Merge branch 'dygraph' of https://github.com/PaddlePaddle/PaddleOCR into test_v7

test1/setup.py

-# Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved.
-#
-# 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
-
-from setuptools import setup
-from io import open
-import shutil
-
-with open('../requirements.txt', encoding="utf-8-sig") as f:
-    requirements = f.readlines()
-    requirements.append('tqdm')
-
-
-def readme():
-    with open('api_ch.md', encoding="utf-8-sig") as f:
-        README = f.read()
-    return README
-
-
-shutil.copytree('./table', './test1/table')
-shutil.copyfile('./predict_system.py', './test1/predict_system.py')
-shutil.copyfile('./utility.py', './test1/utility.py')
-shutil.copytree('../ppocr', './ppocr')
-shutil.copytree('../tools', './tools')
-shutil.copyfile('../LICENSE', './LICENSE')
-
-setup(
-    name='paddlestructure',
-    packages=['paddlestructure'],
-    package_dir={'paddlestructure': ''},
-    include_package_data=True,
-    entry_points={"console_scripts": ["paddlestructure= paddlestructure.paddlestructure:main"]},
-    version='1.0',
-    install_requires=requirements,
-    license='Apache License 2.0',
-    description='Awesome OCR toolkits based on PaddlePaddle （8.6M ultra-lightweight pre-trained model, support training and deployment among server, mobile, embeded and IoT devices',
-    long_description=readme(),
-    long_description_content_type='text/markdown',
-    url='https://github.com/PaddlePaddle/PaddleOCR',
-    download_url='https://github.com/PaddlePaddle/PaddleOCR.git',
-    keywords=[
-        'ocr textdetection textrecognition paddleocr crnn east star-net rosetta ocrlite db chineseocr chinesetextdetection chinesetextrecognition'
-    ],
-    classifiers=[
-        'Intended Audience :: Developers', 'Operating System :: OS Independent',
-        'Natural Language :: Chinese (Simplified)',
-        'Programming Language :: Python :: 3',
-        'Programming Language :: Python :: 3.2',
-        'Programming Language :: Python :: 3.3',
-        'Programming Language :: Python :: 3.4',
-        'Programming Language :: Python :: 3.5',
-        'Programming Language :: Python :: 3.6',
-        'Programming Language :: Python :: 3.7', 'Topic :: Utilities'
-    ], )
-
-shutil.rmtree('ppocr')
-shutil.rmtree('tools')
-shutil.rmtree('test1')
-os.remove('LICENSE')

test1/table/README.md

-# Table structure and content prediction
-
-## 1. pipeline
-The ocr of the table mainly contains three models
-1. Single line text detection-DB
-2. Single line text recognition-CRNN
-3. Table structure and cell coordinate prediction-RARE
-
-The table ocr flow chart is as follows
-
-![tableocr_pipeline](../../doc/table/tableocr_pipeline.png)
-
-1. The coordinates of single-line text is detected by DB model, and then sends it to the recognition model to get the recognition result.
-2. The table structure and cell coordinates is predicted by RARE model.
-3. The recognition result of the cell is combined by the coordinates, recognition result of the single line and the coordinates of the cell.
-4. The cell recognition result and the table structure together construct the html string of the table.
-
-## 2. How to use
-
-
-### 2.1 Train
-TBD
-
-### 2.2 Eval
-First cd to the PaddleOCR/ppstructure directory
-
-The table uses TEDS (Tree-Edit-Distance-based Similarity) as the evaluation metric of the model. Before the model evaluation, the three models in the pipeline need to be exported as inference models (we have provided them), and the gt for evaluation needs to be prepared. Examples of gt are as follows:
-```json
-{"PMC4289340_004_00.png": [["<html>", "<body>", "<table>", "<thead>", "<tr>", "<td>", "</td>", "<td>", "</td>", "<td>", "</td>", "</tr>", "</thead>", "<tbody>", "<tr>", "<td>", "</td>", "<td>", "</td>", "<td>", "</td>", "</tr>",  "</tbody>", "</table>", "</body>", "</html>"], [[1, 4, 29, 13], [137, 4, 161, 13], [215, 4, 236, 13], [1, 17, 30, 27], [137, 17, 147, 27], [215, 17, 225, 27]], [["<b>", "F", "e", "a", "t", "u", "r", "e", "</b>"], ["<b>", "G", "b", "3", " ", "+", "</b>"], ["<b>", "G", "b", "3", " ", "-", "</b>"], ["<b>", "P", "a", "t", "i", "e", "n", "t", "s", "</b>"], ["6", "2"], ["4", "5"]]]}
-```
-In gt json, the key is the image name, the value is the corresponding gt, and gt is a list composed of four items, and each item is
-1. HTML string list of table structure
-2. The coordinates of each cell (not including the empty text in the cell)
-3. The text information in each cell (not including the empty text in the cell)
-4. The text information in each cell (including the empty text in the cell)
-
-Use the following command to evaluate. After the evaluation is completed, the teds indicator will be output.
-```python
-python3 table/eval_table.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 --gt_path=path/to/gt.json
-```
-
-
-### 2.3 Inference
-First cd to the PaddleOCR/ppstructure directory
-
-```python
-python3 table/predict_table.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, the excel sheet of each picture will be saved in the directory specified by the output field
\ No newline at end of file

tools/infer/predict_cls.py

@@ -112,7 +112,6 @@ class TextClassifier(object):
                 if '180' in label and score > self.cls_thresh:
                     img_list[indices[beg_img_no + rno]] = cv2.rotate(
                         img_list[indices[beg_img_no + rno]], 1)
-        elapse = time.time() - starttime
         return img_list, cls_res, elapse
 
 
@@ -146,7 +145,6 @@ def main(args):
                                                cls_res[ino]))
     logger.info(
         "The predict time about text angle classify module is as follows: ")
-    text_classifier.cls_times.info(average=False)
 
 
 if __name__ == "__main__":

tools/infer/utility.py

@@ -24,8 +24,6 @@ from paddle import inference
 import time
 from ppocr.utils.logging import get_logger
 
-logger = get_logger()
-
 
 def str2bool(v):
     return v.lower() in ("true", "t", "1")
@@ -50,8 +48,8 @@ def init_args():
 
     # DB parmas
     parser.add_argument("--det_db_thresh", type=float, default=0.3)
-    parser.add_argument("--det_db_box_thresh", type=float, default=0.5)
-    parser.add_argument("--det_db_unclip_ratio", type=float, default=1.6)
+    parser.add_argument("--det_db_box_thresh", type=float, default=0.6)
+    parser.add_argument("--det_db_unclip_ratio", type=float, default=1.5)
     parser.add_argument("--max_batch_size", type=int, default=10)
     parser.add_argument("--use_dilation", type=bool, default=False)
     parser.add_argument("--det_db_score_mode", type=str, default="fast")
@@ -171,45 +169,45 @@ def create_predictor(args, mode, logger):
         if mode == "det":
             min_input_shape = {
                 "x": [1, 3, 50, 50],
-                "conv2d_92.tmp_0": [1, 96, 20, 20],
-                "conv2d_91.tmp_0": [1, 96, 10, 10],
+                "conv2d_92.tmp_0": [1, 120, 20, 20],
+                "conv2d_91.tmp_0": [1, 24, 10, 10],
                 "conv2d_59.tmp_0": [1, 96, 20, 20],
-                "nearest_interp_v2_1.tmp_0": [1, 96, 10, 10],
-                "nearest_interp_v2_2.tmp_0": [1, 96, 20, 20],
-                "conv2d_124.tmp_0": [1, 96, 20, 20],
-                "nearest_interp_v2_3.tmp_0": [1, 24, 20, 20],
-                "nearest_interp_v2_4.tmp_0": [1, 24, 20, 20],
-                "nearest_interp_v2_5.tmp_0": [1, 24, 20, 20],
+                "nearest_interp_v2_1.tmp_0": [1, 256, 10, 10],
+                "nearest_interp_v2_2.tmp_0": [1, 256, 20, 20],
+                "conv2d_124.tmp_0": [1, 256, 20, 20],
+                "nearest_interp_v2_3.tmp_0": [1, 64, 20, 20],
+                "nearest_interp_v2_4.tmp_0": [1, 64, 20, 20],
+                "nearest_interp_v2_5.tmp_0": [1, 64, 20, 20],
                 "elementwise_add_7": [1, 56, 2, 2],
-                "nearest_interp_v2_0.tmp_0": [1, 96, 2, 2]
+                "nearest_interp_v2_0.tmp_0": [1, 256, 2, 2]
             }
             max_input_shape = {
                 "x": [1, 3, 2000, 2000],
-                "conv2d_92.tmp_0": [1, 96, 400, 400],
-                "conv2d_91.tmp_0": [1, 96, 200, 200],
+                "conv2d_92.tmp_0": [1, 120, 400, 400],
+                "conv2d_91.tmp_0": [1, 24, 200, 200],
                 "conv2d_59.tmp_0": [1, 96, 400, 400],
-                "nearest_interp_v2_1.tmp_0": [1, 96, 200, 200],
+                "nearest_interp_v2_1.tmp_0": [1, 256, 200, 200],
                 "conv2d_124.tmp_0": [1, 256, 400, 400],
-                "nearest_interp_v2_2.tmp_0": [1, 96, 400, 400],
-                "nearest_interp_v2_3.tmp_0": [1, 24, 400, 400],
-                "nearest_interp_v2_4.tmp_0": [1, 24, 400, 400],
-                "nearest_interp_v2_5.tmp_0": [1, 24, 400, 400],
+                "nearest_interp_v2_2.tmp_0": [1, 256, 400, 400],
+                "nearest_interp_v2_3.tmp_0": [1, 64, 400, 400],
+                "nearest_interp_v2_4.tmp_0": [1, 64, 400, 400],
+                "nearest_interp_v2_5.tmp_0": [1, 64, 400, 400],
                 "elementwise_add_7": [1, 56, 400, 400],
-                "nearest_interp_v2_0.tmp_0": [1, 96, 400, 400]
+                "nearest_interp_v2_0.tmp_0": [1, 256, 400, 400]
             }
             opt_input_shape = {
                 "x": [1, 3, 640, 640],
-                "conv2d_92.tmp_0": [1, 96, 160, 160],
-                "conv2d_91.tmp_0": [1, 96, 80, 80],
+                "conv2d_92.tmp_0": [1, 120, 160, 160],
+                "conv2d_91.tmp_0": [1, 24, 80, 80],
                 "conv2d_59.tmp_0": [1, 96, 160, 160],
-                "nearest_interp_v2_1.tmp_0": [1, 96, 80, 80],
-                "nearest_interp_v2_2.tmp_0": [1, 96, 160, 160],
+                "nearest_interp_v2_1.tmp_0": [1, 256, 80, 80],
+                "nearest_interp_v2_2.tmp_0": [1, 256, 160, 160],
                 "conv2d_124.tmp_0": [1, 256, 160, 160],
-                "nearest_interp_v2_3.tmp_0": [1, 24, 160, 160],
-                "nearest_interp_v2_4.tmp_0": [1, 24, 160, 160],
-                "nearest_interp_v2_5.tmp_0": [1, 24, 160, 160],
+                "nearest_interp_v2_3.tmp_0": [1, 64, 160, 160],
+                "nearest_interp_v2_4.tmp_0": [1, 64, 160, 160],
+                "nearest_interp_v2_5.tmp_0": [1, 64, 160, 160],
                 "elementwise_add_7": [1, 56, 40, 40],
-                "nearest_interp_v2_0.tmp_0": [1, 96, 40, 40]
+                "nearest_interp_v2_0.tmp_0": [1, 256, 40, 40]
             }
         elif mode == "rec":
             min_input_shape = {"x": [args.rec_batch_num, 3, 32, 10]}