diff --git a/doc/doc_en/multi_languages_en.md b/doc/doc_en/multi_languages_en.md new file mode 100644 index 0000000000000000000000000000000000000000..d1c4583f66f611fbef7191d52d32e02187853c9b --- /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 29576d971486326aec3c93601656d7b982ef3336..7bb4c906d298af54ed56e2805f487a2c22d1894b 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 1cb6e01b087ff98efb0a57be3cc58a79425fea57..24388026b8f395427c93e285ed550446e3aa9b9c 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 de7ee9d342063161f2e329c99d2428051c0ecf8c..ba81aff0a940fbee234e59e98f73c62fc7f69f09 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 9019f003b44d9ecb69ed390fba8cc97d4d074cd5..b273eaf3258421d5c5c30c132f99e78f9f0999ba 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()