diff --git a/doc/doc_ch/inference.md b/doc/doc_ch/inference.md index 431cdb5a4a9f24cf5862c159d51be2a07e9d4047..709a07515c316cdfd60b74f0b090d4baeeb290a7 100644 --- a/doc/doc_ch/inference.md +++ b/doc/doc_ch/inference.md @@ -24,6 +24,7 @@ inference 模型（`fluid.io.save_inference_model`保存的模型） - [2. 基于CTC损失的识别模型推理](#基于CTC损失的识别模型推理) - [3. 基于Attention损失的识别模型推理](#基于Attention损失的识别模型推理) - [4. 自定义文本识别字典的推理](#自定义文本识别字典的推理) + - [5. 多语言模型的推理](#多语言模型的推理) - [四、方向分类模型推理](#方向识别模型推理) - [1. 方向分类模型推理](#方向分类模型推理) @@ -305,6 +306,22 @@ dict_character = list(self.character_str) python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png" --rec_model_dir="./your inference model" --rec_image_shape="3, 32, 100" --rec_char_type="en" --rec_char_dict_path="your text dict path" ``` + +### 5. 多语言模型的推理 +如果您需要预测的是其他语言模型，在使用inference模型预测时，需要通过`--rec_char_dict_path`指定使用的字典路径, 同时为了得到正确的可视化结果， +需要通过 `--vis_font_path` 指定可视化的字体路径，`doc/` 路径下有默认提供的小语种字体，例如韩文识别： + +``` +python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/korean/1.jpg" --rec_model_dir="./your inference model" --rec_char_type="korean" --rec_char_dict_path="ppocr/utils/korean_dict.txt" --vis_font_path="doc/korean.ttf" +``` +![](../imgs_words/korean/1.jpg) + +执行命令后，上图的预测结果为： +``` text +2020-09-19 16:15:05,076-INFO: index: [205 206 38 39] +2020-09-19 16:15:05,077-INFO: word : 바탕으로 +2020-09-19 16:15:05,077-INFO: score: 0.9171358942985535 +``` ## 四、方向分类模型推理 diff --git a/doc/doc_ch/recognition.md b/doc/doc_ch/recognition.md index 1920be56d1a05bb2f7ade944fd225e690fb484a4..0f4173bef6fbe80e1a14d993e560308a84dcd387 100644 --- a/doc/doc_ch/recognition.md +++ b/doc/doc_ch/recognition.md @@ -201,7 +201,19 @@ Optimizer: ``` **注意，预测/评估时的配置文件请务必与训练一致。** +- 小语种 +PaddleOCR也提供了多语言的， `configs/rec/multi_languages` 路径下的提供了多语言的配置文件，目前PaddleOCR支持的多语言算法有： + +| 配置文件 | 算法名称 | backbone | trans | seq | pred | language ｜ +| :--------: | :-------: | :-------: | :-------: | :-----: | :-----: | :-----: | +| rec_en_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 英语 ｜ +| rec_french_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 法语 ｜ +| rec_ger_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 德语 ｜ +| rec_japan_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 日语 ｜ +| rec_korean_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 韩语 ｜ + +多语言模型训练方式与中文模型一致，训练数据集均为100w的合成数据，少量的字体和测试数据可以在[百度网盘]()上下载。 ### 评估 diff --git a/doc/french.ttf b/doc/french.ttf new file mode 100644 index 0000000000000000000000000000000000000000..ab68fb197d4479b3b6dec6e85bd5cbaf433a87c5 Binary files /dev/null and b/doc/french.ttf differ diff --git a/doc/german.ttf b/doc/german.ttf new file mode 100644 index 0000000000000000000000000000000000000000..ab68fb197d4479b3b6dec6e85bd5cbaf433a87c5 Binary files /dev/null and b/doc/german.ttf differ diff --git a/doc/imgs_words/french/1.jpg b/doc/imgs_words/french/1.jpg new file mode 100644 index 0000000000000000000000000000000000000000..077ca28e70b74ed07fa637011c80219aecc448d5 Binary files /dev/null and b/doc/imgs_words/french/1.jpg differ diff --git a/doc/imgs_words/french/2.jpg b/doc/imgs_words/french/2.jpg new file mode 100644 index 0000000000000000000000000000000000000000..38a73caa621710a7eb7378603e0152ba9c14dd41 Binary files /dev/null and b/doc/imgs_words/french/2.jpg differ diff --git a/doc/imgs_words/german/1.jpg b/doc/imgs_words/german/1.jpg new file mode 100644 index 0000000000000000000000000000000000000000..d26ec9ed14de65c2d27e37693ff0da133e774b94 Binary files /dev/null and b/doc/imgs_words/german/1.jpg differ diff --git a/doc/imgs_words/japan/1.jpg b/doc/imgs_words/japan/1.jpg new file mode 100644 index 0000000000000000000000000000000000000000..684879749764a1b6063da32d7910bff911e855f4 Binary files /dev/null and b/doc/imgs_words/japan/1.jpg differ diff --git a/doc/imgs_words/korean/1.jpg b/doc/imgs_words/korean/1.jpg new file mode 100644 index 0000000000000000000000000000000000000000..48a89389ae880783a39a13e9b06a861b88948fba Binary files /dev/null and b/doc/imgs_words/korean/1.jpg differ diff --git a/doc/imgs_words/korean/2.jpg b/doc/imgs_words/korean/2.jpg new file mode 100644 index 0000000000000000000000000000000000000000..b24f28914d574be44e147943d906f8634f149ed5 Binary files /dev/null and b/doc/imgs_words/korean/2.jpg differ diff --git a/doc/japan.ttc b/doc/japan.ttc new file mode 100644 index 0000000000000000000000000000000000000000..ad68243b968fc87b207928594c585039859b75a9 Binary files /dev/null and b/doc/japan.ttc differ diff --git a/doc/korean.ttf b/doc/korean.ttf new file mode 100644 index 0000000000000000000000000000000000000000..e638ce37f67ff1cd9babf73387786eaeb5c52968 Binary files /dev/null and b/doc/korean.ttf differ diff --git a/tools/infer/predict_system.py b/tools/infer/predict_system.py index 3e6be234c68dcd82f0f9e844f3ad2859000cec88..29c4d7e8e35ceda3966dfcadcca5f0ae985d1bb1 100755 --- a/tools/infer/predict_system.py +++ b/tools/infer/predict_system.py @@ -133,6 +133,7 @@ def main(args): image_file_list = get_image_file_list(args.image_dir) text_sys = TextSystem(args) is_visualize = True + font_path = args.vis_font_path for image_file in image_file_list: img, flag = check_and_read_gif(image_file) if not flag: @@ -160,7 +161,7 @@ def main(args): scores = [rec_res[i][1] for i in range(len(rec_res))] draw_img = draw_ocr( - image, boxes, txts, scores, drop_score=drop_score) + image, boxes, txts, scores, drop_score=drop_score, font_path=font_path) draw_img_save = "./inference_results/" if not os.path.exists(draw_img_save): os.makedirs(draw_img_save) diff --git a/tools/infer/utility.py b/tools/infer/utility.py index e844a0ae67480e94ef1b9286d3d59e7373e75a5c..a1c7c205bdc6621d7395004bf45cb443d273d9c0 100755 --- a/tools/infer/utility.py +++ b/tools/infer/utility.py @@ -71,6 +71,10 @@ def parse_args(): type=str, default="./ppocr/utils/ppocr_keys_v1.txt") parser.add_argument("--use_space_char", type=str2bool, default=True) + parser.add_argument( + "--vis_font_path", + type=str, + default="./doc/simfang.ttf") # params for text classifier parser.add_argument("--use_angle_cls", type=str2bool, default=False) @@ -198,7 +202,7 @@ def draw_ocr(image, return image -def draw_ocr_box_txt(image, boxes, txts): +def draw_ocr_box_txt(image, boxes, txts, font_path="./doc/simfang.ttf"): h, w = image.height, image.width img_left = image.copy() img_right = Image.new('RGB', (w, h), (255, 255, 255)) @@ -225,7 +229,7 @@ def draw_ocr_box_txt(image, boxes, txts): if box_height > 2 * box_width: font_size = max(int(box_width * 0.9), 10) font = ImageFont.truetype( - "./doc/simfang.ttf", font_size, encoding="utf-8") + font_path, font_size, encoding="utf-8") cur_y = box[0][1] for c in txt: char_size = font.getsize(c) @@ -235,7 +239,7 @@ def draw_ocr_box_txt(image, boxes, txts): else: font_size = max(int(box_height * 0.8), 10) font = ImageFont.truetype( - "./doc/simfang.ttf", font_size, encoding="utf-8") + font_path, font_size, encoding="utf-8") draw_right.text( [box[0][0], box[0][1]], txt, fill=(0, 0, 0), font=font) img_left = Image.blend(image, img_left, 0.5)