forgetest5
/
PaddleOCR
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
PaddleOCR/doc/doc_en/whl_en.md

312 lines
18 KiB
Markdown
Raw Normal View History

init commit for build whl
2020-08-22 19:42:14 +08:00
# paddleocr package
## Get started quickly
### install package
update whl doc (#1289)
2020-12-01 01:39:15 +08:00
First, you need to refer to [installation document](installation_en.md) to install paddlepaddle, and then start to install paddleocr package
init commit for build whl
2020-08-22 19:42:14 +08:00
install by pypi
```bash
pip install paddleocr
```
build own whl package and install
```bash
update python to python3
2020-09-21 12:48:07 +08:00
python3 setup.py bdist_wheel
update pip to pip3
2020-09-21 12:48:31 +08:00
pip3 install dist/paddleocr-x.x.x-py3-none-any.whl # x.x.x is the version of paddleocr
init commit for build whl
2020-08-22 19:42:14 +08:00
```
### 1. Use by code
whl包添加分类模型
2020-09-16 20:00:34 +08:00
* detection classification and recognition
```python
from paddleocr import PaddleOCR,draw_ocr
fix whl doc and add multi-language
2020-09-19 20:06:23 +08:00
# Paddleocr supports Chinese, English, French, German, Korean and Japanese.
update doc
2020-09-21 16:16:25 +08:00
# You can set the parameter `lang` as `ch`, `en`, `french`, `german`, `korean`, `japan`
fix whl doc and add multi-language
2020-09-19 20:06:23 +08:00
# to switch the language model in order.
ppocr支持多语言切换
2020-09-18 11:29:39 +08:00
ocr = PaddleOCR(use_angle_cls=True, lang='en') # need to run only once to download and load model into memory
whl包添加分类模型
2020-09-16 20:00:34 +08:00
img_path = 'PaddleOCR/doc/imgs_en/img_12.jpg'
result = ocr.ocr(img_path, cls=True)
for line in result:
print(line)
fix whl doc and add multi-language
2020-09-19 20:06:23 +08:00
whl包添加分类模型
2020-09-16 20:00:34 +08:00
# draw result
from PIL import Image
image = Image.open(img_path).convert('RGB')
boxes = [line[0] for line in result]
txts = [line[1][0] for line in result]
scores = [line[1][1] for line in result]
im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')
```
Output will be a list, each item contains bounding box, text and recognition confidence
```bash
[[[442.0, 173.0], [1169.0, 173.0], [1169.0, 225.0], [442.0, 225.0]], ['ACKNOWLEDGEMENTS', 0.99283075]]
[[[393.0, 340.0], [1207.0, 342.0], [1207.0, 389.0], [393.0, 387.0]], ['We would like to thank all the designers and', 0.9357758]]
[[[399.0, 398.0], [1204.0, 398.0], [1204.0, 433.0], [399.0, 433.0]], ['contributors whohave been involved in the', 0.9592447]]
......
```
Visualization of results
<div align="center">
<img src="../imgs_results/whl/12_det_rec.jpg" width="800">
</div>
init commit for build whl
2020-08-22 19:42:14 +08:00
* detection and recognition
```python
from paddleocr import PaddleOCR,draw_ocr
ppocr支持多语言切换
2020-09-18 11:29:39 +08:00
ocr = PaddleOCR(lang='en') # need to run only once to download and load model into memory
init commit for build whl
2020-08-22 19:42:14 +08:00
img_path = 'PaddleOCR/doc/imgs_en/img_12.jpg'
result = ocr.ocr(img_path)
for line in result:
print(line)
# draw result
from PIL import Image
image = Image.open(img_path).convert('RGB')
boxes = [line[0] for line in result]
txts = [line[1][0] for line in result]
scores = [line[1][1] for line in result]
im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')
```
Output will be a list, each item contains bounding box, text and recognition confidence
```bash
[[[442.0, 173.0], [1169.0, 173.0], [1169.0, 225.0], [442.0, 225.0]], ['ACKNOWLEDGEMENTS', 0.99283075]]
[[[393.0, 340.0], [1207.0, 342.0], [1207.0, 389.0], [393.0, 387.0]], ['We would like to thank all the designers and', 0.9357758]]
[[[399.0, 398.0], [1204.0, 398.0], [1204.0, 433.0], [399.0, 433.0]], ['contributors whohave been involved in the', 0.9592447]]
修正文档
2020-08-24 11:30:00 +08:00
......
init commit for build whl
2020-08-22 19:42:14 +08:00
```
Visualization of results
<div align="center">
<img src="../imgs_results/whl/12_det_rec.jpg" width="800">
</div>
whl包添加分类模型
2020-09-16 20:00:34 +08:00
* classification and recognition
```python
from paddleocr import PaddleOCR
ppocr支持多语言切换
2020-09-18 11:29:39 +08:00
ocr = PaddleOCR(use_angle_cls=True, lang='en') # need to run only once to load model into memory
whl包添加分类模型
2020-09-16 20:00:34 +08:00
img_path = 'PaddleOCR/doc/imgs_words_en/word_10.png'
result = ocr.ocr(img_path, det=False, cls=True)
for line in result:
print(line)
```
Output will be a list, each item contains recognition text and confidence
```bash
['PAIN', 0.990372]
```
init commit for build whl
2020-08-22 19:42:14 +08:00
* only detection
```python
from paddleocr import PaddleOCR,draw_ocr
修正文档
2020-08-24 11:30:00 +08:00
ocr = PaddleOCR() # need to run only once to download and load model into memory
init commit for build whl
2020-08-22 19:42:14 +08:00
img_path = 'PaddleOCR/doc/imgs_en/img_12.jpg'
result = ocr.ocr(img_path,rec=False)
for line in result:
print(line)
# draw result
from PIL import Image
image = Image.open(img_path).convert('RGB')
im_show = draw_ocr(image, result, txts=None, scores=None, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')
```
Output will be a list, each item only contains bounding box
```bash
[[756.0, 812.0], [805.0, 812.0], [805.0, 830.0], [756.0, 830.0]]
[[820.0, 803.0], [1085.0, 801.0], [1085.0, 836.0], [820.0, 838.0]]
[[393.0, 801.0], [715.0, 805.0], [715.0, 839.0], [393.0, 836.0]]
修正文档
2020-08-24 11:30:00 +08:00
......
init commit for build whl
2020-08-22 19:42:14 +08:00
```
Visualization of results
<div align="center">
<img src="../imgs_results/whl/12_det.jpg" width="800">
</div>
* only recognition
```python
from paddleocr import PaddleOCR
ppocr支持多语言切换
2020-09-18 11:29:39 +08:00
ocr = PaddleOCR(lang='en') # need to run only once to load model into memory
init commit for build whl
2020-08-22 19:42:14 +08:00
img_path = 'PaddleOCR/doc/imgs_words_en/word_10.png'
whl包添加分类模型
2020-09-16 20:00:34 +08:00
result = ocr.ocr(img_path, det=False, cls=False)
init commit for build whl
2020-08-22 19:42:14 +08:00
for line in result:
print(line)
```
whl包添加分类模型
2020-09-16 20:00:34 +08:00
Output will be a list, each item contains recognition text and confidence
init commit for build whl
2020-08-22 19:42:14 +08:00
```bash
['PAIN', 0.990372]
```
whl包添加分类模型
2020-09-16 20:00:34 +08:00
* only classification
```python
from paddleocr import PaddleOCR
ocr = PaddleOCR(use_angle_cls=True) # need to run only once to load model into memory
img_path = 'PaddleOCR/doc/imgs_words_en/word_10.png'
result = ocr.ocr(img_path, det=False, rec=False, cls=True)
for line in result:
print(line)
```
Output will be a list, each item contains classification result and confidence
```bash
['0', 0.99999964]
```
init commit for build whl
2020-08-22 19:42:14 +08:00
### Use by command line
show help information
```bash
paddleocr -h
```
whl包添加分类模型
2020-09-16 20:00:34 +08:00
* detection classification and recognition
```bash
update whl doc (#1289)
2020-12-01 01:39:15 +08:00
paddleocr --image_dir PaddleOCR/doc/imgs_en/img_12.jpg --use_angle_cls true --lang en
whl包添加分类模型
2020-09-16 20:00:34 +08:00
```
Output will be a list, each item contains bounding box, text and recognition confidence
```bash
[[[442.0, 173.0], [1169.0, 173.0], [1169.0, 225.0], [442.0, 225.0]], ['ACKNOWLEDGEMENTS', 0.99283075]]
[[[393.0, 340.0], [1207.0, 342.0], [1207.0, 389.0], [393.0, 387.0]], ['We would like to thank all the designers and', 0.9357758]]
[[[399.0, 398.0], [1204.0, 398.0], [1204.0, 433.0], [399.0, 433.0]], ['contributors whohave been involved in the', 0.9592447]]
......
```
init commit for build whl
2020-08-22 19:42:14 +08:00
* detection and recognition
```bash
ppocr支持多语言切换
2020-09-18 11:29:39 +08:00
paddleocr --image_dir PaddleOCR/doc/imgs_en/img_12.jpg --lang en
init commit for build whl
2020-08-22 19:42:14 +08:00
```
Output will be a list, each item contains bounding box, text and recognition confidence
```bash
[[[442.0, 173.0], [1169.0, 173.0], [1169.0, 225.0], [442.0, 225.0]], ['ACKNOWLEDGEMENTS', 0.99283075]]
[[[393.0, 340.0], [1207.0, 342.0], [1207.0, 389.0], [393.0, 387.0]], ['We would like to thank all the designers and', 0.9357758]]
[[[399.0, 398.0], [1204.0, 398.0], [1204.0, 433.0], [399.0, 433.0]], ['contributors whohave been involved in the', 0.9592447]]
修正文档
2020-08-24 11:30:00 +08:00
......
init commit for build whl
2020-08-22 19:42:14 +08:00
```
whl包添加分类模型
2020-09-16 20:00:34 +08:00
* classification and recognition
```bash
update whl doc (#1289)
2020-12-01 01:39:15 +08:00
paddleocr --image_dir PaddleOCR/doc/imgs_words_en/word_10.png --use_angle_cls true --det false --lang en
whl包添加分类模型
2020-09-16 20:00:34 +08:00
```
Output will be a list, each item contains text and recognition confidence
```bash
['PAIN', 0.990372]
```
init commit for build whl
2020-08-22 19:42:14 +08:00
* only detection
```bash
paddleocr --image_dir PaddleOCR/doc/imgs_en/img_12.jpg --rec false
```
Output will be a list, each item only contains bounding box
```bash
[[756.0, 812.0], [805.0, 812.0], [805.0, 830.0], [756.0, 830.0]]
[[820.0, 803.0], [1085.0, 801.0], [1085.0, 836.0], [820.0, 838.0]]
[[393.0, 801.0], [715.0, 805.0], [715.0, 839.0], [393.0, 836.0]]
修正文档
2020-08-24 11:30:00 +08:00
......
init commit for build whl
2020-08-22 19:42:14 +08:00
```
* only recognition
```bash
update whl doc (#1289)
2020-12-01 01:39:15 +08:00
paddleocr --image_dir PaddleOCR/doc/imgs_words_en/word_10.png --det false --lang en
init commit for build whl
2020-08-22 19:42:14 +08:00
```
Output will be a list, each item contains text and recognition confidence
```bash
['PAIN', 0.990372]
```
whl包添加分类模型
2020-09-16 20:00:34 +08:00
* only classification
```bash
update whl doc (#1289)
2020-12-01 01:39:15 +08:00
paddleocr --image_dir PaddleOCR/doc/imgs_words_en/word_10.png --use_angle_cls true --det false --rec false
whl包添加分类模型
2020-09-16 20:00:34 +08:00
```
Output will be a list, each item contains classification result and confidence
```bash
['0', 0.99999964]
```
添加使用自定义模型文档
2020-08-24 16:25:36 +08:00
## Use custom model
When the built-in model cannot meet the needs, you need to use your own trained model.
First, refer to the first section of [inference_en.md](./inference_en.md) to convert your det and rec model to inference model, and then use it as follows
### 1. Use by code
```python
from paddleocr import PaddleOCR,draw_ocr
# The path of detection and recognition model must contain model and params files
ppocr支持多语言切换
2020-09-18 11:29:39 +08:00
ocr = PaddleOCR(det_model_dir='{your_det_model_dir}', rec_model_dir='{your_rec_model_dir}', rec_char_dict_path='{your_rec_char_dict_path}', cls_model_dir='{your_cls_model_dir}', use_angle_cls=True)
添加使用自定义模型文档
2020-08-24 16:25:36 +08:00
img_path = 'PaddleOCR/doc/imgs_en/img_12.jpg'
whl包添加分类模型
2020-09-16 20:00:34 +08:00
result = ocr.ocr(img_path, cls=True)
添加使用自定义模型文档
2020-08-24 16:25:36 +08:00
for line in result:
print(line)
# draw result
from PIL import Image
image = Image.open(img_path).convert('RGB')
boxes = [line[0] for line in result]
txts = [line[1][0] for line in result]
scores = [line[1][1] for line in result]
im_show = draw_ocr(image, boxes, txts, scores, font_path='/path/to/PaddleOCR/doc/simfang.ttf')
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')
```
### Use by command line
```bash
update whl doc (#1289)
2020-12-01 01:39:15 +08:00
paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --det_model_dir {your_det_model_dir} --rec_model_dir {your_rec_model_dir} --rec_char_dict_path {your_rec_char_dict_path} --cls_model_dir {your_cls_model_dir} --use_angle_cls true
添加使用自定义模型文档
2020-08-24 16:25:36 +08:00
```
init commit for build whl
2020-08-22 19:42:14 +08:00
## Parameter Description
| Parameter | Description | Default value |
|-------------------------|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------|
| use_gpu | use GPU or not | TRUE |
| gpu_mem | GPU memory size used for initialization | 8000M |
| image_dir | The images path or folder path for predicting when used by the command line | |
| det_algorithm | Type of detection algorithm selected | DB |
修正文档
2020-08-24 11:30:00 +08:00
| det_model_dir | the text detection inference model folder. There are two ways to transfer parameters, 1. None: Automatically download the built-in model to `~/.paddleocr/det`; 2. The path of the inference model converted by yourself, the model and params files must be included in the model path | None |
init commit for build whl
2020-08-22 19:42:14 +08:00
| det_max_side_len | The maximum size of the long side of the image. When the long side exceeds this value, the long side will be resized to this size, and the short side will be scaled proportionally | 960 |
| det_db_thresh | Binarization threshold value of DB output map | 0.3 |
| det_db_box_thresh | The threshold value of the DB output box. Boxes score lower than this value will be discarded | 0.5 |
| det_db_unclip_ratio | The expanded ratio of DB output box | 2 |
| det_east_score_thresh | Binarization threshold value of EAST output map | 0.8 |
| det_east_cover_thresh | The threshold value of the EAST output box. Boxes score lower than this value will be discarded | 0.1 |
| det_east_nms_thresh | The NMS threshold value of EAST model output box | 0.2 |
| rec_algorithm | Type of recognition algorithm selected | CRNN |
修正文档
2020-08-24 11:30:00 +08:00
| rec_model_dir | the text recognition inference model folder. There are two ways to transfer parameters, 1. None: Automatically download the built-in model to `~/.paddleocr/rec`; 2. The path of the inference model converted by yourself, the model and params files must be included in the model path | None |
init commit for build whl
2020-08-22 19:42:14 +08:00
| rec_image_shape | image shape of recognition algorithm | "3,32,320" |
| rec_char_type | Character type of recognition algorithm, Chinese (ch) or English (en) | ch |
| rec_batch_num | When performing recognition, the batchsize of forward images | 30 |
修正文档
2020-08-24 11:30:00 +08:00
| max_text_length | The maximum text length that the recognition algorithm can recognize | 25 |
| rec_char_dict_path | the alphabet path which needs to be modified to your own path when `rec_model_Name` use mode 2 | ./ppocr/utils/ppocr_keys_v1.txt |
init commit for build whl
2020-08-22 19:42:14 +08:00
| use_space_char | Whether to recognize spaces | TRUE |
whl包添加分类模型
2020-09-16 20:00:34 +08:00
| use_angle_cls | Whether to load classification model | FALSE |
| cls_model_dir | the classification inference model folder. There are two ways to transfer parameters, 1. None: Automatically download the built-in model to `~/.paddleocr/cls`; 2. The path of the inference model converted by yourself, the model and params files must be included in the model path | None |
| cls_image_shape | image shape of classification algorithm | "3,48,192" |
| label_list | label list of classification algorithm | ['0','180'] |
| cls_batch_num | When performing classification, the batchsize of forward images | 30 |
init commit for build whl
2020-08-22 19:42:14 +08:00
| enable_mkldnn | Whether to enable mkldnn | FALSE |
whl包添加分类模型
2020-09-16 20:00:34 +08:00
| use_zero_copy_run | Whether to forward by zero_copy_run | FALSE |
update doc
2020-09-21 16:16:59 +08:00
| lang | The support language, now only Chinese(ch)、English(en)、French(french)、German(german)、Korean(korean)、Japanese(japan) are supported | ch |
init commit for build whl
2020-08-22 19:42:14 +08:00
| det | Enable detction when `ppocr.ocr` func exec | TRUE |
whl包添加分类模型
2020-09-16 20:00:34 +08:00
| rec | Enable recognition when `ppocr.ocr` func exec | TRUE |
update whl doc (#1289)
2020-12-01 01:39:15 +08:00
| cls | Enable classification when `ppocr.ocr` func exec，this parameter only exists in `code usage` mode | FALSE |