diff --git a/paddleocr.py b/paddleocr.py index ccb02cfdd..c10fdd460 100644 --- a/paddleocr.py +++ b/paddleocr.py @@ -732,6 +732,9 @@ class PaddleOCR(predict_system.TextSystem): - For PDF files, if the input is a list of images and the page_num is specified, only the first page_num images will be processed. - The preprocess_image function is used to preprocess the input image by applying alpha color replacement, inversion, and binarization if specified. """ + assert ( + det or rec or cls + ), "det and rec and cls can not be False at the same time" assert isinstance(img, (np.ndarray, list, str, bytes)) if isinstance(img, list) and det == True: logger.error("When input a list of images, det must be false") @@ -781,7 +784,7 @@ class PaddleOCR(predict_system.TextSystem): tmp_res = [box.tolist() for box in dt_boxes] ocr_res.append(tmp_res) return ocr_res - else: + elif rec or cls: ocr_res = [] cls_res = [] for img in imgs: @@ -792,11 +795,15 @@ class PaddleOCR(predict_system.TextSystem): img, cls_res_tmp, elapse = self.text_classifier(img) if not rec: cls_res.append(cls_res_tmp) + continue rec_res, elapse = self.text_recognizer(img) ocr_res.append(rec_res) if not rec: return cls_res return ocr_res + else: + logger.error("det and rec and cls can not be False at the same time") + exit(0) class PPStructure(StructureSystem):