Dom/OmniParser
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

move back to check_ocr_box

Browse Source
This commit is contained in:
Thomas Dhome-Casanova
2025-01-27 22:38:05 -08:00
parent 9cb2263545
commit 72040b9ded
2 changed files with 21 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
demo/remote_request.py
View File

@@ -4,7 +4,7 @@ import sys
import os
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
from utils import get_som_labeled_img, get_caption_model_processor, get_yolo_model, get_ocr_bbox
from utils import get_som_labeled_img, get_caption_model_processor, get_yolo_model, check_ocr_box
import torch
from PIL import Image
from typing import Dict, Tuple, List
@@ -45,7 +45,7 @@ class Omniparser(object):
}
BOX_TRESHOLD = config['BOX_TRESHOLD']
text, ocr_bbox = get_ocr_bbox(image)
(text, ocr_bbox), _ = check_ocr_box(image, display_img=False, output_bb_format='xyxy', easyocr_args={'text_threshold': 0.8}, use_paddleocr=False)
dino_labled_img, label_coordinates, parsed_content_list = get_som_labeled_img(image, self.som_model, BOX_TRESHOLD = BOX_TRESHOLD, output_coord_in_ratio=True, ocr_bbox=ocr_bbox,draw_bbox_config=draw_bbox_config, caption_model_processor=self.caption_model_processor, ocr_text=text,use_local_semantics=True, iou_threshold=0.7, scale_img=False, batch_size=128)
return dino_labled_img, parsed_content_list