update doc

deploy/android_demo/app/src/main/cpp/native.cpp

@@ -47,7 +47,7 @@ str_to_cpu_mode(const std::string &cpu_mode) {
   std::string upper_key;
   std::transform(cpu_mode.cbegin(), cpu_mode.cend(), upper_key.begin(),
                  ::toupper);
-  auto index = cpu_mode_map.find(upper_key);
+  auto index = cpu_mode_map.find(upper_key.c_str());
   if (index == cpu_mode_map.end()) {
     LOGE("cpu_mode not found %s", upper_key.c_str());
     return paddle::lite_api::LITE_POWER_HIGH;

deploy/android_demo/app/src/main/java/com/baidu/paddle/lite/demo/ocr/OCRPredictorNative.java

@@ -54,7 +54,7 @@ public class OCRPredictorNative {
     }
 
     public void destory() {
-        if (nativePointer > 0) {
+        if (nativePointer != 0) {
             release(nativePointer);
             nativePointer = 0;
         }

deploy/cpp_infer/docs/windows_vs2019_build.md

@@ -109,8 +109,10 @@ CUDA_LIB、CUDNN_LIB、TENSORRT_DIR、WITH_GPU、WITH_TENSORRT
 
 运行之前，将下面文件拷贝到`build/Release/`文件夹下
 1. `paddle_inference/paddle/lib/paddle_inference.dll`
-2. `opencv/build/x64/vc15/bin/opencv_world455.dll`
-3. 如果使用openblas版本的预测库还需要拷贝 `paddle_inference/third_party/install/openblas/lib/openblas.dll`
+2. `paddle_inference/third_party/install/onnxruntime/lib/onnxruntime.dll`
+3. `paddle_inference/third_party/install/paddle2onnx/lib/paddle2onnx.dll`
+4. `opencv/build/x64/vc15/bin/opencv_world455.dll`
+5. 如果使用openblas版本的预测库还需要拷贝 `paddle_inference/third_party/install/openblas/lib/openblas.dll`
 
 ### Step4: 预测
 

deploy/slim/quantization/README_en.md

@@ -73,4 +73,4 @@ python deploy/slim/quantization/export_model.py -c configs/det/ch_ppocr_v2.0/ch_
 The numerical range of the quantized model parameters derived from the above steps is still FP32, but the numerical range of the parameters is int8.
 The derived model can be converted through the `opt tool` of PaddleLite.
 
-For quantitative model deployment, please refer to [Mobile terminal model deployment](../../lite/readme_en.md)
+For quantitative model deployment, please refer to [Mobile terminal model deployment](../../lite/readme.md)

paddleocr.py

@@ -636,4 +636,6 @@ def main():
 
             for item in result:
                 item.pop('img')
+                item.pop('res')
                 logger.info(item)
+            logger.info('result save to {}'.format(args.output))

ppocr/data/imaug/copy_paste.py

@@ -35,10 +35,12 @@ class CopyPaste(object):
         point_num = data['polys'].shape[1]
         src_img = data['image']
         src_polys = data['polys'].tolist()
+        src_texts = data['texts']
         src_ignores = data['ignore_tags'].tolist()
         ext_data = data['ext_data'][0]
         ext_image = ext_data['image']
         ext_polys = ext_data['polys']
+        ext_texts = ext_data['texts']
         ext_ignores = ext_data['ignore_tags']
 
         indexs = [i for i in range(len(ext_ignores)) if not ext_ignores[i]]
@@ -53,7 +55,7 @@ class CopyPaste(object):
         src_img = cv2.cvtColor(src_img, cv2.COLOR_BGR2RGB)
         ext_image = cv2.cvtColor(ext_image, cv2.COLOR_BGR2RGB)
         src_img = Image.fromarray(src_img).convert('RGBA')
-        for poly, tag in zip(select_polys, select_ignores):
+        for idx, poly, tag in zip(select_idxs, select_polys, select_ignores):
             box_img = get_rotate_crop_image(ext_image, poly)
 
             src_img, box = self.paste_img(src_img, box_img, src_polys)
@@ -62,6 +64,7 @@ class CopyPaste(object):
                 for _ in range(len(box), point_num):
                     box.append(box[-1])
                 src_polys.append(box)
+                src_texts.append(ext_texts[idx])
                 src_ignores.append(tag)
         src_img = cv2.cvtColor(np.array(src_img), cv2.COLOR_RGB2BGR)
         h, w = src_img.shape[:2]
@@ -70,6 +73,7 @@ class CopyPaste(object):
         src_polys[:, :, 1] = np.clip(src_polys[:, :, 1], 0, h)
         data['image'] = src_img
         data['polys'] = src_polys
+        data['texts'] = src_texts
         data['ignore_tags'] = np.array(src_ignores)
         return data
 

ppocr/metrics/rec_metric.py

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-import Levenshtein
+from rapidfuzz.distance import Levenshtein
 import string
 
 
@@ -46,8 +46,7 @@ class RecMetric(object):
             if self.is_filter:
                 pred = self._normalize_text(pred)
                 target = self._normalize_text(target)
-            norm_edit_dis += Levenshtein.distance(pred, target) / max(
-                len(pred), len(target), 1)
+            norm_edit_dis += Levenshtein.normalized_distance(pred, target)
             if pred == target:
                 correct_num += 1
             all_num += 1

ppocr/utils/dict/kie_dict/xfund_class_list.txt

+OTHER
+QUESTION
+ANSWER
+HEADER

ppocr/utils/save_load.py

@@ -194,6 +194,9 @@ def save_model(model,
     _mkdir_if_not_exist(model_path, logger)
     model_prefix = os.path.join(model_path, prefix)
     paddle.save(optimizer.state_dict(), model_prefix + '.pdopt')
+
+    is_nlp_model = config['Architecture']["model_type"] == 'kie' and config[
+        "Architecture"]["algorithm"] not in ["SDMGR"]
     if is_nlp_model is not True:
         paddle.save(model.state_dict(), model_prefix + '.pdparams')
         metric_prefix = model_prefix

ppstructure/README.md

@@ -106,9 +106,9 @@ PP-Structure Series Model List (Updating)
 
 |model name|description|model size|download|
 | --- | --- | --- | --- |
-|ch_PP-OCRv3_det_slim|[New] slim quantization with distillation lightweight model, supporting Chinese, English, multilingual text detection| 1.1M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_distill_train.tar)|
-|ch_PP-OCRv3_rec_slim |[New] Slim qunatization with distillation lightweight model, supporting Chinese, English text recognition| 4.9M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_train.tar) |
-|ch_ppstructure_mobile_v2.0_SLANet|Chinese table recognition model trained on PubTabNet dataset based on SLANet|9.3M|[inference model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_train.tar) |
+|ch_PP-OCRv3_det| [New] Lightweight model, supporting Chinese, English, multilingual text detection | 3.8M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_distill_train.tar)|
+|ch_PP-OCRv3_rec| [New] Lightweight model, supporting Chinese, English, multilingual text recognition | 12.4M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_train.tar) |
+|ch_ppstructure_mobile_v2.0_SLANet|Chinese table recognition model based on SLANet|9.3M|[inference model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_train.tar) |
 
 ### 7.3 KIE model
 

ppstructure/README_ch.md

@@ -120,9 +120,9 @@ PP-Structure系列模型列表（更新中）
 
 |模型名称|模型简介|模型大小|下载地址|
 | --- | --- | --- | --- |
-|ch_PP-OCRv3_det_slim|【最新】slim量化+蒸馏版超轻量模型，支持中英文、多语种文本检测| 1.1M |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_distill_train.tar)|
-|ch_PP-OCRv3_rec_slim |【最新】slim量化版超轻量模型，支持中英文、数字识别| 4.9M |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_train.tar) |
-|ch_ppstructure_mobile_v2.0_SLANet|基于SLANet在PubTabNet数据集上训练的中文表格识别模型|9.3M|[推理模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_train.tar) |
+|ch_PP-OCRv3_det| 【最新】超轻量模型，支持中英文、多语种文本检测 | 3.8M |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_distill_train.tar)|
+|ch_PP-OCRv3_rec|【最新】超轻量模型，支持中英文、数字识别|12.4M |[推理模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_train.tar) |
+|ch_ppstructure_mobile_v2.0_SLANet|基于SLANet的中文表格识别模型|9.3M|[推理模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_train.tar) |
 
 
 <a name="73"></a>

ppstructure/docs/inference.md

@@ -4,7 +4,7 @@
   - [1.1 版面分析+表格识别](#1.1)
   - [1.2 版面分析](#1.2)
   - [1.3 表格识别](#1.3)
-- [2. DocVQA](#2)
+- [2. 关键信息抽取](#2)
 
 <a name="1"></a>
 ## 1. Structure
@@ -16,23 +16,26 @@ cd ppstructure
 下载模型
 ```bash
 mkdir inference && cd inference
-# 下载PP-OCRv2文本检测模型并解压
-wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_slim_quant_infer.tar && tar xf ch_PP-OCRv2_det_slim_quant_infer.tar
-# 下载PP-OCRv2文本识别模型并解压
-wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_infer.tar && tar xf ch_PP-OCRv2_rec_slim_quant_infer.tar
-# 下载超轻量级英文表格预测模型并解压
-wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar
+# 下载PP-Structurev2版面分析模型并解压
+wget https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_layout_infer.tar && tar xf picodet_lcnet_x1_0_layout_infer.tar
+# 下载PP-OCRv3文本检测模型并解压
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar && tar xf ch_PP-OCRv3_det_infer.tar
+# 下载PP-OCRv3文本识别模型并解压
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar && tar xf ch_PP-OCRv3_rec_infer.tar
+# 下载PP-Structurev2表格识别模型并解压
+wget https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar && tar xf ch_ppstructure_mobile_v2.0_SLANet_infer.tar
 cd ..
 ```
 <a name="1.1"></a>
 ### 1.1 版面分析+表格识别
 ```bash
-python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv2_det_slim_quant_infer \
-                          --rec_model_dir=inference/ch_PP-OCRv2_rec_slim_quant_infer \
-                          --table_model_dir=inference/en_ppocr_mobile_v2.0_table_structure_infer \
+python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv3_det_infer \
+                          --rec_model_dir=inference/ch_PP-OCRv3_rec_infer \
+                          --table_model_dir=inference/ch_ppstructure_mobile_v2.0_SLANet_infer \
+                          --layout_model_dir=inference/picodet_lcnet_x1_0_layout_infer \
                           --image_dir=./docs/table/1.png \
                           --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \
-                          --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt \
+                          --table_char_dict_path=../ppocr/utils/dict/table_structure_dict_ch.txt \
                           --output=../output \
                           --vis_font_path=../doc/fonts/simfang.ttf
 ```
@@ -41,19 +44,23 @@ python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv2_det_slim_quant_i
 <a name="1.2"></a>
 ### 1.2 版面分析
 ```bash
-python3 predict_system.py --image_dir=./docs/table/1.png --table=false --ocr=false --output=../output/
+python3 predict_system.py --layout_model_dir=inference/picodet_lcnet_x1_0_layout_infer \
+                          --image_dir=./docs/table/1.png \
+                          --output=../output \
+                          --table=false \
+                          --ocr=false
 ```
 运行完成后，每张图片会在`output`字段指定的目录下的`structure`目录下有一个同名目录，图片区域会被裁剪之后保存下来，图片名为表格在图片里的坐标。版面分析结果会存储在`res.txt`文件中。
 
 <a name="1.3"></a>
 ### 1.3 表格识别
 ```bash
-python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv2_det_slim_quant_infer \
-                          --rec_model_dir=inference/ch_PP-OCRv2_rec_slim_quant_infer \
-                          --table_model_dir=inference/en_ppocr_mobile_v2.0_table_structure_infer \
+python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv3_det_infer \
+                          --rec_model_dir=inference/ch_PP-OCRv3_rec_infer \
+                          --table_model_dir=inference/ch_ppstructure_mobile_v2.0_SLANet_infer \
                           --image_dir=./docs/table/table.jpg \
                           --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \
-                          --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt \
+                          --table_char_dict_path=../ppocr/utils/dict/table_structure_dict_ch.txt \
                           --output=../output \
                           --vis_font_path=../doc/fonts/simfang.ttf \
                           --layout=false
@@ -61,20 +68,22 @@ python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv2_det_slim_quant_i
 运行完成后，每张图片会在`output`字段指定的目录下的`structure`目录下有一个同名目录，表格会存储为一个excel，excel文件名为`[0,0,img_h,img_w]`。
 
 <a name="2"></a>
-## 2. DocVQA
+## 2. 关键信息抽取
 
 ```bash
 cd ppstructure
 
-# 下载模型
 mkdir inference && cd inference
-# 下载SER xfun 模型并解压
-wget https://paddleocr.bj.bcebos.com/pplayout/PP-Layout_v1.0_ser_pretrained.tar && tar xf PP-Layout_v1.0_ser_pretrained.tar
+# 下载SER XFUND 模型并解压
+wget https://paddleocr.bj.bcebos.com/ppstructure/models/vi_layoutxlm/ser_vi_layoutxlm_xfund_infer.tar && tar -xf ser_vi_layoutxlm_xfund_infer.tar
 cd ..
-
-python3 predict_system.py --model_name_or_path=kie/PP-Layout_v1.0_ser_pretrained/ \
-                          --mode=kie \
-                          --image_dir=kie/images/input/zh_val_0.jpg  \
-                          --vis_font_path=../doc/fonts/simfang.ttf
+python3 kie/predict_kie_token_ser.py \
+  --kie_algorithm=LayoutXLM \
+  --ser_model_dir=../inference/ser_vi_layoutxlm_xfund_infer \
+  --image_dir=./docs/kie/input/zh_val_42.jpg \
+  --ser_dict_path=../ppocr/utils/dict/kie_dict/xfund_class_list.txt \
+  --vis_font_path=../doc/fonts/simfang.ttf \
+  --ocr_order_method="tb-yx"
 ```
+
 运行完成后，每张图片会在`output`字段指定的目录下的`kie`目录下存放可视化之后的图片，图片名和输入图片名一致。

ppstructure/docs/inference_en.md

@@ -4,7 +4,7 @@
   - [1.1 layout analysis + table recognition](#1.1)
   - [1.2 layout analysis](#1.2)
   - [1.3 table recognition](#1.3)
-- [2. DocVQA](#2)
+- [2. KIE](#2)
 
 <a name="1"></a>
 ## 1. Structure
@@ -18,23 +18,26 @@ download model
 
 ```bash
 mkdir inference && cd inference
-# Download the PP-OCRv2 text detection model and unzip it
-wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_slim_quant_infer.tar && tar xf ch_PP-OCRv2_det_slim_quant_infer.tar
-# Download the PP-OCRv2 text recognition model and unzip it
-wget https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_infer.tar && tar xf ch_PP-OCRv2_rec_slim_quant_infer.tar
-# Download the ultra-lightweight English table structure model and unzip it
-wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar && tar xf en_ppocr_mobile_v2.0_table_structure_infer.tar
+# Download the PP-Structurev2 layout analysis model and unzip it
+wget https://paddleocr.bj.bcebos.com/ppstructure/models/layout/picodet_lcnet_x1_0_layout_infer.tar && tar xf picodet_lcnet_x1_0_layout_infer.tar
+# Download the PP-OCRv3 text detection model and unzip it
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar && tar xf ch_PP-OCRv3_det_infer.tar
+# Download the PP-OCRv3 text recognition model and unzip it
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar && tar xf ch_PP-OCRv3_rec_infer.tar
+# Download the PP-Structurev2 form recognition model and unzip it
+wget https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar && tar xf ch_ppstructure_mobile_v2.0_SLANet_infer.tar
 cd ..
 ```
 <a name="1.1"></a>
 ### 1.1 layout analysis + table recognition
 ```bash
-python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv2_det_slim_quant_infer \
-                          --rec_model_dir=inference/ch_PP-OCRv2_rec_slim_quant_infer \
-                          --table_model_dir=inference/en_ppocr_mobile_v2.0_table_structure_infer \
+python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv3_det_infer \
+                          --rec_model_dir=inference/ch_PP-OCRv3_rec_infer \
+                          --table_model_dir=inference/ch_ppstructure_mobile_v2.0_SLANet_infer \
+                          --layout_model_dir=inference/picodet_lcnet_x1_0_layout_infer \
                           --image_dir=./docs/table/1.png \
                           --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \
-                          --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt \
+                          --table_char_dict_path=../ppocr/utils/dict/table_structure_dict_ch.txt \
                           --output=../output \
                           --vis_font_path=../doc/fonts/simfang.ttf
 ```
@@ -43,19 +46,23 @@ After the operation is completed, each image will have a directory with the same
 <a name="1.2"></a>
 ### 1.2 layout analysis
 ```bash
-python3 predict_system.py --image_dir=./docs/table/1.png --table=false --ocr=false --output=../output/
+python3 predict_system.py --layout_model_dir=inference/picodet_lcnet_x1_0_layout_infer \
+                          --image_dir=./docs/table/1.png \
+                          --output=../output \
+                          --table=false \
+                          --ocr=false
 ```
 After the operation is completed, each image will have a directory with the same name in the `structure` directory under the directory specified by the `output` field. Each picture in image will be cropped and saved. The filename of picture area is their coordinates in the image. Layout analysis results will be stored in the `res.txt` file
 
 <a name="1.3"></a>
 ### 1.3 table recognition
 ```bash
-python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv2_det_slim_quant_infer \
-                          --rec_model_dir=inference/ch_PP-OCRv2_rec_slim_quant_infer \
-                          --table_model_dir=inference/en_ppocr_mobile_v2.0_table_structure_infer \
+python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv3_det_infer \
+                          --rec_model_dir=inference/ch_PP-OCRv3_rec_infer \
+                          --table_model_dir=inference/ch_ppstructure_mobile_v2.0_SLANet_infer \
                           --image_dir=./docs/table/table.jpg \
                           --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \
-                          --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt \
+                          --table_char_dict_path=../ppocr/utils/dict/table_structure_dict_ch.txt \
                           --output=../output \
                           --vis_font_path=../doc/fonts/simfang.ttf \
                           --layout=false
@@ -63,19 +70,22 @@ python3 predict_system.py --det_model_dir=inference/ch_PP-OCRv2_det_slim_quant_i
 After the operation is completed, each image will have a directory with the same name in the `structure` directory under the directory specified by the `output` field. Each table in the image will be stored as an excel. The filename of excel is their coordinates in the image.
 
 <a name="2"></a>
-## 2. DocVQA
+## 2. KIE
 
 ```bash
 cd ppstructure
 
-# download model
 mkdir inference && cd inference
-wget https://paddleocr.bj.bcebos.com/pplayout/PP-Layout_v1.0_ser_pretrained.tar && tar xf PP-Layout_v1.0_ser_pretrained.tar
+# download model
+wget https://paddleocr.bj.bcebos.com/ppstructure/models/vi_layoutxlm/ser_vi_layoutxlm_xfund_infer.tar && tar -xf ser_vi_layoutxlm_xfund_infer.tar
 cd ..
-
-python3 predict_system.py --model_name_or_path=kie/PP-Layout_v1.0_ser_pretrained/ \
-                          --mode=kie \
-                          --image_dir=kie/images/input/zh_val_0.jpg  \
-                          --vis_font_path=../doc/fonts/simfang.ttf
+python3 kie/predict_kie_token_ser.py \
+  --kie_algorithm=LayoutXLM \
+  --ser_model_dir=../inference/ser_vi_layoutxlm_xfund_infer \
+  --image_dir=./docs/kie/input/zh_val_42.jpg \
+  --ser_dict_path=../ppocr/utils/dict/kie_dict/xfund_class_list.txt \
+  --vis_font_path=../doc/fonts/simfang.ttf \
+  --ocr_order_method="tb-yx"
 ```
+
 After the operation is completed, each image will store the visualized image in the `kie` directory under the directory specified by the `output` field, and the image name is the same as the input image name.

ppstructure/docs/installation.md

 - [快速安装](#快速安装)
   - [1. PaddlePaddle 和 PaddleOCR](#1-paddlepaddle-和-paddleocr)
   - [2. 安装其他依赖](#2-安装其他依赖)
-    - [2.1  VQA所需依赖](#21--kie所需依赖)
+    - [2.1 KIE所需依赖](#21-kie所需依赖)
 
 # 快速安装
 
@@ -11,16 +11,11 @@
 
 ## 2. 安装其他依赖
 
-### 2.1  VQA所需依赖
-* paddleocr
+### 2.1  KIE所需依赖
 
-```bash
-pip3 install paddleocr
-```
+* paddleocr
 
-* PaddleNLP
 ```bash
-git clone https://github.com/PaddlePaddle/PaddleNLP -b develop
-cd PaddleNLP
-pip3 install -e .
+pip install paddleocr -U
+pip install -r ./kie/requirements.txt
 ```

ppstructure/docs/installation_en.md

@@ -2,7 +2,7 @@
 
 - [1. PaddlePaddle 和 PaddleOCR](#1)
 - [2. Install other dependencies](#2)
-  - [2.1  VQA](#21)
+  - [2.1 KIE](#21)
 
 
 <a name="1"></a>
@@ -14,17 +14,11 @@ Please refer to [PaddleOCR installation documentation](../../doc/doc_en/installa
 ## 2. Install other dependencies
 
 <a name="21"></a>
-### 2.1  VQA
+### 2.1  KIE
 
 * paddleocr
 
 ```bash
-pip3 install paddleocr
-```
-
-* PaddleNLP
-```bash
-git clone https://github.com/PaddlePaddle/PaddleNLP -b develop
-cd PaddleNLP
-pip3 install -e .
+pip install paddleocr -U
+pip install -r ./kie/requirements.txt
 ```

ppstructure/docs/models_list.md

@@ -28,8 +28,8 @@
 
 |模型名称|模型简介|推理模型大小|下载地址|
 | --- | --- | --- | --- |
-|en_ppocr_mobile_v2.0_table_det|PubLayNet数据集训练的英文表格场景的文字检测|4.7M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_det_train.tar) |
-|en_ppocr_mobile_v2.0_table_rec|PubLayNet数据集训练的英文表格场景的文字识别|6.9M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_rec_train.tar) |
+|en_ppocr_mobile_v2.0_table_det|PubTabNet数据集训练的英文表格场景的文字检测|4.7M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_det_train.tar) |
+|en_ppocr_mobile_v2.0_table_rec|PubTabNet数据集训练的英文表格场景的文字识别|6.9M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_rec_train.tar) |
 
 如需要使用其他OCR模型，可以在 [PP-OCR model_list](../../doc/doc_ch/models_list.md) 下载模型或者使用自己训练好的模型配置到 `det_model_dir`, `rec_model_dir`两个字段即可。
 
@@ -40,7 +40,7 @@
 | --- | --- | --- | --- |
 |en_ppocr_mobile_v2.0_table_structure|基于TableRec-RARE在PubTabNet数据集上训练的英文表格识别模型|6.8M|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_structure_train.tar) |
 |en_ppstructure_mobile_v2.0_SLANet|基于SLANet在PubTabNet数据集上训练的英文表格识别模型|9.2M|[推理模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_train.tar) |
-|ch_ppstructure_mobile_v2.0_SLANet|基于SLANet在PubTabNet数据集上训练的中文表格识别模型|9.3M|[推理模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_train.tar) |
+|ch_ppstructure_mobile_v2.0_SLANet|基于SLANet的中文表格识别模型|9.3M|[推理模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_train.tar) |
 
 <a name="3"></a>
 

ppstructure/docs/models_list_en.md

@@ -39,7 +39,7 @@ If you need to use other OCR models, you can download the model in [PP-OCR model
 | --- |-----------------------------------------------------------------------------| --- | --- |
 |en_ppocr_mobile_v2.0_table_structure| English table recognition model trained on PubTabNet dataset based on TableRec-RARE |6.8M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/table/en_ppocr_mobile_v2.0_table_structure_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.1/table/en_ppocr_mobile_v2.0_table_structure_train.tar) |
 |en_ppstructure_mobile_v2.0_SLANet|English table recognition model trained on PubTabNet dataset based on SLANet|9.2M|[inference model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/en_ppstructure_mobile_v2.0_SLANet_train.tar) |
-|ch_ppstructure_mobile_v2.0_SLANet|Chinese table recognition model trained on PubTabNet dataset based on SLANet|9.3M|[inference model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_train.tar) |
+|ch_ppstructure_mobile_v2.0_SLANet|Chinese table recognition model based on SLANet|9.3M|[inference model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_train.tar) |
 
 <a name="3"></a>
 ## 3. KIE

ppstructure/docs/quickstart.md

@@ -7,18 +7,22 @@
     - [2.1.2 版面分析+表格识别](#212-版面分析表格识别)
     - [2.1.3 版面分析](#213-版面分析)
     - [2.1.4 表格识别](#214-表格识别)
-    - [2.1.5 DocVQA](#215-dockie)
+    - [2.1.5 关键信息抽取](#215-关键信息抽取)
     - [2.1.6 版面恢复](#216-版面恢复)
   - [2.2 代码使用](#22-代码使用)
-    - [2.2.1 图像方向分类版面分析表格识别](#221-图像方向分类版面分析表格识别)
+
+    - [2.2.1 图像方向+分类版面分析+表格识别](#221-图像方向分类版面分析表格识别)
     - [2.2.2 版面分析+表格识别](#222-版面分析表格识别)
     - [2.2.3 版面分析](#223-版面分析)
     - [2.2.4 表格识别](#224-表格识别)
-    - [2.2.5 DocVQA](#225-dockie)
+
+    - [2.2.5 关键信息抽取](#225-关键信息抽取)
     - [2.2.6 版面恢复](#226-版面恢复)
+
   - [2.3 返回结果说明](#23-返回结果说明)
-    - [2.3.1 版面分+表格识别](#231-版面分析表格识别)
-    - [2.3.2 DocVQA](#232-dockie)
+    - [2.3.1 版面分析+表格识别](#231-版面分析表格识别)
+    - [2.3.2 关键信息抽取](#232-关键信息抽取)
+
   - [2.4 参数说明](#24-参数说明)
 
 
@@ -28,8 +32,8 @@
 ```bash
 # 安装 paddleocr，推荐使用2.6版本
 pip3 install "paddleocr>=2.6"
-# 安装 DocVQA依赖包paddlenlp（如不需要DocVQA功能，可跳过）
-pip3 install paddlenlp
+# 安装 关键信息抽取 依赖包（如不需要KIE功能，可跳过）
+pip install -r kie/requirements.txt
 # 安装 图像方向分类依赖包paddleclas（如不需要图像方向分类功能，可跳过）
 pip3 install paddleclas
 ```
@@ -66,9 +70,8 @@ paddleocr --image_dir=PaddleOCR/ppstructure/docs/table/table.jpg --type=structur
 
 <a name="215"></a>
 
-#### 2.1.5 DocVQA
-
-请参考：[文档视觉问答](../kie/README.md)。
+#### 2.1.5 关键信息抽取
+请参考：[关键信息抽取教程](../kie/README_ch.md)。
 
 <a name="216"></a>
 
@@ -184,9 +187,9 @@ for line in result:
 ```
 
 <a name="225"></a>
-#### 2.2.5 DocVQA
+#### 2.2.5 关键信息抽取
 
-请参考：[文档视觉问答](../kie/README.md)。
+请参考：[关键信息抽取教程](../kie/README_ch.md)。
 
 <a name="226"></a>
 
@@ -249,9 +252,9 @@ dict 里各个字段说明如下
   ```
 
 <a name="232"></a>
-#### 2.3.2 DocVQA
+#### 2.3.2 关键信息抽取
 
-请参考：[文档视觉问答](../kie/README.md)。
+请参考：[关键信息抽取教程](../kie/README_ch.md)。
 
 <a name="24"></a>
 ### 2.4 参数说明

ppstructure/docs/quickstart_en.md

@@ -7,7 +7,7 @@
     - [2.1.2 layout analysis + table recognition](#212-layout-analysis--table-recognition)
     - [2.1.3 layout analysis](#213-layout-analysis)
     - [2.1.4 table recognition](#214-table-recognition)
-    - [2.1.5 DocVQA](#215-dockie)
+    - [2.1.5 Key Information Extraction](#215-Key-Information-Extraction)
     - [2.1.6 layout recovery](#216-layout-recovery)
   - [2.2 Use by code](#22-use-by-code)
     - [2.2.1 image orientation + layout analysis + table recognition](#221-image-orientation--layout-analysis--table-recognition)
@@ -15,10 +15,11 @@
     - [2.2.3 layout analysis](#223-layout-analysis)
     - [2.2.4 table recognition](#224-table-recognition)
     - [2.2.5 DocVQA](#225-dockie)
+    - [2.2.5 Key Information Extraction](#225-Key-Information-Extraction)
     - [2.2.6 layout recovery](#226-layout-recovery)  
   - [2.3 Result description](#23-result-description)
     - [2.3.1 layout analysis + table recognition](#231-layout-analysis--table-recognition)
-    - [2.3.2 DocVQA](#232-dockie)
+    - [2.3.2 Key Information Extraction](#232-Key-Information-Extraction)
   - [2.4 Parameter Description](#24-parameter-description)
 
 
@@ -28,14 +29,14 @@
 ```bash
 # Install paddleocr, version 2.6 is recommended
 pip3 install "paddleocr>=2.6"
-# Install the DocVQA dependency package paddlenlp (if you do not use the DocVQA, you can skip it)
-pip3 install paddlenlp
+# Install the KIE dependency packages (if you do not use the KIE, you can skip it)
+pip install -r kie/requirements.txt
 # Install the image direction classification dependency package paddleclas (if you do not use the image direction classification, you can skip it)
 pip3 install paddleclas
-
 ```
 
 <a name="2"></a>
+
 ## 2. Use
 
 <a name="21"></a>
@@ -66,9 +67,9 @@ paddleocr --image_dir=PaddleOCR/ppstructure/docs/table/table.jpg --type=structur
 ```
 
 <a name="215"></a>
-#### 2.1.5 DocVQA
+#### 2.1.5 Key Information Extraction
 
-Please refer to: [Documentation Visual Q&A](../kie/README.md) .
+Please refer to: [Key Information Extraction](../kie/README.md) .
 
 <a name="216"></a>
 #### 2.1.6 layout recovery
@@ -130,7 +131,7 @@ for line in result:
 
 from PIL import Image
 
-font_path = 'PaddleOCR/doc/fonts/simfang.ttf' # PaddleOCR下提供字体包
+font_path = 'PaddleOCR/doc/fonts/simfang.ttf' # font provieded in PaddleOCR
 image = Image.open(img_path).convert('RGB')
 im_show = draw_structure_result(image, result,font_path=font_path)
 im_show = Image.fromarray(im_show)
@@ -180,9 +181,9 @@ for line in result:
 ```
 
 <a name="225"></a>
-#### 2.2.5 DocVQA
+#### 2.2.5 Key Information Extraction
 
-Please refer to: [Documentation Visual Q&A](../kie/README.md) .
+Please refer to: [Key Information Extraction](../kie/README.md) .
 
 <a name="226"></a>
 #### 2.2.6 layout recovery
@@ -244,9 +245,9 @@ After the recognition is completed, each image will have a directory with the sa
   ```
 
 <a name="232"></a>
-#### 2.3.2 DocVQA
+#### 2.3.2 Key Information Extraction
 
-Please refer to: [Documentation Visual Q&A](../kie/README.md) .
+Please refer to: [Key Information Extraction](../kie/README.md) .
 
 <a name="24"></a>
 ### 2.4 Parameter Description

ppstructure/kie/README.md

@@ -246,7 +246,7 @@ For training, evaluation and inference tutorial for text recognition models, ple
 
 If you want to finish the KIE tasks in your scene, and don't know what to prepare,  please refer to [End cdoc](../../doc/doc_en/recognition.md).
 
-关于怎样在自己的场景中完成关键信息抽取任务，请参考：[Guide to End-to-end KIE](./how_to_do_kie_en.md)。
+To complete the key information extraction task in your own scenario from data preparation to model selection, please refer to: [Guide to End-to-end KIE](./how_to_do_kie_en.md)。
 
 
 ## 5. Reference

ppstructure/kie/tools/eval_with_label_end2end.py

@@ -20,7 +20,7 @@ from shapely.geometry import Polygon
 import numpy as np
 from collections import defaultdict
 import operator
-import Levenshtein
+from rapidfuzz.distance import Levenshtein
 import argparse
 import json
 import copy

ppstructure/table/README.md

@@ -59,16 +59,16 @@ cd PaddleOCR/ppstructure
 # download model
 mkdir inference && cd inference
 # Download the PP-OCRv3 text detection model and unzip it
-wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_infer.tar && tar xf ch_PP-OCRv3_det_slim_infer.tar
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar && tar xf ch_PP-OCRv3_det_infer.tar
 # Download the PP-OCRv3 text recognition model and unzip it
-wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar && tar xf ch_PP-OCRv3_rec_slim_infer.tar
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar && tar xf ch_PP-OCRv3_rec_infer.tar
 # Download the PP-Structurev2 form recognition model and unzip it
 wget https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar && tar xf ch_ppstructure_mobile_v2.0_SLANet_infer.tar
 cd ..
 # run
 python3.7 table/predict_table.py \
-    --det_model_dir=inference/ch_PP-OCRv3_det_slim_infer \
-    --rec_model_dir=inference/ch_PP-OCRv3_rec_slim_infer  \
+    --det_model_dir=inference/ch_PP-OCRv3_det_infer \
+    --rec_model_dir=inference/ch_PP-OCRv3_rec_infer  \
     --table_model_dir=inference/ch_ppstructure_mobile_v2.0_SLANet_infer \
     --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \
     --table_char_dict_path=../ppocr/utils/dict/table_structure_dict_ch.txt \

ppstructure/table/README_ch.md

@@ -64,16 +64,16 @@ cd PaddleOCR/ppstructure
 # 下载模型
 mkdir inference && cd inference
 # 下载PP-OCRv3文本检测模型并解压
-wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_infer.tar && tar xf ch_PP-OCRv3_det_slim_infer.tar
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_infer.tar && tar xf ch_PP-OCRv3_det_infer.tar
 # 下载PP-OCRv3文本识别模型并解压
-wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.tar && tar xf ch_PP-OCRv3_rec_slim_infer.tar
+wget https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_infer.tar && tar xf ch_PP-OCRv3_rec_infer.tar
 # 下载PP-Structurev2表格识别模型并解压
 wget https://paddleocr.bj.bcebos.com/ppstructure/models/slanet/ch_ppstructure_mobile_v2.0_SLANet_infer.tar && tar xf ch_ppstructure_mobile_v2.0_SLANet_infer.tar
 cd ..
 # 执行表格识别
 python table/predict_table.py \
-    --det_model_dir=inference/ch_PP-OCRv3_det_slim_infer \
-    --rec_model_dir=inference/ch_PP-OCRv3_rec_slim_infer  \
+    --det_model_dir=inference/ch_PP-OCRv3_det_infer \
+    --rec_model_dir=inference/ch_PP-OCRv3_rec_infer  \
     --table_model_dir=inference/ch_ppstructure_mobile_v2.0_SLANet_infer \
     --rec_char_dict_path=../ppocr/utils/ppocr_keys_v1.txt \
     --table_char_dict_path=../ppocr/utils/dict/table_structure_dict_ch.txt \

ppstructure/table/table_metric/table_metric.py

@@ -9,7 +9,7 @@
 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 # Apache 2.0 License for more details.
 
-import distance
+from rapidfuzz.distance import Levenshtein
 from apted import APTED, Config
 from apted.helpers import Tree
 from lxml import etree, html
@@ -39,17 +39,6 @@ class TableTree(Tree):
 
 
 class CustomConfig(Config):
-    @staticmethod
-    def maximum(*sequences):
-        """Get maximum possible value
-        """
-        return max(map(len, sequences))
-
-    def normalized_distance(self, *sequences):
-        """Get distance from 0 to 1
-        """
-        return float(distance.levenshtein(*sequences)) / self.maximum(*sequences)
-
     def rename(self, node1, node2):
         """Compares attributes of trees"""
         #print(node1.tag)
@@ -58,23 +47,12 @@ class CustomConfig(Config):
         if node1.tag == 'td':
             if node1.content or node2.content:
                 #print(node1.content, )
-                return self.normalized_distance(node1.content, node2.content)
+                return Levenshtein.normalized_distance(node1.content, node2.content)
         return 0.
 
 
 
 class CustomConfig_del_short(Config):
-    @staticmethod
-    def maximum(*sequences):
-        """Get maximum possible value
-        """
-        return max(map(len, sequences))
-
-    def normalized_distance(self, *sequences):
-        """Get distance from 0 to 1
-        """
-        return float(distance.levenshtein(*sequences)) / self.maximum(*sequences)
-
     def rename(self, node1, node2):
         """Compares attributes of trees"""
         if (node1.tag != node2.tag) or (node1.colspan != node2.colspan) or (node1.rowspan != node2.rowspan):
@@ -90,21 +68,10 @@ class CustomConfig_del_short(Config):
                     node1_content = ['####']
                 if len(node2_content) < 3:
                     node2_content = ['####']   
-                return self.normalized_distance(node1_content, node2_content)
+                return Levenshtein.normalized_distance(node1_content, node2_content)
         return 0.
 
 class CustomConfig_del_block(Config):
-    @staticmethod
-    def maximum(*sequences):
-        """Get maximum possible value
-        """
-        return max(map(len, sequences))
-
-    def normalized_distance(self, *sequences):
-        """Get distance from 0 to 1
-        """
-        return float(distance.levenshtein(*sequences)) / self.maximum(*sequences)
-
     def rename(self, node1, node2):
         """Compares attributes of trees"""
         if (node1.tag != node2.tag) or (node1.colspan != node2.colspan) or (node1.rowspan != node2.rowspan):
@@ -120,7 +87,7 @@ class CustomConfig_del_block(Config):
                 while ' ' in node2_content:
                     print(node2_content.index(' '))
                     node2_content.pop(node2_content.index(' '))
-                return self.normalized_distance(node1_content, node2_content)
+                return Levenshtein.normalized_distance(node1_content, node2_content)
         return 0.
 
 class TEDS(object):

ppstructure/utility.py

@@ -38,7 +38,7 @@ def init_args():
     parser.add_argument(
         "--layout_dict_path",
         type=str,
-        default="../ppocr/utils/dict/layout_dict/layout_pubalynet_dict.txt")
+        default="../ppocr/utils/dict/layout_dict/layout_publaynet_dict.txt")
     parser.add_argument(
         "--layout_score_threshold",
         type=float,

requirements.txt

@@ -6,7 +6,7 @@ lmdb
 tqdm
 numpy
 visualdl
-python-Levenshtein
+rapidfuzz
 opencv-contrib-python==4.4.0.46
 cython
 lxml

tools/infer/predict_system.py

@@ -120,11 +120,14 @@ def sorted_boxes(dt_boxes):
     _boxes = list(sorted_boxes)
 
     for i in range(num_boxes - 1):
-        if abs(_boxes[i + 1][0][1] - _boxes[i][0][1]) < 10 and \
-                (_boxes[i + 1][0][0] < _boxes[i][0][0]):
-            tmp = _boxes[i]
-            _boxes[i] = _boxes[i + 1]
-            _boxes[i + 1] = tmp
+        for j in range(i, 0, -1):
+            if abs(_boxes[j + 1][0][1] - _boxes[j][0][1]) < 10 and \
+                    (_boxes[j + 1][0][0] < _boxes[j][0][0]):
+                tmp = _boxes[j]
+                _boxes[j] = _boxes[j + 1]
+                _boxes[j + 1] = tmp
+            else:
+                break
     return _boxes
 
 

tools/infer/utility.py

@@ -228,7 +228,8 @@ def create_predictor(args, mode, logger):
                 # collect shape
                 if args.shape_info_filename is not None:
                     if not os.path.exists(args.shape_info_filename):
-                    config.collect_shape_range_info(args.shape_info_filename)
+                        config.collect_shape_range_info(
+                            args.shape_info_filename)
                         logger.info(
                             f"collect dynamic shape info into : {args.shape_info_filename}"
                         )
@@ -549,7 +550,7 @@ def text_visual(texts,
 def base64_to_cv2(b64str):
     import base64
     data = base64.b64decode(b64str.encode('utf8'))
-    data = np.fromstring(data, np.uint8)
+    data = np.frombuffer(data, np.uint8)
     data = cv2.imdecode(data, cv2.IMREAD_COLOR)
     return data
 

tools/infer_kie.py

@@ -88,6 +88,29 @@ def draw_kie_result(batch, node, idx_to_cls, count):
     cv2.imwrite(save_path, vis_img)
     logger.info("The Kie Image saved in {}".format(save_path))
 
+def write_kie_result(fout, node, data):
+    """
+    Write infer result to output file, sorted by the predict label of each line.
+    The format keeps the same as the input with additional score attribute.
+    """
+    import json
+    label = data['label']
+    annotations = json.loads(label)
+    max_value, max_idx = paddle.max(node, -1), paddle.argmax(node, -1)
+    node_pred_label = max_idx.numpy().tolist()
+    node_pred_score = max_value.numpy().tolist()
+    res = []
+    for i, label in enumerate(node_pred_label):
+        pred_score = '{:.2f}'.format(node_pred_score[i])
+        pred_res = {
+                'label': label,
+                'transcription': annotations[i]['transcription'],
+                'score': pred_score,
+                'points': annotations[i]['points'],
+            }
+        res.append(pred_res)
+    res.sort(key=lambda x: x['label'])
+    fout.writelines([json.dumps(res, ensure_ascii=False) + '\n'])
 
 def main():
     global_config = config['Global']
@@ -114,7 +137,7 @@ def main():
 
     warmup_times = 0
     count_t = []
-    with open(save_res_path, "wb") as fout:
+    with open(save_res_path, "w") as fout:
         with open(config['Global']['infer_img'], "rb") as f:
             lines = f.readlines()
             for index, data_line in enumerate(lines):
@@ -139,6 +162,8 @@ def main():
                 node = F.softmax(node, -1)
                 count_t.append(time.time() - st)
                 draw_kie_result(batch, node, idx_to_cls, index)
+                write_kie_result(fout, node, data)
+        fout.close()
     logger.info("success!")
     logger.info("It took {} s for predict {} images.".format(
         np.sum(count_t), len(count_t)))

tools/infer_kie_token_ser_re.py

@@ -39,7 +39,7 @@ from ppocr.utils.visual import draw_re_results
 from ppocr.utils.logging import get_logger
 from ppocr.utils.utility import get_image_file_list, load_vqa_bio_label_maps, print_dict
 from tools.program import ArgsParser, load_config, merge_config
-from tools.infer_vqa_token_ser import SerPredictor
+from tools.infer_kie_token_ser import SerPredictor
 
 
 class ReArgsParser(ArgsParser):