From 4a913ce61edb7bb201c175ff4f9d641205e3eed2 Mon Sep 17 00:00:00 2001 From: Furqanil Taqwa <50163983+Linaqruf@users.noreply.github.com> Date: Tue, 28 Nov 2023 17:22:35 +0700 Subject: [PATCH] initialize keep_tokens_separator to dataset config --- library/config_util.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/library/config_util.py b/library/config_util.py index ab90fb63..47868f3b 100644 --- a/library/config_util.py +++ b/library/config_util.py @@ -53,6 +53,7 @@ class BaseSubsetParams: shuffle_caption: bool = False caption_separator: str = ',', keep_tokens: int = 0 + keep_tokens_separator: str = None, color_aug: bool = False flip_aug: bool = False face_crop_aug_range: Optional[Tuple[float, float]] = None @@ -160,6 +161,7 @@ class ConfigSanitizer: "random_crop": bool, "shuffle_caption": bool, "keep_tokens": int, + "keep_tokens_separator": str, "token_warmup_min": int, "token_warmup_step": Any(float,int), "caption_prefix": str, @@ -461,6 +463,7 @@ def generate_dataset_group_by_blueprint(dataset_group_blueprint: DatasetGroupBlu num_repeats: {subset.num_repeats} shuffle_caption: {subset.shuffle_caption} keep_tokens: {subset.keep_tokens} + keep_tokens_separator: {subset.keep_tokens_separator} caption_dropout_rate: {subset.caption_dropout_rate} caption_dropout_every_n_epoches: {subset.caption_dropout_every_n_epochs} caption_tag_dropout_rate: {subset.caption_tag_dropout_rate}