Skip to content

Commit

Permalink
Update docs
Browse files Browse the repository at this point in the history
  • Loading branch information
@SWHL
SWHL committed Sep 21, 2023
1 parent 27208d0 commit 0828d0d
Showing 1 changed file with 109 additions and 69 deletions.
178 changes: 109 additions & 69 deletions content/docs/install_usage/rapidocr_onnxruntime/usage.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -73,8 +73,79 @@ class RapidOCR:
res, elapse = engine(img, use_det=True, use_cls=True, use_rec=True)
```

### 灵活搭配
类RapidOCR在调用时，有三个参数`use_det | use_cls | use_rec`，可以控制是否使用检测、方向分类和识别这三部分。详细搭配如下：
### 输入
支持4种输入类型：`Union[str, np.ndarray, bytes, Path]`

{{< tabs tabTotal="4">}}
{{% tab tabName="str" %}}

```python {linenos=table}
from pathlib import Path

from rapidocr_onnxruntime import RapidOCR

engine = RapidOCR()

img_path = 'tests/test_files/ch_en_num.jpg'
result, elapse = engine(img_path)
print(result)
print(elapse)
```

{{% /tab %}}
{{% tab tabName="np.ndarray" %}}

```python {linenos=table}
from pathlib import Path

import cv2
from rapidocr_onnxruntime import RapidOCR

engine = RapidOCR()
img = cv2.imread('tests/test_files/ch_en_num.jpg')
result, elapse = engine(img)
print(result)
print(elapse)
```

{{% /tab %}}
{{% tab tabName="Bytes" %}}

```python {linenos=table}
from pathlib import Path

from rapidocr_onnxruntime import RapidOCR

engine = RapidOCR()

img_path = 'tests/test_files/ch_en_num.jpg'
with open(img_path, 'rb') as f:
img = f.read()
result, elapse = engine(img)
print(result)
print(elapse)
```

{{% /tab %}}
{{% tab tabName="Path" %}}

```python {linenos=table}
from pathlib import Path

from rapidocr_onnxruntime import RapidOCR

engine = RapidOCR()

img_path = Path('tests/test_files/ch_en_num.jpg')
result, elapse = engine(img_path)
print(result)
print(elapse)
```
{{% /tab %}}
{{< /tabs >}}

### 输出
类RapidOCR在调用时，有三个参数`use_det | use_cls | use_rec`，可以控制是否使用检测、方向分类和识别这三部分。不同的参数，决定了不同的输出，详细搭配如下：

{{< tabs tabTotal="3">}}
{{% tab tabName="只有检测" %}}
Expand All @@ -92,7 +163,7 @@ print(result)
print(elapse)
```

返回值为: `List[List[float]]` (每个框的坐标`[左上角x,y, 右下角x,y]`)
返回值`result`: `List[List[float]]` (每个框的坐标`[左上, 右上, 右下, 左下]`)
```python
[
[[5.0, 2.0], [322.0, 9.0], [319.0, 103.0], [3.0, 96.0]],
Expand All @@ -117,7 +188,7 @@ result, elapse = engine(img_path, use_det=False, use_cls=True, use_rec=False)
print(result)
print(elapse)
```
返回值为: `List[List[str, float]]` (`[方向0或180, 置信度]`)
返回值`result`: `List[List[str, float]]` (`[方向0或180, 置信度]`)
```python
[
['0', 0.9998784],
Expand All @@ -140,7 +211,7 @@ result, elapse = engine(img_path, use_det=False, use_cls=False, use_rec=True)
print(result)
print(elapse)
```
返回值为: `List[List[str, float]]` (`[识别的文本, 置信度]`)
返回值`result`: `List[List[str, float]]` (`[识别的文本, 置信度]`)
```python
[
['韩国小馆', 0.7992169380187988],
Expand All @@ -149,14 +220,7 @@ print(elapse)
```

{{% /tab %}}
{{< /tabs >}}


### 输入
支持4种输入类型：`Union[str, np.ndarray, bytes, Path]`

{{< tabs tabTotal="4">}}
{{% tab tabName="str" %}}
{{% tab tabName="检测 + 识别" %}}

```python {linenos=table}
from pathlib import Path
Expand All @@ -166,29 +230,21 @@ from rapidocr_onnxruntime import RapidOCR
engine = RapidOCR()

img_path = 'tests/test_files/ch_en_num.jpg'
result, elapse = engine(img_path)
result, elapse = engine(img_path, use_det=True, use_cls=False, use_rec=True)
print(result)
print(elapse)
```

{{% /tab %}}
{{% tab tabName="np.ndarray" %}}

返回值`result`: `List[List[float], str, float]` (`[[左上, 右上, 右下, 左下], 文本内容, 置信度]`)
```python {linenos=table}
from pathlib import Path

import cv2
from rapidocr_onnxruntime import RapidOCR

engine = RapidOCR()
img = cv2.imread('tests/test_files/ch_en_num.jpg')
result, elapse = engine(img)
print(result)
print(elapse)
[
[[[9.0, 2.0], [321.0, 11.0], [318.0, 102.0], [6.0, 93.0]], '正品促销', '0.7986101984977723'],
[[[70.0, 98.0], [251.0, 98.0], [251.0, 125.0], [70.0, 125.0]], '大桶装更划算', '0.7368737288883754'],
...
]
```

{{% /tab %}}
{{% tab tabName="Bytes" %}}
{{% tab tabName="分类 + 识别" %}}

```python {linenos=table}
from pathlib import Path
Expand All @@ -198,15 +254,21 @@ from rapidocr_onnxruntime import RapidOCR
engine = RapidOCR()

img_path = 'tests/test_files/ch_en_num.jpg'
with open(img_path, 'rb') as f:
img = f.read()
result, elapse = engine(img)
result, elapse = engine(img_path, use_det=False, use_cls=True, use_rec=True)
print(result)
print(elapse)
```

返回值`result`: `List[List[str, float]]` (`[识别的文本, 置信度]`)
```python
[
['韩国小馆', 0.7992169380187988],
...
]
```

{{% /tab %}}
{{% tab tabName="Path" %}}
{{% tab tabName="检测 + 分类 + 识别" %}}

```python {linenos=table}
from pathlib import Path
Expand All @@ -215,48 +277,26 @@ from rapidocr_onnxruntime import RapidOCR

engine = RapidOCR()

img_path = Path('tests/test_files/ch_en_num.jpg')
result, elapse = engine(img_path)
img_path = 'tests/test_files/ch_en_num.jpg'

# 默认都为True
result, elapse = engine(img_path, use_det=True, use_cls=True, use_rec=True)
print(result)
print(elapse)
```

返回值`result`: `List[List[float], str, float]` (`[[左上, 右上, 右下, 左下], 文本内容, 置信度]`)
```python {linenos=table}
[
[[[9.0, 2.0], [321.0, 11.0], [318.0, 102.0], [6.0, 93.0]], '正品促销', '0.7986101984977723'],
[[[70.0, 98.0], [251.0, 98.0], [251.0, 125.0], [70.0, 125.0]], '大桶装更划算', '0.7368737288883754'],
...
]
```

{{% /tab %}}
{{< /tabs >}}

### 输出
- 有值：`([[文本框坐标], 文本内容, 置信度], 推理时间)`，示例如下：
```text
[[左上, 右上, 右下, 左下], '小明', '0.99'], [0.02, 0.02, 0.85]
```
- 无值：`(None, None)`
- 除耗时外的示例结果：

<details>
<summary>详情</summary>

```python {linenos=table}
[
[[[9.0, 2.0], [321.0, 11.0], [318.0, 102.0], [6.0, 93.0]], '正品促销', '0.7986101984977723'],
[[[70.0, 98.0], [251.0, 98.0], [251.0, 125.0], [70.0, 125.0]], '大桶装更划算', '0.7368737288883754'],
[[[69.0, 144.0], [255.0, 144.0], [255.0, 164.0], [69.0, 164.0]], '强力去污符合国标', '0.8172478278477987'],
[[[107.0, 170.0], [219.0, 170.0], [219.0, 182.0], [107.0, 182.0]], '-40深度防冻不结冰', '0.8655969283797524'],
[[[35.0, 227.0], [63.0, 227.0], [63.0, 236.0], [35.0, 236.0]], '日常价?', '0.6502826035022735'],
[[[141.0, 223.0], [187.0, 225.0], [185.0, 249.0], [139.0, 247.0]], '直击', '0.596031109491984'],
[[[34.0, 234.0], [81.0, 236.0], [80.0, 254.0], [33.0, 252.0]], '10.0起', '0.8231529593467712'],
[[[257.0, 234.0], [304.0, 236.0], [303.0, 253.0], [256.0, 251.0]], '10.0起', '0.8304102122783661'],
[[[258.0, 227.0], [287.0, 226.0], [287.0, 236.0], [258.0, 237.0]], '日常价?', '0.5725070595741272'],
[[[140.0, 245.0], [186.0, 246.0], [186.0, 272.0], [139.0, 271.0]], '底价', '0.5142453710238138'],
[[[129.0, 290.0], [207.0, 292.0], [206.0, 339.0], [128.0, 337.0]], '5.8', '0.6341951936483383'],
[[[98.0, 320.0], [129.0, 320.0], [129.0, 331.0], [98.0, 331.0]], '券后价?', '0.6209247708320618'],
[[[114.0, 343.0], [210.0, 343.0], [210.0, 355.0], [114.0, 355.0]], '惊喜福利不容错过', '0.8640043867958916'],
[[[69.0, 363.0], [151.0, 363.0], [151.0, 383.0], [69.0, 383.0]], '极速发货', '0.7552512288093567'],
[[[201.0, 363.0], [285.0, 363.0], [285.0, 383.0], [201.0, 383.0]], '冰点标准', '0.7194759607315063'],
[[[68.0, 392.0], [151.0, 392.0], [151.0, 412.0], [68.0, 412.0]], '破损就赔', '0.7711991906166077'],
[[[202.0, 391.0], [285.0, 391.0], [285.0, 413.0], [202.0, 413.0]], '假一赔十', '0.6546663284301758']
]
```
</details>

### 可视化查看结果
为了便于查看检测和识别结果，该库中封装了[`VisRes`](https://github.com/RapidAI/RapidOCR/blob/a981e21743f03d9bbfbe596974123fecfe8a7d62/python/rapidocr_onnxruntime/utils.py#L351)类，可借助该类快速可视化查看结果。

Expand Down

0 comments on commit 0828d0d

Please sign in to comment.