未验证 提交 1d98ced0 编写于 作者: B BreezeDeus 提交者: GitHub

Merge pull request #8 from breezedeus/dev

fix readme
......@@ -71,9 +71,11 @@ res = ocr.ocr_for_single_line('examples/rand_cn1.png')
print("Predicted Chars:", res)
```
With file [examples/multi-line_cn1.png](./examples/multi-line_cn1.png)
![examples/rand_cn1.png](./examples/rand_cn1.png)
You will get:
you will get:
```python
Predicted Chars: ['笠', '淡', '嘿', '骅', '谧', '鼎', '皋', '姚', '歼', '蠢', '驼', '耳', '胬', '挝', '涯', '狗', '蒽', '子', '犷']
......
......@@ -107,7 +107,7 @@ python scripts/cnocr_train.py --cpu 2 --num_proc 4 --loss ctc --dataset cn_ocr
## 未来工作
* [x] support multi-line-characters recognition
* [x] 支持图片包含多行文字
* 支持`空格`识别
* 修bugs(目前代码还比较凌乱。。)
* 完善测试用例
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册