe080
Add error handling for bad exif, and rotate before sizing
2023-03-28 19:19:08 +02:00
56256ab9ef
attempt to catch some errors reported on github
2023-03-26 11:52:49 -04:00
35d52b56e0
added some resolutions, option for val-loss pos-neg, fix wandb
2023-03-25 20:09:06 -04:00
cdafa2dc43
Avoid unnecessary iteration over files in folder
2023-03-21 12:09:52 +01:00
161e0a563c
Prioritize tags, `image > local > global`, but respect weights
2023-03-21 00:15:53 +01:00
fae0b3c535
Retain original tag order when parsing captions
2023-03-19 23:30:42 +01:00
5afd75fd98
try-except around preloading items to help troubleshoot issues
2023-03-18 22:27:09 -04:00
f01a7354f0
remove sort from dataset due to slowdown on large sets, add contribution readme
2023-03-18 22:24:03 -04:00
48f132554c
Assign default value for MAX_CAPTION_LENGTH
2023-03-15 21:52:32 +01:00
ba687de8b4
add pbar back to preloading, remove cruft from testing loss stuff
2023-03-15 12:06:29 -04:00
605716a646
conf
2023-03-15 11:22:40 -04:00
da3c183cc5
autofix exif orientation
2023-03-15 11:12:59 -04:00
493afc3f20
Merge pull request #106 from qslug/enhanced-config
...
Add support for enhanced dataset configuration
2023-03-14 01:28:54 -04:00
7e20a74586
Fix cond_dropout and rating handling
2023-03-13 00:36:59 +01:00
dea8c6e862
Refactor dataset to support multiple main_prompts
...
...rather than multiple whole captions
2023-03-12 19:48:15 +01:00
f0111a6e2b
make validation more comparable across runs
2023-03-09 08:21:59 +01:00
0716c40ab6
Add support for enhanced dataset configuration
...
Add support for:
* flip_p.txt
* cond_dropout.txt
* local.yaml consolidated config (including default captions)
* global.yaml consolidated config which applies recursively to subfolders
* flip_p, and cond_dropout config per image
* manifest.json with full image-level configuration
2023-03-08 15:02:14 +01:00
2e3d044ba3
Merge branch 'main' of https://github.com/victorchall/EveryDream2trainer
2023-03-04 15:09:31 -05:00
87ffb5413e
log warning when val/loss is showing upward trend
2023-03-04 15:08:47 -05:00
e2fd45737d
overwrite args.seed with the actual seed if -1 is passed (so it appears in tensorboard)
...
also improve logging when unet training is disabled
2023-03-02 22:52:33 +01:00
61558be2ae
logging and progress bar improvements
2023-03-02 18:29:28 +01:00
8abef6bc74
revert multiline txt for now due to bug
2023-02-28 21:14:19 -05:00
6c87af7711
doc, fix lr defaulting bug, notdreambooth.md, read multicaption from .txt by line
2023-02-26 19:11:42 -05:00
e7fc71ffa1
Merge pull request #92 from victorchall/lion
...
fix mem leak on huge data, rework optimizer to separate json, add lio…
2023-02-25 16:20:10 -05:00
a9b0189947
fix mem leak on huge data, rework optimizer to separate json, add lion optimizer
2023-02-25 15:05:22 -05:00
be8cdf8af8
actually use validation seed 😭 also fix log of sample negative prompt
2023-02-20 21:58:46 +01:00
7956e24b61
fix division by zero
2023-02-19 10:25:38 +01:00
8a8a4cf3df
make val optional, revert multiply algo
2023-02-08 13:04:12 -05:00
19347bcaa8
make fractional multiplier logic apply per-directory
2023-02-08 14:15:54 +01:00
a7b00e9ef3
fix multiplier logic
2023-02-08 13:46:58 +01:00
4e37200dda
fix multiplier issues with validation and refactor validation logic
2023-02-08 11:28:45 +01:00
bca1e6e594
consistent spelling
2023-02-07 18:21:05 +01:00
e2d9600e34
cleaner config handling
2023-02-07 18:18:21 +01:00
dad9e347ff
log ed batch name on creation
2023-02-07 18:08:19 +01:00
f0d7310c12
clarify init function names
2023-02-07 17:54:00 +01:00
c3d844a1bc
better config handling
2023-02-07 17:52:23 +01:00
29396ec21b
update EveryDreamValidator for noprompt's changes
2023-02-07 17:46:30 +01:00
41c9f36ed7
GH-36: Add support for validation split (WIP)
...
Co-authored-by: Damian Stewart <office@damianstewart.com>
2023-02-06 22:10:34 -08:00
85f19b9a2f
doc and bug with undersized
2023-02-06 13:11:24 -05:00
56f130c027
Forgot to add train.py earlier 🤦 ; move write_batch_schedule to train.py
2023-01-29 18:11:34 -08:00
12a0cb6286
Update documentation
2023-01-29 17:58:42 -08:00
3fe335f328
Update documentation
2023-01-29 17:47:10 -08:00
c0ec46c030
Don't need to set data loader singleton; formatting tweaks
2023-01-29 17:31:57 -08:00
326d861a86
Push DLMA into main, pass config to resolve
...
This patch
* passes the configuration (`argparse.Namespace`) to the resolver,
* pushes the DLMA code into the main function,
* makes DLMA take a `list[ImageTrainItem]` instead of `data_root`,
* makes `EveryDreamBatch` take `DLMA` instead of `data_root`, etc.
* allows `data_root` to be a list.
By doing these things, both `EveryDreamBatch` and DLMA can be free from
data resolution logic. It also reduces the number of arguments which
need to be passed down to EDB and DLMA.
2023-01-29 17:08:54 -08:00
Victor Hall