diff --git a/doc/doc_en/multi_languages_en.md b/doc/doc_en/multi_languages_en.md
new file mode 100644
index 00000000..d1c4583f
--- /dev/null
+++ b/doc/doc_en/multi_languages_en.md
@@ -0,0 +1,285 @@
+# Multi-language model
+
+**Recent Update**
+
+-2021.4.9 supports the detection and recognition of 80 languages
+-2021.4.9 supports **lightweight high-precision** English model detection and recognition
+
+-[1 Installation](#Install)
+ -[1.1 paddle installation](#paddleinstallation)
+ -[1.2 paddleocr package installation](#paddleocr_package_install)
+
+-[2 Quick Use](#Quick_Use)
+ -[2.1 Command line operation](#Command_line_operation)
+ -[2.1.1 Prediction of the whole image](#bash_detection+recognition)
+ -[2.1.2 Recognition](#bash_Recognition)
+ -[2.1.3 Detection](#bash_detection)
+ -[2.2 python script running](#python_Script_running)
+ -[2.2.1 Whole image prediction](#python_detection+recognition)
+ -[2.2.2 Recognition](#python_Recognition)
+ -[2.2.3 Detection](#python_detection)
+-[3 Custom Training](#Custom_Training)
+-[4 Supported languages and abbreviations](#language_abbreviations)
+
+
+## 1 Installation
+
+
+### 1.1 paddle installation
+```
+# cpu
+pip install paddlepaddle
+
+# gpu
+pip instll paddlepaddle-gpu
+```
+
+
+### 1.2 paddleocr package installation
+
+
+pip install
+```
+pip install "paddleocr>=2.0.4" # 2.0.4 version is recommended
+```
+Build and install locally
+```
+python3 setup.py bdist_wheel
+pip3 install dist/paddleocr-x.x.x-py3-none-any.whl # x.x.x is the version number of paddleocr
+```
+
+
+## 2 Quick use
+
+
+### 2.1 Command line operation
+
+View help information
+
+```
+paddleocr -h
+```
+
+* Whole image prediction (detection + recognition)
+
+Paddleocr currently supports 80 languages, which can be switched by modifying the --lang parameter.
+The specific supported [language] (#language_abbreviations) can be viewed in the table.
+
+``` bash
+
+paddleocr --image_dir doc/imgs/japan_2.jpg --lang=japan
+```
+![](https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/release/2.0/doc/imgs/japan_2.jpg)
+
+The result is a list, each item contains a text box, text and recognition confidence
+```text
+[[[671.0, 60.0], [847.0, 63.0], [847.0, 104.0], [671.0, 102.0]], ('もちもち', 0.9993342)]
+[[[394.0, 82.0], [536.0, 77.0], [538.0, 127.0], [396.0, 132.0]], ('自然の', 0.9919842)]
+[[[880.0, 89.0], [1014.0, 93.0], [1013.0, 127.0], [879.0, 124.0]], ('とろっと', 0.9976762)]
+[[[1067.0, 101.0], [1294.0, 101.0], [1294.0, 138.0], [1067.0, 138.0]], ('后味のよい', 0.9988712)]
+......
+```
+
+* Recognition
+
+```bash
+paddleocr --image_dir doc/imgs_words/japan/1.jpg --det false --lang=japan
+```
+
+![](https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/release/2.0/doc/imgs_words/japan/1.jpg)
+
+The result is a tuple, which returns the recognition result and recognition confidence
+
+```text
+('したがって', 0.99965394)
+```
+
+* Detection
+
+```
+paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --rec false
+```
+
+The result is a list, each item contains only text boxes
+
+```
+[[26.0, 457.0], [137.0, 457.0], [137.0, 477.0], [26.0, 477.0]]
+[[25.0, 425.0], [372.0, 425.0], [372.0, 448.0], [25.0, 448.0]]
+[[128.0, 397.0], [273.0, 397.0], [273.0, 414.0], [128.0, 414.0]]
+......
+```
+
+
+### 2.2 python script running
+
+ppocr also supports running in python scripts for easy embedding in your own code:
+
+* Whole image prediction (detection + recognition)
+
+```
+from paddleocr import PaddleOCR, draw_ocr
+
+# Also switch the language by modifying the lang parameter
+ocr = PaddleOCR(lang="korean") # The model file will be downloaded automatically when executed for the first time
+img_path ='doc/imgs/korean_1.jpg'
+result = ocr.ocr(img_path)
+# Print detection frame and recognition result
+for line in result:
+ print(line)
+
+# Visualization
+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/korean.ttf')
+im_show = Image.fromarray(im_show)
+im_show.save('result.jpg')
+```
+
+Visualization of results:
+![](https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/release/2.0/doc/imgs_results/korean.jpg)
+
+
+* Recognition
+
+```
+from paddleocr import PaddleOCR
+ocr = PaddleOCR(lang="german")
+img_path ='PaddleOCR/doc/imgs_words/german/1.jpg'
+result = ocr.ocr(img_path, det=False, cls=True)
+for line in result:
+ print(line)
+```
+
+![](https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/release/2.0/doc/imgs_words/german/1.jpg)
+
+The result is a tuple, which only contains the recognition result and recognition confidence
+
+```
+('leider auch jetzt', 0.97538936)
+```
+
+* Detection
+
+```python
+from paddleocr import PaddleOCR, draw_ocr
+ocr = PaddleOCR() # need to run only once to download and load model into memory
+img_path ='PaddleOCR/doc/imgs_en/img_12.jpg'
+result = ocr.ocr(img_path, rec=False)
+for line in result:
+ print(line)
+
+# show 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/fonts/simfang.ttf')
+im_show = Image.fromarray(im_show)
+im_show.save('result.jpg')
+```
+The result is a list, each item contains only text boxes
+```bash
+[[26.0, 457.0], [137.0, 457.0], [137.0, 477.0], [26.0, 477.0]]
+[[25.0, 425.0], [372.0, 425.0], [372.0, 448.0], [25.0, 448.0]]
+[[128.0, 397.0], [273.0, 397.0], [273.0, 414.0], [128.0, 414.0]]
+......
+```
+
+Visualization of results:
+![](https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/release/2.0/doc/imgs_results/whl/12_det.jpg)
+
+ppocr also supports direction classification. For more usage methods, please refer to: [whl package instructions](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.0/doc/doc_ch/whl.md).
+
+
+## 3 Custom training
+
+ppocr supports using your own data for custom training or finetune, where the recognition model can refer to [French configuration file](../../configs/rec/multi_language/rec_french_lite_train.yml)
+Modify the training data path, dictionary and other parameters.
+
+For specific data preparation and training process, please refer to: [Text Detection](../doc_en/detection_en.md), [Text Recognition](../doc_en/recognition_en.md), more functions such as predictive deployment,
+For functions such as data annotation, you can read the complete [Document Tutorial](../../README.md).
+
+
+## 4 Support languages and abbreviations
+
+| Language | Abbreviation |
+| --- | --- |
+|chinese and english|ch|
+|english|en|
+|french|fr|
+|german|german|
+|japan|japan|
+|korean|korean|
+|chinese traditional |ch_tra|
+| Italian |it|
+|Spanish |es|
+| Portuguese|pt|
+|Russia|ru|
+|Arabic|ar|
+|Hindi|hi|
+|Uyghur|ug|
+|Persian|fa|
+|Urdu|ur|
+| Serbian(latin) |rs_latin|
+|Occitan |oc|
+|Marathi|mr|
+|Nepali|ne|
+|Serbian(cyrillic)|rs_cyrillic|
+|Bulgarian |bg|
+|Ukranian|uk|
+|Belarusian|be|
+|Telugu |te|
+|Kannada |kn|
+|Tamil |ta|
+|Afrikaans |af|
+|Azerbaijani |az|
+|Bosnian|bs|
+|Czech|cs|
+|Welsh |cy|
+|Danish|da|
+|Estonian |et|
+|Irish |ga|
+|Croatian |hr|
+|Hungarian |hu|
+|Indonesian|id|
+|Icelandic|is|
+|Kurdish|ku|
+|Lithuanian |lt|
+ |Latvian |lv|
+|Maori|mi|
+|Malay|ms|
+|Maltese |mt|
+|Dutch |nl|
+|Norwegian |no|
+|Polish |pl|
+|Romanian |ro|
+|Slovak |sk|
+|Slovenian |sl|
+|Albanian |sq|
+|Swedish |sv|
+|Swahili |sw|
+|Tagalog |tl|
+|Turkish |tr|
+|Uzbek |uz|
+|Vietnamese |vi|
+|Mongolian |mn|
+|Abaza |abq|
+|Adyghe |ady|
+|Kabardian |kbd|
+|Avar |ava|
+|Dargwa |dar|
+|Ingush |inh|
+|Lak |lbe|
+|Lezghian |lez|
+|Tabassaran |tab|
+|Bihari |bh|
+|Maithili |mai|
+|Angika |ang|
+|Bhojpuri |bho|
+|Magahi |mah|
+|Nagpur |sck|
+|Newari |new|
+|Goan Konkani|gom|
+|Saudi Arabia|sa|
diff --git a/ppocr/utils/utility.py b/ppocr/utils/utility.py
index 29576d97..7bb4c906 100755
--- a/ppocr/utils/utility.py
+++ b/ppocr/utils/utility.py
@@ -61,6 +61,7 @@ def get_image_file_list(img_file):
imgs_lists.append(file_path)
if len(imgs_lists) == 0:
raise Exception("not found any img file in {}".format(img_file))
+ imgs_lists = sorted(imgs_lists)
return imgs_lists
diff --git a/tools/infer/predict_rec.py b/tools/infer/predict_rec.py
index 1cb6e01b..24388026 100755
--- a/tools/infer/predict_rec.py
+++ b/tools/infer/predict_rec.py
@@ -41,6 +41,7 @@ class TextRecognizer(object):
self.character_type = args.rec_char_type
self.rec_batch_num = args.rec_batch_num
self.rec_algorithm = args.rec_algorithm
+ self.max_text_length = args.max_text_length
postprocess_params = {
'name': 'CTCLabelDecode',
"character_type": args.rec_char_type,
@@ -186,8 +187,9 @@ class TextRecognizer(object):
norm_img = norm_img[np.newaxis, :]
norm_img_batch.append(norm_img)
else:
- norm_img = self.process_image_srn(
- img_list[indices[ino]], self.rec_image_shape, 8, 25)
+ norm_img = self.process_image_srn(img_list[indices[ino]],
+ self.rec_image_shape, 8,
+ self.max_text_length)
encoder_word_pos_list = []
gsrm_word_pos_list = []
gsrm_slf_attn_bias1_list = []
diff --git a/tools/infer/predict_system.py b/tools/infer/predict_system.py
index de7ee9d3..ba81aff0 100755
--- a/tools/infer/predict_system.py
+++ b/tools/infer/predict_system.py
@@ -13,6 +13,7 @@
# limitations under the License.
import os
import sys
+import subprocess
__dir__ = os.path.dirname(os.path.abspath(__file__))
sys.path.append(__dir__)
@@ -141,6 +142,7 @@ def sorted_boxes(dt_boxes):
def main(args):
image_file_list = get_image_file_list(args.image_dir)
+ image_file_list = image_file_list[args.process_id::args.total_process_num]
text_sys = TextSystem(args)
is_visualize = True
font_path = args.vis_font_path
@@ -184,4 +186,18 @@ def main(args):
if __name__ == "__main__":
- main(utility.parse_args())
+ args = utility.parse_args()
+ if args.use_mp:
+ p_list = []
+ total_process_num = args.total_process_num
+ for process_id in range(total_process_num):
+ cmd = [sys.executable, "-u"] + sys.argv + [
+ "--process_id={}".format(process_id),
+ "--use_mp={}".format(False)
+ ]
+ p = subprocess.Popen(cmd, stdout=sys.stdout, stderr=sys.stdout)
+ p_list.append(p)
+ for p in p_list:
+ p.wait()
+ else:
+ main(args)
diff --git a/tools/infer/utility.py b/tools/infer/utility.py
index 9019f003..b273eaf3 100755
--- a/tools/infer/utility.py
+++ b/tools/infer/utility.py
@@ -98,6 +98,10 @@ def parse_args():
parser.add_argument("--enable_mkldnn", type=str2bool, default=False)
parser.add_argument("--use_pdserving", type=str2bool, default=False)
+ parser.add_argument("--use_mp", type=str2bool, default=False)
+ parser.add_argument("--total_process_num", type=int, default=1)
+ parser.add_argument("--process_id", type=int, default=0)
+
return parser.parse_args()