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

remove unnessary img save

Browse Source
This commit is contained in:
yadonglu
2025-03-10 09:06:00 -07:00
parent 547cb8f743
commit f5fcdf40e6
1 changed files with 3 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
gradio_demo.py
View File

@@ -40,10 +40,7 @@ def process(
imgsz
) -> Optional[Image.Image]:
image_save_path = 'imgs/saved_image_demo.png'
image_input.save(image_save_path)
image = Image.open(image_save_path)
box_overlay_ratio = image.size[0] / 3200
box_overlay_ratio = image_input.size[0] / 3200
draw_bbox_config = {
'text_scale': 0.8 * box_overlay_ratio,
'text_thickness': max(int(2 * box_overlay_ratio), 1),
@@ -52,10 +49,9 @@ def process(
}
# import pdb; pdb.set_trace()
ocr_bbox_rslt, is_goal_filtered = check_ocr_box(image_save_path, display_img = False, output_bb_format='xyxy', goal_filtering=None, easyocr_args={'paragraph': False, 'text_threshold':0.9}, use_paddleocr=use_paddleocr)
ocr_bbox_rslt, is_goal_filtered = check_ocr_box(image_input, display_img = False, output_bb_format='xyxy', goal_filtering=None, easyocr_args={'paragraph': False, 'text_threshold':0.9}, use_paddleocr=use_paddleocr)
text, ocr_bbox = ocr_bbox_rslt
# print('prompt:', prompt)
dino_labled_img, label_coordinates, parsed_content_list = get_som_labeled_img(image_save_path, yolo_model, BOX_TRESHOLD = box_threshold, output_coord_in_ratio=True, ocr_bbox=ocr_bbox,draw_bbox_config=draw_bbox_config, caption_model_processor=caption_model_processor, ocr_text=text,iou_threshold=iou_threshold, imgsz=imgsz,)
dino_labled_img, label_coordinates, parsed_content_list = get_som_labeled_img(image_input, yolo_model, BOX_TRESHOLD = box_threshold, output_coord_in_ratio=True, ocr_bbox=ocr_bbox,draw_bbox_config=draw_bbox_config, caption_model_processor=caption_model_processor, ocr_text=text,iou_threshold=iou_threshold, imgsz=imgsz,)
image = Image.open(io.BytesIO(base64.b64decode(dino_labled_img)))
print('finish processing')
parsed_content_list = '\n'.join([f'icon {i}: ' + str(v) for i,v in enumerate(parsed_content_list)])