VictorMylle/Kohya-ss-sd-scripts
1
0
Fork 1
mirror of https://github.com/kohya-ss/sd-scripts.git synced 2026-04-09 06:45:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add cleaning patterns

Browse Source
This commit is contained in:
Kohya S
2023-02-03 21:04:37 +09:00
parent 58a809eaff
commit 73d612ff9c
1 changed files with 15 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
finetune/make_captions_by_git.py
View File

@@ -13,17 +13,26 @@ import library.train_util as train_util
DEVICE = torch.device('cuda' if torch.cuda.is_available() else 'cpu') DEVICE = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
PATTERN_REPLACE = [re.compile(r'with the (words?|letters?) (" ?[^"]*"|\w+)( on (the)? ?\w+)?'), PATTERN_REPLACE = [
re.compile(r'that says (" ?[^"]*"|\w+)')] re.compile(r'(has|with|and) the (words?|letters?|name) (" ?[^"]*"|\w+)( ?(is )?(on|in) (the |her |their |him )?\w+)?'),
re.compile(r'(with a sign )?that says ?(" ?[^"]*"|\w+)( ?on it)?'),
re.compile(r"(with a sign )?that says ?(' ?(i'm)?[^']*'|\w+)( ?on it)?"),
re.compile(r'with the number \d+ on (it|\w+ \w+)'),
re.compile(r'with the words "'),
re.compile(r'word \w+ on it'),
re.compile(r'that says the word \w+ on it'),
re.compile('that says\'the word "( on it)?'),
]
# 誤検知しまくりの with the word xxxx を消す # 誤検知しまくりの with the word xxxx を消す
def remove_words(captions, debug): def remove_words(captions, debug):
removed_caps = [] removed_caps = []
for caption in captions: for caption in captions:
cap = caption cap = caption
for pat in PATTERN_REPLACE: for pat in PATTERN_REPLACE:
cap = pat.sub("", caption) cap = pat.sub("", cap)
if debug and cap != caption: if debug and cap != caption:
print(caption) print(caption)
print(cap) print(cap)