SWHL
commented
3 months ago 看你勾选了愿意提交PR来修复这个问题，期待你的PR哈
Closed bbg221 closed 3 months ago
SWHL
commented
3 months ago 看你勾选了愿意提交PR来修复这个问题，期待你的PR哈
Gmgge
commented
3 months ago 我看到你的日志中rec_char_dict_path='D:\myown\baidupaddle\paddleocr_py39\lib\site-packages\paddleocr\ppocr\utils\ppocr_keys_v1.txt'，请确认是否切换繁体识别的字典？
根据官方文档描述，更换繁体识别模型对应字典为：ppocr/utils/dict/chinese_cht_dict.txt | 中文繁体识别
bbg221
commented
3 months ago 我看到你的日志中rec_char_dict_path='D:\myown\baidupaddle\paddleocr_py39\lib\site-packages\paddleocr\ppocr\utils\ppocr_keys_v1.txt'，请确认是否切换繁体识别的字典？
根据官方文档描述，更换繁体识别模型对应字典为：ppocr/utils/dict/chinese_cht_dict.txt | 中文繁体识别 非常感谢，切换字典后正常了。
from paddleocr import PaddleOCR, draw_ocr
ocr = PaddleOCR(use_angle_cls=True, lang="ch", use_gpu=False, det_model_dir=r'D:\myown\baidupaddle\modela', rec_model_dir=r'D:\myown\baidupaddle\modelb', cls_model_dir=r'D:\myown\baidupaddle\modelc', rec_char_dict_path=r'D:\myown\baidupaddle\paddleocr_py39\Lib\site-packages\paddleocr\ppocr\utils\dict\chinese_cht_dict.txt' ) impath = './b.jpg' r = ocr.ocr(impath, cls=True) print (r)
bbg221
commented
3 months ago [[[[[45.0, 13.0], [78.0, 13.0], [77.0, 566.0], [44.0, 566.0]], ('東風起日落汀洲一望時愁情不斷如春水人日', 0.9933711886405945)], [[[90.0, 14.0], [120.0, 14.0], [121.0, 566.0], [91.0, 566.0]], ('汀洲人未歸其二一日杏省煙波隔千黑白蘋香散', 0.8930906057357788)], [[[138.0, 12.0], [168.0, 12.0], [166.0, 566.0], [136.0, 566.0]], ('孤村芳草遠斜日杏花飛江南春畫離陽斷 頻濤', 0.9436619281768799)], [[[176.0, 10.0], [213.0, 10.0], [215.0, 568.0], [178.0, 568.0]], ('傷為主當為江南表二施其一日波泓泓郴欣依', 0.8255800604820251)], [[[266.0, 10.0], [302.0, 10.0], [306.0, 541.0], [270.0, 542.0]], ('無人渡孤舟畫日橫到海尺十黑過山應萬重', 0.9826182126998901)], [[[317.0, 13.0], [346.0, 13.0], [346.0, 542.0], [317.0, 542.0]], ('方前代羅江東趙渭南也錄公警策之篇岩遠', 0.9869053959846497)], [[[362.0, 14.0], [391.0, 14.0], [391.0, 568.0], [362.0, 568.0]], ('公之墓序初知巴東日詩家者流目海冠巴東以', 0.9445298910140991)], [[[406.0, 12.0], [436.0, 12.0], [437.0, 570.0], [407.0, 570.0]], ('不欽噗故樞相文康即公之婿實有道之士焉志', 0.9343686103820801)], [[[264.0, 541.0], [307.0, 541.0], [307.0, 563.0], [264.0, 563.0]], ('詩此', 0.9987170696258545)], [[[322.0, 538.0], [344.0, 545.0], [339.0, 564.0], [316.0, 557.0]], ('K', 0.5856369733810425)]]]
Search before asking
[X] I have searched the PaddleOCR Docs and found no similar bug report.
[X] I have searched the PaddleOCR Issues and found no similar bug report.
[X] I have searched the PaddleOCR Discussions and found no similar bug report.
Bug
from paddleocr import PaddleOCR, draw_ocr
ocr = PaddleOCR(use_angle_cls=True, lang="ch", use_gpu=False, det_model_dir=r'D:\myown\baidupaddle\modela', rec_model_dir=r'D:\myown\baidupaddle\modelb', cls_model_dir=r'D:\myown\baidupaddle\modelc' ) impath = './b.jpg' r = ocr.ocr(impath, cls=True) print (r)
我从https://github.com/PaddlePaddle/PaddleOCR/blob/main/doc/doc_ch/models_list.md下载了中文繁体识别模型，然后解压后替换到了rec_model_dir里边，重新运行就报错： (paddleocr_py39) PS D:\myown\baidupaddle> python .\paddleocr_test.py [2024/08/05 08:38:52] ppocr DEBUG: Namespace(help='==SUPPRESS==', use_gpu=False, use_xpu=False, use_npu=False, use_mlu=False, ir_optim=True, use_tensorrt=False, min_subgraph_size=15, precision='fp32', gpu_mem=500, gpu_id=0, image_dir=None, page_num=0, det_algorithm='DB', det_model_dir='D:\myown\baidupaddle\modela', det_limit_side_len=960, det_limit_type='max', det_box_type='quad', 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_pse_thresh=0, det_pse_box_thresh=0.85, det_pse_min_area=16, det_pse_scale=1, scales=[8, 16, 32], alpha=1.0, beta=1.0, fourier_degree=5, rec_algorithm='SVTR_LCNet', rec_model_dir='D:\myown\baidupaddle\modelb', rec_image_inverse=True, rec_image_shape='3, 48, 320', rec_batch_num=6, max_text_length=25, rec_char_dict_path='D:\myown\baidupaddle\paddleocr_py39\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=True, cls_model_dir='D:\myown\baidupaddle\modelc', 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, sr_model_dir=None, sr_image_shape='3, 32, 128', sr_batch_num=1, 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, return_word_box=False, output='./output', table_max_len=488, table_algorithm='TableAttn', table_model_dir=None, merge_no_span_structure=True, table_char_dict_path=None, layout_model_dir=None, layout_dict_path=None, layout_score_threshold=0.5, layout_nms_threshold=0.5, kie_algorithm='LayoutXLM', ser_model_dir=None, re_model_dir=None, use_visual_backbone=True, ser_dict_path='../train_data/XFUND/class_list_xfun.txt', ocr_order_method=None, mode='structure', image_orientation=False, layout=True, table=True, ocr=True, recovery=False, use_pdf2docx_api=False, invert=False, binarize=False, alphacolor=(255, 255, 255), lang='ch', det=True, rec=True, type='ocr', savefile=False, ocr_version='PP-OCRv4', structure_version='PP-StructureV2') [2024/08/05 08:38:53] ppocr DEBUG: dt_boxes num : 12, elapsed : 0.19106101989746094 [2024/08/05 08:38:53] ppocr DEBUG: cls num : 12, elapsed : 0.061598777770996094 Traceback (most recent call last): File "D:\myown\baidupaddle\paddleocr_test.py", line 29, in
r = ocr.ocr(impath, cls=True)
File "D:\myown\baidupaddle\paddleocr_py39\lib\site-packages\paddleocr\paddleocr.py", line 729, in ocr
dt_boxes, recres, = self.call(img, cls, slice)
File "D:\myown\baidupaddle\paddleocr_py39\lib\site-packages\paddleocr\tools\infer\predict_system.py", line 144, in call
rec_res, elapse = self.text_recognizer(img_crop_list)
File "D:\myown\baidupaddle\paddleocr_py39\lib\site-packages\paddleocr\tools\infer\predict_rec.py", line 689, in call
rec_result = self.postprocess_op(
File "D:\myown\baidupaddle\paddleocr_py39\lib\site-packages\paddleocr\ppocr\postprocess\rec_postprocess.py", line 206, in call
text = self.decode(
File "D:\myown\baidupaddle\paddleocr_py39\lib\site-packages\paddleocr\ppocr\postprocess\rec_postprocess.py", line 154, in decode
char_list = [
File "D:\myown\baidupaddle\paddleocr_py39\lib\site-packages\paddleocr\ppocr\postprocess\rec_postprocess.py", line 155, in
self.character[text_id] for text_id in text_index[batch_idx][selection]
IndexError: list index out of range
(paddleocr_py39) PS D:\myown\baidupaddle>
Environment
windows11 python39 AMD64
(paddleocr_py39) PS D:\myown\baidupaddle> pip list Package Version
anyio 4.4.0 astor 0.8.1 beautifulsoup4 4.12.3 certifi 2024.7.4 charset-normalizer 3.3.2 colorama 0.4.6 contourpy 1.2.1 cycler 0.12.1 Cython 3.0.10 decorator 5.1.1 exceptiongroup 1.2.2 fire 0.6.0 fonttools 4.53.1 h11 0.14.0 httpcore 1.0.5 httpx 0.27.0 idna 3.7 imageio 2.34.2 imgaug 0.4.0 importlib_resources 6.4.0 kiwisolver 1.4.5 lazy_loader 0.4 lmdb 1.5.1 lxml 5.2.2 matplotlib 3.9.1 networkx 3.2.1 numpy 1.26.4 opencv-contrib-python 4.10.0.84 opencv-python 4.10.0.84 opt-einsum 3.3.0 packaging 24.1 paddleocr 2.8.1 paddlepaddle 2.6.1 pillow 10.4.0 pip 22.0.4 protobuf 3.20.2 pyclipper 1.3.0.post5 pyparsing 3.1.2 python-dateutil 2.9.0.post0 python-docx 1.1.2 PyYAML 6.0.1 rapidfuzz 3.9.5 requests 2.32.3 scikit-image 0.24.0 scipy 1.13.1 setuptools 58.1.0 shapely 2.0.5 six 1.16.0 sniffio 1.3.1 soupsieve 2.5 termcolor 2.4.0 tifffile 2024.7.24 tqdm 4.66.4 typing_extensions 4.12.2 urllib3 2.2.2 zipp 3.19.2
Minimal Reproducible Example
from paddleocr import PaddleOCR, draw_ocr
ocr = PaddleOCR(use_angle_cls=True, lang="ch", use_gpu=False, det_model_dir=r'D:\myown\baidupaddle\modela', rec_model_dir=r'D:\myown\baidupaddle\modelb', cls_model_dir=r'D:\myown\baidupaddle\modelc' ) impath = './b.jpg' r = ocr.ocr(impath, cls=True) print (r)
Additional
No response
Are you willing to submit a PR?