The bbox return by model have wrong x,y co-ordinates

#28
by rdhoundiyal - opened

Hi, I am new to this, I have used the model, it is identifying the text correctly, but the bbox returned is not the actual x,y co-ordinates of the screen elements, I have check the output image and placed it in photoshop, the x,y co-ordinates are different, than given by model. What am I missing here?

def get_som_labeled_img(img_path, model=None, BOX_TRESHOLD = 0.01, output_coord_in_ratio=False, ocr_bbox=None, text_scale=0.4, text_padding=5, draw_bbox_config=None, caption_model_processor=None, ocr_text=[], use_local_semantics=True, iou_threshold=0.9,prompt=None,imgsz=640):

output_coord_in_ratio=False

thanks its working

rdhoundiyal changed discussion status to closed

Sign up or log in to comment