VictorMylle/Kohya-ss-sd-scripts
1
0
Fork 1
mirror of https://github.com/kohya-ss/sd-scripts.git synced 2026-04-08 22:35:09 +00:00
Code Issues Packages Projects Releases Wiki Activity

add arbitrary dataset feature to each script

Browse Source
This commit is contained in:
Kohya S
2023-06-15 20:39:39 +09:00
parent f2989b36c2
commit 9806b00f74
6 changed files with 115 additions and 92 deletions
Download Patch File Download Diff File Expand all files Collapse all files

54
fine_tune.py
View File

@@ -42,33 +42,37 @@ def train(args):
tokenizer = train_util.load_tokenizer(args)
blueprint_generator = BlueprintGenerator(ConfigSanitizer(False, True, True))
if args.dataset_config is not None:
print(f"Load dataset config from {args.dataset_config}")
user_config = config_util.load_user_config(args.dataset_config)
ignored = ["train_data_dir", "in_json"]
if any(getattr(args, attr) is not None for attr in ignored):
print(
"ignore following options because config file is found: {0} / 設定ファイルが利用されるため以下のオプションは無視されます: {0}".format(
", ".join(ignored)
# データセットを準備する
if args.dataset_class is None:
blueprint_generator = BlueprintGenerator(ConfigSanitizer(False, True, True))
if args.dataset_config is not None:
print(f"Load dataset config from {args.dataset_config}")
user_config = config_util.load_user_config(args.dataset_config)
ignored = ["train_data_dir", "in_json"]
if any(getattr(args, attr) is not None for attr in ignored):
print(
"ignore following options because config file is found: {0} / 設定ファイルが利用されるため以下のオプションは無視されます: {0}".format(
", ".join(ignored)
)
)
)
else:
user_config = {
"datasets": [
{
"subsets": [
{
"image_dir": args.train_data_dir,
"metadata_file": args.in_json,
}
]
}
]
}
else:
user_config = {
"datasets": [
{
"subsets": [
{
"image_dir": args.train_data_dir,
"metadata_file": args.in_json,
}
]
}
]
}
blueprint = blueprint_generator.generate(user_config, args, tokenizer=tokenizer)
train_dataset_group = config_util.generate_dataset_group_by_blueprint(blueprint.dataset_group)
blueprint = blueprint_generator.generate(user_config, args, tokenizer=tokenizer)
train_dataset_group = config_util.generate_dataset_group_by_blueprint(blueprint.dataset_group)
else:
train_dataset_group = train_util.load_arbitrary_dataset(args, tokenizer)
current_epoch = Value("i", 0)
current_step = Value("i", 0)