frotms / PaddleOCR2Pytorch

PaddleOCR inference in PyTorch. Converted from [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
Apache License 2.0
809 stars 159 forks source link

使用英文模型, 识别结果为中文的情况 #52

Open yaoing opened 1 year ago

yaoing commented 1 year ago

作者好, 我尝试用 ./tools/infer/predict_system.py 来串联识别英文, 检测模型用的是en_ptocr_v3_det_infer.pth, 识别模型分别试用了en_ptocr_v3_rec_infer.pthen_number_mobile_v2.0_rec_infer.pth, 但是返回的结果都是中文~

dt_boxes num : 2, elapse : 0.0470426082611084
rec_res num  : 2, elapse : 0.06331539154052734
Predict time of ../tess_train/data/1.jpg: 0.112s
房韵, 0.996
rec_res num  : 2, elapse : 0.06833672523498535
Predict time of ../tess_train/data/1.jpg: 0.127s
房韵, 0.755

求助~

frotms commented 1 year ago

需要设置字库为相应的英文字库,--rec_char_dict_path

yaoing commented 1 year ago

好的, 明白~