breezedeus / CnOCR

CnOCR: Awesome Chinese/English OCR Python toolkits based on PyTorch. It comes with 20+ well-trained models for different application scenarios and can be used directly after installation. 【基于 PyTorch/MXNet 的中文/英文 OCR Python 包。】

Home Page:https://www.breezedeus.com/article/cnocr

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

似乎纯英文无法识别

Hodoio opened this issue · comments

commented

789
这是我的配置与想要识别的图片,我得到的结果是这样的:

       [     342.27,      20.185],
       [     342.27,      39.492],
       [     14.042,      39.492]], dtype=float32)}, {'text': '', 'score': 0.9859431982040405, 'position': array([[     14.956,      63.328],
       [     344.06,      64.614],
       [     343.99,      84.624],
       [     14.878,      83.338]], dtype=float32)}, {'text': '', 'score': 0.9859431982040405, 'position': array([[     14.063,      107.09],
       [     465.15,      108.01],
       [     465.11,       126.4],
       [     14.026,      125.48]], dtype=float32)}, {'text': '', 'score': 0.9859431982040405, 'position': array([[     14.947,      150.51],
       [     416.89,      151.63],
       [     416.84,      171.35],
       [     14.892,      170.23]], dtype=float32)}, {'text': '', 'score': 0.9859431982040405, 'position': array([[     14.972,      191.94],
       [     668.79,       194.7],
       [      668.7,      215.99],
       [     14.882,      213.23]], dtype=float32)}, {'text': '', 'score': 0.9859431982040405, 'position': array([[     14.942,      238.06],
       [     658.23,      239.61],
       [     658.18,      259.68],
       [     14.894,      258.13]], dtype=float32)}]```

显然不可能不支持英文啊,关注下运行过程中的报错吧。可以在 Demo 试效果。

image