python 脚本检测结果与网页版本和c++版本的不一致

[Morgan]

请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
我用python https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.5/doc/doc_ch/quickstart.md 能很快检测出字符,但是用网页https://www.paddlepaddle.org.cn/hub/scene/ocr 和c++ https://github.com/PaddlePaddle/PaddleOCR/tree/release/2.5/deploy/cpp_infer 的就不识别,都是用的PP-OCRv3为什么结果会不一样呢?

• 系统环境/System Environment：win10
• 版本号/Version：Paddle：2.3.0 PaddleOCR： 2.5.0.3 问题相关组件/Related components：

(PP) C:\Users\dell>paddleocr --image_dir E:\Work\1.jpg --det false
[2022/06/20 19:09:13] ppocr DEBUG: Namespace(help='==SUPPRESS==', use_gpu=False, ir_optim=True, use_tensorrt=False, min_subgraph_size=15, precision='fp32', gpu_mem=500, image_dir='E:\\Work\\1.jpg', det_algorithm='DB', det_model_dir='C:\\Users\\dell/.paddleocr/whl\\det\\ch\\ch_PP-OCRv3_det_infer', det_limit_side_len=960, det_limit_type='max', det_db_thresh=0.3, det_db_box_thresh=0.6, det_db_unclip_ratio=1.5, max_batch_size=10, use_dilation=False, det_db_score_mode='fast', det_east_score_thresh=0.8, det_east_cover_thresh=0.1, det_east_nms_thresh=0.2, det_sast_score_thresh=0.5, det_sast_nms_thresh=0.2, det_sast_polygon=False, det_pse_thresh=0, det_pse_box_thresh=0.85, det_pse_min_area=16, det_pse_box_type='quad', det_pse_scale=1, scales=[8, 16, 32], alpha=1.0, beta=1.0, fourier_degree=5, det_fce_box_type='poly', rec_algorithm='SVTR_LCNet', rec_model_dir='C:\\Users\\dell/.paddleocr/whl\\rec\\ch\\ch_PP-OCRv3_rec_infer', rec_image_shape='3, 48, 320', rec_batch_num=6, max_text_length=25, rec_char_dict_path='E:\\Anaconda\\lib\\site-packages\\paddleocr\\ppocr\\utils\\ppocr_keys_v1.txt', use_space_char=True, vis_font_path='./doc/fonts/simfang.ttf', drop_score=0.5, e2e_algorithm='PGNet', e2e_model_dir=None, e2e_limit_side_len=768, e2e_limit_type='max', e2e_pgnet_score_thresh=0.5, e2e_char_dict_path='./ppocr/utils/ic15_dict.txt', e2e_pgnet_valid_set='totaltext', e2e_pgnet_mode='fast', use_angle_cls=False, cls_model_dir='C:\\Users\\dell/.paddleocr/whl\\cls\\ch_ppocr_mobile_v2.0_cls_infer', cls_image_shape='3, 48, 192', label_list=['0', '180'], cls_batch_num=6, cls_thresh=0.9, enable_mkldnn=False, cpu_threads=10, use_pdserving=False, warmup=False, draw_img_save_dir='./inference_results', save_crop_res=False, crop_res_save_dir='./output', use_mp=False, total_process_num=1, process_id=0, benchmark=False, save_log_path='./log_output/', show_log=True, use_onnx=False, output='./output', table_max_len=488, table_model_dir=None, table_char_dict_path=None, layout_path_model='lp://PubLayNet/ppyolov2_r50vd_dcn_365e_publaynet/config', layout_label_map=None, mode='structure', layout=True, table=True, ocr=True, lang='ch', det=False, rec=True, type='ocr', ocr_version='PP-OCRv3', structure_version='PP-STRUCTURE')
[2022/06/20 19:09:16] ppocr INFO: **********E:\Work\1.jpg**********
[2022/06/20 19:09:18] ppocr INFO: ('22E302V', 0.9865360260009766)

原图

[littletomatodonkey]

你好，二者的模型和后处理超参数不太相同