merge dygraph

ppocr/modeling/transforms/tps.py

@@ -230,15 +230,8 @@ class GridGenerator(nn.Layer):
     def build_inv_delta_C_paddle(self, C):
         """ Return inv_delta_C which is needed to calculate T """
         F = self.F
-        hat_C = paddle.zeros((F, F), dtype='float64')  # F x F
-        for i in range(0, F):
-            for j in range(i, F):
-                if i == j:
-                    hat_C[i, j] = 1
-                else:
-                    r = paddle.norm(C[i] - C[j])
-                    hat_C[i, j] = r
-                    hat_C[j, i] = r
+        hat_eye = paddle.eye(F, dtype='float64')  # F x F
+        hat_C = paddle.norm(C.reshape([1, F, 2]) - C.reshape([F, 1, 2]), axis=2) + hat_eye
         hat_C = (hat_C**2) * paddle.log(hat_C)
         delta_C = paddle.concat(  # F+3 x F+3
             [

ppocr/postprocess/__init__.py

@@ -24,7 +24,8 @@ __all__ = ['build_post_process']
 from .db_postprocess import DBPostProcess
 from .east_postprocess import EASTPostProcess
 from .sast_postprocess import SASTPostProcess
-from .rec_postprocess import CTCLabelDecode, AttnLabelDecode, SRNLabelDecode, DistillationCTCLabelDecode
+from .rec_postprocess import CTCLabelDecode, AttnLabelDecode, SRNLabelDecode, DistillationCTCLabelDecode, \
+    TableLabelDecode
 from .cls_postprocess import ClsPostProcess
 from .pg_postprocess import PGPostProcess
 
@@ -33,7 +34,7 @@ def build_post_process(config, global_config=None):
     support_dict = [
         'DBPostProcess', 'EASTPostProcess', 'SASTPostProcess', 'CTCLabelDecode',
         'AttnLabelDecode', 'ClsPostProcess', 'SRNLabelDecode', 'PGPostProcess',
-        'DistillationCTCLabelDecode'
+        'DistillationCTCLabelDecode', 'TableLabelDecode'
     ]
 
     config = copy.deepcopy(config)

ppocr/postprocess/rec_postprocess.py

@@ -44,16 +44,16 @@ class BaseRecLabelDecode(object):
             self.character_str = string.printable[:-6]
             dict_character = list(self.character_str)
         elif character_type in support_character_type:
-            self.character_str = ""
+            self.character_str = []
             assert character_dict_path is not None, "character_dict_path should not be None when character_type is {}".format(
                 character_type)
             with open(character_dict_path, "rb") as fin:
                 lines = fin.readlines()
                 for line in lines:
                     line = line.decode('utf-8').strip("\n").strip("\r\n")
-                    self.character_str += line
+                    self.character_str.append(line)
             if use_space_char:
-                self.character_str += " "
+                self.character_str.append(" ")
             dict_character = list(self.character_str)
 
         else:
@@ -319,3 +319,138 @@ class SRNLabelDecode(BaseRecLabelDecode):
             assert False, "unsupport type %s in get_beg_end_flag_idx" \
                           % beg_or_end
         return idx
+
+
+class TableLabelDecode(object):
+    """  """
+
+    def __init__(self,
+                 character_dict_path,
+                 **kwargs):
+        list_character, list_elem = self.load_char_elem_dict(character_dict_path)
+        list_character = self.add_special_char(list_character)
+        list_elem = self.add_special_char(list_elem)
+        self.dict_character = {}
+        self.dict_idx_character = {}
+        for i, char in enumerate(list_character):
+            self.dict_idx_character[i] = char
+            self.dict_character[char] = i
+        self.dict_elem = {}
+        self.dict_idx_elem = {}
+        for i, elem in enumerate(list_elem):
+            self.dict_idx_elem[i] = elem
+            self.dict_elem[elem] = i
+
+    def load_char_elem_dict(self, character_dict_path):
+        list_character = []
+        list_elem = []
+        with open(character_dict_path, "rb") as fin:
+            lines = fin.readlines()
+            substr = lines[0].decode('utf-8').strip("\n").split("\t")
+            character_num = int(substr[0])
+            elem_num = int(substr[1])
+            for cno in range(1, 1 + character_num):
+                character = lines[cno].decode('utf-8').strip("\n")
+                list_character.append(character)
+            for eno in range(1 + character_num, 1 + character_num + elem_num):
+                elem = lines[eno].decode('utf-8').strip("\n")
+                list_elem.append(elem)
+        return list_character, list_elem
+
+    def add_special_char(self, list_character):
+        self.beg_str = "sos"
+        self.end_str = "eos"
+        list_character = [self.beg_str] + list_character + [self.end_str]
+        return list_character
+
+    def __call__(self, preds):
+        structure_probs = preds['structure_probs']
+        loc_preds = preds['loc_preds']
+        if isinstance(structure_probs,paddle.Tensor):
+            structure_probs = structure_probs.numpy()
+        if isinstance(loc_preds,paddle.Tensor):
+            loc_preds = loc_preds.numpy()
+        structure_idx = structure_probs.argmax(axis=2)
+        structure_probs = structure_probs.max(axis=2)
+        structure_str, structure_pos, result_score_list, result_elem_idx_list = self.decode(structure_idx,
+                                                                                            structure_probs, 'elem')
+        res_html_code_list = []
+        res_loc_list = []
+        batch_num = len(structure_str)
+        for bno in range(batch_num):
+            res_loc = []
+            for sno in range(len(structure_str[bno])):
+                text = structure_str[bno][sno]
+                if text in ['<td>', '<td']:
+                    pos = structure_pos[bno][sno]
+                    res_loc.append(loc_preds[bno, pos])
+            res_html_code = ''.join(structure_str[bno])
+            res_loc = np.array(res_loc)
+            res_html_code_list.append(res_html_code)
+            res_loc_list.append(res_loc)
+        return {'res_html_code': res_html_code_list, 'res_loc': res_loc_list, 'res_score_list': result_score_list,
+                'res_elem_idx_list': result_elem_idx_list,'structure_str_list':structure_str}
+
+    def decode(self, text_index, structure_probs, char_or_elem):
+        """convert text-label into text-index.
+        """
+        if char_or_elem == "char":
+            current_dict = self.dict_idx_character
+        else:
+            current_dict = self.dict_idx_elem
+            ignored_tokens = self.get_ignored_tokens('elem')
+            beg_idx, end_idx = ignored_tokens
+
+        result_list = []
+        result_pos_list = []
+        result_score_list = []
+        result_elem_idx_list = []
+        batch_size = len(text_index)
+        for batch_idx in range(batch_size):
+            char_list = []
+            elem_pos_list = []
+            elem_idx_list = []
+            score_list = []
+            for idx in range(len(text_index[batch_idx])):
+                tmp_elem_idx = int(text_index[batch_idx][idx])
+                if idx > 0 and tmp_elem_idx == end_idx:
+                    break
+                if tmp_elem_idx in ignored_tokens:
+                    continue
+
+                char_list.append(current_dict[tmp_elem_idx])
+                elem_pos_list.append(idx)
+                score_list.append(structure_probs[batch_idx, idx])
+                elem_idx_list.append(tmp_elem_idx)
+            result_list.append(char_list)
+            result_pos_list.append(elem_pos_list)
+            result_score_list.append(score_list)
+            result_elem_idx_list.append(elem_idx_list)
+        return result_list, result_pos_list, result_score_list, result_elem_idx_list
+
+    def get_ignored_tokens(self, char_or_elem):
+        beg_idx = self.get_beg_end_flag_idx("beg", char_or_elem)
+        end_idx = self.get_beg_end_flag_idx("end", char_or_elem)
+        return [beg_idx, end_idx]
+
+    def get_beg_end_flag_idx(self, beg_or_end, char_or_elem):
+        if char_or_elem == "char":
+            if beg_or_end == "beg":
+                idx = self.dict_character[self.beg_str]
+            elif beg_or_end == "end":
+                idx = self.dict_character[self.end_str]
+            else:
+                assert False, "Unsupport type %s in get_beg_end_flag_idx of char" \
+                              % beg_or_end
+        elif char_or_elem == "elem":
+            if beg_or_end == "beg":
+                idx = self.dict_elem[self.beg_str]
+            elif beg_or_end == "end":
+                idx = self.dict_elem[self.end_str]
+            else:
+                assert False, "Unsupport type %s in get_beg_end_flag_idx of elem" \
+                              % beg_or_end
+        else:
+            assert False, "Unsupport type %s in char_or_elem" \
+                          % char_or_elem
+        return idx

ppocr/utils/dict/table_dict.txt

+←
+</overline>
+☆
+─
+α
+
+ 
+⋅
+$
+ω
+ψ
+χ
+(
+υ
+≥
+σ
+,
+ρ
+ε
+0
+■
+4
+8
+✗
+b
+<
+✓
+Ψ
+Ω
+€
+D
+3
+Π
+H
+║
+</strike>
+L
+Φ
+Χ
+θ
+P
+κ
+λ
+μ
+T
+ξ
+X
+β
+γ
+δ
+\
+ζ
+η
+`
+d
+<strike>
+h
+f
+l
+Θ
+p
+√
+t
+</sub>
+x
+Β
+Γ
+Δ
+|
+ǂ
+ɛ
+j
+̧
+➢
+⁡
+̌
+′
+«
+△
+▲
+#
+</b>
+'
+Ι
++
+¶
+/
+▼
+⇑
+□
+·
+7
+▪
+;
+?
+➔
+∩
+C
+÷
+G
+⇒
+K
+<sup>
+O
+S
+С
+W
+Α
+[
+○
+_
+●
+‡
+c
+z
+g
+<i>
+o
+<sub>
+〈
+〉
+s
+⩽
+w
+φ
+ʹ
+{
+»
+∣
+̆
+e
+ˆ
+∈
+τ
+◆
+ι
+∅
+∆
+∙
+∘
+Ø
+ß
+✔
+∞
+∑
+−
+×
+◊
+∗
+∖
+˃
+˂
+∫
+"
+i
+&
+π
+↔
+*
+∥
+æ
+∧
+.
+⁄
+ø
+Q
+∼
+6
+⁎
+:
+★
+>
+a
+B
+≈
+F
+J
+̄
+N
+♯
+R
+V
+<overline>
+―
+Z
+♣
+^
+¤
+¥
+§
+<underline>
+¢
+£
+≦
+­
+≤
+‖
+Λ
+©
+n
+↓
+→
+↑
+r
+°
+±
+v
+<b>
+♂
+k
+♀
+~
+ᅟ
+̇
+@
+”
+♦
+ł
+®
+⊕
+„
+!
+</sup>
+%
+⇓
+)
+-
+1
+5
+9
+=
+А
+A
+‰
+⋆
+Σ
+E
+◦
+I
+※
+M
+m
+̨
+⩾
+†
+</i>
+•
+U
+Y
+

+]
+̸
+2
+‐
+–
+‒
+̂
+—
+̀
+́
+’
+‘
+⋮
+⋯
+̊
+“
+̈
+≧
+q
+u
+ı
+y
+</underline>
+​
+̃
+}
+ν

ppocr/utils/logging.py

@@ -22,7 +22,7 @@ logger_initialized = {}
 
 
 @functools.lru_cache()
-def get_logger(name='root', log_file=None, log_level=logging.INFO):
+def get_logger(name='root', log_file=None, log_level=logging.DEBUG):
     """Initialize and get a logger by name.
     If the logger has not been initialized, this method will initialize the
     logger by adding one or two handlers, otherwise the initialized logger will

ppocr/utils/network.py

+# copyright (c) 2020 PaddlePaddle Authors. All Rights Reserve.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+import os
+import sys
+import tarfile
+import requests
+from tqdm import tqdm
+
+from ppocr.utils.logging import get_logger
+
+
+def download_with_progressbar(url, save_path):
+    logger = get_logger()
+    response = requests.get(url, stream=True)
+    total_size_in_bytes = int(response.headers.get('content-length', 0))
+    block_size = 1024  # 1 Kibibyte
+    progress_bar = tqdm(total=total_size_in_bytes, unit='iB', unit_scale=True)
+    with open(save_path, 'wb') as file:
+        for data in response.iter_content(block_size):
+            progress_bar.update(len(data))
+            file.write(data)
+    progress_bar.close()
+    if total_size_in_bytes == 0 or progress_bar.n != total_size_in_bytes:
+        logger.error("Something went wrong while downloading models")
+        sys.exit(0)
+
+
+def maybe_download(model_storage_directory, url):
+    # using custom model
+    tar_file_name_list = [
+        'inference.pdiparams', 'inference.pdiparams.info', 'inference.pdmodel'
+    ]
+    if not os.path.exists(
+            os.path.join(model_storage_directory, 'inference.pdiparams')
+    ) or not os.path.exists(
+        os.path.join(model_storage_directory, 'inference.pdmodel')):
+        assert url.endswith('.tar'), 'Only supports tar compressed package'
+        tmp_path = os.path.join(model_storage_directory, url.split('/')[-1])
+        print('download {} to {}'.format(url, tmp_path))
+        os.makedirs(model_storage_directory, exist_ok=True)
+        download_with_progressbar(url, tmp_path)
+        with tarfile.open(tmp_path, 'r') as tarObj:
+            for member in tarObj.getmembers():
+                filename = None
+                for tar_file_name in tar_file_name_list:
+                    if tar_file_name in member.name:
+                        filename = tar_file_name
+                if filename is None:
+                    continue
+                file = tarObj.extractfile(member)
+                with open(
+                        os.path.join(model_storage_directory, filename),
+                        'wb') as f:
+                    f.write(file.read())
+        os.remove(tmp_path)
+
+
+def is_link(s):
+    return s is not None and s.startswith('http')
+
+
+def confirm_model_dir_url(model_dir, default_model_dir, default_url):
+    url = default_url
+    if model_dir is None or is_link(model_dir):
+        if is_link(model_dir):
+            url = model_dir
+        file_name = url.split('/')[-1][:-4]
+        model_dir = default_model_dir
+        model_dir = os.path.join(model_dir, file_name)
+    return model_dir, url

ppocr/utils/save_load.py

@@ -25,7 +25,7 @@ import paddle
 
 from ppocr.utils.logging import get_logger
 
-__all__ = ['init_model', 'save_model', 'load_dygraph_pretrain']
+__all__ = ['init_model', 'save_model', 'load_dygraph_params']
 
 
 def _mkdir_if_not_exist(path, logger):
@@ -89,6 +89,34 @@ def init_model(config, model, optimizer=None, lr_scheduler=None):
     return best_model_dict
 
 
+def load_dygraph_params(config, model, logger, optimizer):
+    ckp = config['Global']['checkpoints']
+    if ckp and os.path.exists(ckp):
+        pre_best_model_dict = init_model(config, model, optimizer)
+        return pre_best_model_dict
+    else:
+        pm = config['Global']['pretrained_model']
+        if pm is None:
+            return {}
+        if not os.path.exists(pm) or not os.path.exists(pm + ".pdparams"):
+            logger.info(f"The pretrained_model {pm} does not exists!")
+            return {}
+        pm = pm if pm.endswith('.pdparams') else pm + '.pdparams'
+        params = paddle.load(pm)
+        state_dict = model.state_dict()
+        new_state_dict = {}
+        for k1, k2 in zip(state_dict.keys(), params.keys()):
+            if list(state_dict[k1].shape) == list(params[k2].shape):
+                new_state_dict[k1] = params[k2]
+        else:
+            logger.info(
+                f"The shape of model params {k1} {state_dict[k1].shape} not matched with loaded params {k2} {params[k2].shape} !"
+            )
+        model.set_state_dict(new_state_dict)
+        logger.info(f"loaded pretrained_model successful from {pm}")
+        return {}
+
+
 def save_model(model,
                optimizer,
                model_path,

test1/MANIFEST.in

+include LICENSE
+include README.md
+
+recursive-include ppocr/utils *.txt utility.py logging.py network.py
+recursive-include ppocr/data/ *.py
+recursive-include ppocr/postprocess *.py
+recursive-include tools/infer *.py
+recursive-include test1 *.py
+

test1/__init__.py

+# copyright (c) 2020 PaddlePaddle Authors. All Rights Reserve.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from .paddlestructure import PaddleStructure, draw_result, to_excel
+
+__all__ = ['PaddleStructure', 'draw_result', 'to_excel']

test1/api.md

+# PaddleStructure
+
+install layoutparser
+```sh
+wget  https://paddleocr.bj.bcebos.com/whl/layoutparser-0.0.0-py3-none-any.whl
+pip3 install layoutparser-0.0.0-py3-none-any.whl
+```
+
+## 1. Introduction to pipeline
+
+PaddleStructure is a toolkit for complex layout text OCR, the process is as follows
+
+![pipeline](../doc/table/pipeline.png)
+
+In PaddleStructure, the image will be analyzed by layoutparser first. In the layout analysis, the area in the image will be classified, and the OCR process will be carried out according to the category.
+
+Currently layoutparser will output five categories:
+1. Text
+2. Title
+3. Figure
+4. List
+5. Table
+   
+Types 1-4 follow the traditional OCR process, and 5 follow the Table OCR process.
+
+## 2. LayoutParser
+
+
+## 3. Table OCR
+
+[doc](table/README.md)
+
+## 4. Predictive by inference engine
+
+Use the following commands to complete the inference
+```python
+python3 table/predict_system.py --det_model_dir=path/to/det_model_dir --rec_model_dir=path/to/rec_model_dir --table_model_dir=path/to/table_model_dir --image_dir=../doc/table/1.png --rec_char_dict_path=../ppocr/utils/dict/table_dict.txt --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt --rec_char_type=EN --det_limit_side_len=736 --det_limit_type=min --output ../output/table
+```
+After running, each image will have a directory with the same name under the directory specified in the output field. Each table in the picture will be stored as an excel, and the excel file name will be the coordinates of the table in the image.
+
+## 5. PaddleStructure whl package introduction
+
+### 5.1 Use
+
+5.1.1 Use by code
+```python
+import os
+import cv2
+from paddlestructure import PaddleStructure,draw_result,save_res
+
+table_engine = PaddleStructure(show_log=True)
+
+save_folder = './output/table'
+img_path = '../doc/table/1.png'
+img = cv2.imread(img_path)
+result = table_engine(img)
+save_res(result, save_folder,os.path.basename(img_path).split('.')[0])
+
+for line in result:
+    print(line)
+
+from PIL import Image
+
+font_path = 'path/tp/PaddleOCR/doc/fonts/simfang.ttf'
+image = Image.open(img_path).convert('RGB')
+im_show = draw_result(image, result,font_path=font_path)
+im_show = Image.fromarray(im_show)
+im_show.save('result.jpg')
+```
+
+5.1.2 Use by command line
+```bash
+paddlestructure --image_dir=../doc/table/1.png
+```
+
+### Parameter Description
+Most of the parameters are consistent with the paddleocr whl package, see [whl package documentation](../doc/doc_ch/whl.md)
+
+| Parameter                    | Description                                            | Default           |
+|------------------------|------------------------------------------------------|------------------|
+| output                 | The path where excel and recognition results are saved                    | ./output/table            |
+| structure_max_len      |  When the table structure model predicts, the long side of the image is resized             |  488            |
+| structure_model_dir      |  Table structure inference model path             |  None            |
+| structure_char_type      | Dictionary path used by table structure model             |  ../ppocr/utils/dict/table_structure_dict.tx            |
+
+

test1/api_ch.md

+# PaddleStructure
+
+安装layoutparser
+```sh
+wget  https://paddleocr.bj.bcebos.com/whl/layoutparser-0.0.0-py3-none-any.whl
+pip3 install layoutparser-0.0.0-py3-none-any.whl
+```
+
+## 1. pipeline介绍
+
+PaddleStructure 是一个用于复杂板式文字OCR的工具包，流程如下
+![pipeline](../doc/table/pipeline.png)
+
+在PaddleStructure中，图片会先经由layoutparser进行版面分析，在版面分析中，会对图片里的区域进行分类，根据根据类别进行对于的ocr流程。
+
+目前layoutparser会输出五个类别:
+1. Text
+2. Title
+3. Figure
+4. List
+5. Table
+   
+1-4类走传统的OCR流程，5走表格的OCR流程。
+
+## 2. LayoutParser
+
+[文档](layout/README.md)
+
+## 3. Table OCR
+
+[文档](table/README_ch.md)
+
+## 4. 预测引擎推理
+
+使用如下命令即可完成预测引擎的推理
+```python
+python3 table/predict_system.py --det_model_dir=path/to/det_model_dir --rec_model_dir=path/to/rec_model_dir --table_model_dir=path/to/table_model_dir --image_dir=../doc/table/1.png --rec_char_dict_path=../ppocr/utils/dict/table_dict.txt --table_char_dict_path=../ppocr/utils/dict/table_structure_dict.txt --rec_char_type=EN --det_limit_side_len=736 --det_limit_type=min --output ../output/table
+```
+运行完成后，每张图片会output字段指定的目录下有一个同名目录，图片里的每个表格会存储为一个excel，excel文件名为表格在图片里的坐标。
+
+## 5. PaddleStructure whl包介绍
+
+### 5.1 使用
+
+5.1.1 代码使用
+```python
+import os
+import cv2
+from paddlestructure import PaddleStructure,draw_result,save_res
+
+table_engine = PaddleStructure(show_log=True)
+
+save_folder = './output/table'
+img_path = '../doc/table/1.png'
+img = cv2.imread(img_path)
+result = table_engine(img)
+save_res(result, save_folder,os.path.basename(img_path).split('.')[0])
+
+for line in result:
+    print(line)
+
+from PIL import Image
+
+font_path = 'path/tp/PaddleOCR/doc/fonts/simfang.ttf'
+image = Image.open(img_path).convert('RGB')
+im_show = draw_result(image, result,font_path=font_path)
+im_show = Image.fromarray(im_show)
+im_show.save('result.jpg')
+```
+
+5.1.2 命令行使用
+```bash
+paddlestructure --image_dir=../doc/table/1.png
+```
+
+### 参数说明
+大部分参数和paddleocr whl包保持一致，见 [whl包文档](../doc/doc_ch/whl.md)
+
+| 字段                    | 说明                                            | 默认值           |
+|------------------------|------------------------------------------------------|------------------|
+| output                 | excel和识别结果保存的地址                    | ./output/table            |
+| table_max_len      |  表格结构模型预测时，图像的长边resize尺度             |  488            |
+| table_model_dir      |  表格结构模型 inference 模型地址             |  None            |
+| table_char_type      |  表格结构模型所用字典地址             |  ../ppocr/utils/dict/table_structure_dict.tx            |
+
+

test1/layout/README.md

+# 版面分析使用说明
+
+* [1. 安装whl包](#安装whl包)
+* [2. 使用](#使用)
+* [3. 后处理](#后处理)
+* [4. 指标](#指标)
+* [5. 训练版面分析模型](#训练版面分析模型)
+
+<a name="安装whl包"></a>
+
+## 1.  安装whl包
+```bash
+wget https://paddleocr.bj.bcebos.com/whl/layoutparser-0.0.0-py3-none-any.whl
+pip install -U layoutparser-0.0.0-py3-none-any.whl
+```
+
+<a name="使用"></a>
+
+## 2. 使用
+
+使用layoutparser识别给定文档的布局：
+
+```python
+import layoutparser as lp
+image = cv2.imread("imags/paper-image.jpg")
+image = image[..., ::-1]
+
+# 加载模型
+model = lp.PaddleDetectionLayoutModel(config_path="lp://PubLayNet/ppyolov2_r50vd_dcn_365e_publaynet/config", 
+                                threshold=0.5,
+                                label_map={0: "Text", 1: "Title", 2: "List", 3:"Table", 4:"Figure"},
+                                enforce_cpu=False, 
+                                enable_mkldnn=True)
+# 检测
+layout = model.detect(image)
+
+# 显示结果
+lp.draw_box(image, layout, box_width=3, show_element_type=True)
+```
+
+下图展示了结果，不同颜色的检测框表示不同的类别，并通过`show_element_type`在框的左上角显示具体类别：
+
+<div align="center">
+<img src="../../doc/table/result_all.jpg"  width = "600" />
+</div>
+
+`PaddleDetectionLayoutModel`函数参数说明如下:
+
+|      参数      |            含义             |   默认值    |                             备注                             |
+| :------------: | :-------------------------: | :---------: | :----------------------------------------------------------: |
+|  config_path   |        模型配置路径         |    None     | 指定config_path会自动下载模型(仅第一次，之后模型存在，不会再下载) |
+|   model_path   |          模型路径           |    None     | 本地模型路径，config_path和model_path必须设置一个，不能同时为None |
+|   threshold    |       预测得分的阈值        |     0.5     |                              \                               |
+|  input_shape   |     reshape之后图片尺寸     | [3,640,640] |                              \                               |
+|   batch_size   |       测试batch size        |      1      |                              \                               |
+|   label_map    |         类别映射表          |    None     | 设置config_path时，可以为None，根据数据集名称自动获取label_map |
+|  enforce_cpu   |     代码是否使用CPU运行     |    False    |         设置为False表示使用GPU，True表示强制使用CPU          |
+| enforce_mkldnn | CPU预测中是否开启MKLDNN加速 |    True     |                              \                               |
+|   thread_num   |        设置CPU线程数        |     10      |                              \                               |
+
+目前支持以下几种模型配置和label map，您可以通过修改 `--config_path`和 `--label_map`使用这些模型，从而检测不同类型的内容：
+
+| dataset                                                      | config_path                                                  | label_map                                                 |
+| ------------------------------------------------------------ | ------------------------------------------------------------ | --------------------------------------------------------- |
+| [TableBank](https://doc-analysis.github.io/tablebank-page/index.html) word | lp://TableBank/ppyolov2_r50vd_dcn_365e_tableBank_word/config | {0:"Table"}                                               |
+| TableBank latex                                              | lp://TableBank/ppyolov2_r50vd_dcn_365e_tableBank_latex/config | {0:"Table"}                                               |
+| [PubLayNet](https://github.com/ibm-aur-nlp/PubLayNet)        | lp://PubLayNet/ppyolov2_r50vd_dcn_365e_publaynet/config      | {0: "Text", 1: "Title", 2: "List", 3:"Table", 4:"Figure"} |
+
+* TableBank word和TableBank latex分别在word文档、latex文档数据集训练；
+* 下载TableBank数据集同时包含word和latex。
+
+<a name="后处理"></a>
+
+## 3. 后处理
+
+版面分析检测包含多个类别，如果只想获取指定类别(如"Text"类别)的检测框、可以使用下述代码：
+
+```python
+# 首先过滤特定文本类型的区域
+text_blocks = lp.Layout([b for b in layout if b.type=='Text'])
+figure_blocks = lp.Layout([b for b in layout if b.type=='Figure'])
+
+# 因为在图像区域内可能检测到文本区域，所以只需要删除它们
+text_blocks = lp.Layout([b for b in text_blocks \
+                   if not any(b.is_in(b_fig) for b_fig in figure_blocks)])
+
+# 对文本区域排序并分配id 
+h, w = image.shape[:2]
+
+left_interval = lp.Interval(0, w/2*1.05, axis='x').put_on_canvas(image)
+
+left_blocks = text_blocks.filter_by(left_interval, center=True)
+left_blocks.sort(key = lambda b:b.coordinates[1])
+
+right_blocks = [b for b in text_blocks if b not in left_blocks]
+right_blocks.sort(key = lambda b:b.coordinates[1])
+
+# 最终合并两个列表，并按顺序添加索引
+text_blocks = lp.Layout([b.set(id = idx) for idx, b in enumerate(left_blocks + right_blocks)])
+
+# 显示结果
+lp.draw_box(image, text_blocks,
+            box_width=3, 
+            show_element_id=True)
+```
+
+显示只有"Text"类别的结果：
+
+<div align="center">
+<img src="../../doc/table/result_text.jpg"  width = "600" />
+</div>
+
+<a name="指标"></a>
+
+## 4. 指标
+
+| Dataset   | mAP  | CPU time cost | GPU time cost |
+| --------- | ---- | ------------- | ------------- |
+| PubLayNet | 93.6 | 1713.7ms      | 66.6ms        |
+| TableBank | 96.2 | 1968.4ms      | 65.1ms        |
+
+**Envrionment：**	
+
+​	**CPU：**  Intel(R) Xeon(R) CPU E5-2650 v4 @ 2.20GHz，24core
+
+​	**GPU：**  a single NVIDIA Tesla P40
+
+<a name="训练版面分析模型"></a>
+
+## 5. 训练版面分析模型
+
+上述模型基于[PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection) 训练，如果您想训练自己的版面分析模型，请参考：[train_layoutparser_model](train_layoutparser_model.md)
+