Merge branch 'PaddlePaddle:dygraph' into dygraph

MANIFEST.in

@@ -2,7 +2,7 @@ include LICENSE
 include README.md
 
 recursive-include ppocr/utils *.txt utility.py logging.py network.py
-recursive-include ppocr/data/ *.py
+recursive-include ppocr/data *.py
 recursive-include ppocr/postprocess *.py
 recursive-include tools/infer *.py
-recursive-include ppocr/utils/e2e_utils/ *.py
\ No newline at end of file
+recursive-include ppocr/utils/e2e_utils *.py
\ No newline at end of file

deploy/cpp_infer/docs/windows_vs2019_build.md

@@ -93,3 +93,5 @@ cd D:\projects\PaddleOCR\deploy\cpp_infer\out\build\x64-Release
 
 ### 注意
 * 在Windows下的终端中执行文件exe时，可能会发生乱码的现象，此时需要在终端中输入`CHCP 65001`，将终端的编码方式由GBK编码(默认)改为UTF-8编码，更加具体的解释可以参考这篇博客：[https://blog.csdn.net/qq_35038153/article/details/78430359](https://blog.csdn.net/qq_35038153/article/details/78430359)。
+
+* 编译时，如果报错`错误：C1083 无法打开包括文件:"dirent.h":No such file or directory`，可以参考该[文档](https://blog.csdn.net/Dora_blank/article/details/117740837#41_C1083_direnthNo_such_file_or_directory_54)，新建`dirent.h`文件，并添加到`VC++`的包含目录中。

deploy/cpp_infer/readme.md

@@ -18,6 +18,7 @@ PaddleOCR模型部署。
 * 首先需要从opencv官网上下载在Linux环境下源码编译的包，以opencv3.4.7为例，下载命令如下。
 
 ```
+cd deploy/cpp_infer
 wget https://github.com/opencv/opencv/archive/3.4.7.tar.gz
 tar -xf 3.4.7.tar.gz
 ```

deploy/cpp_infer/readme_en.md

@@ -18,6 +18,7 @@ PaddleOCR model deployment.
 * First of all, you need to download the source code compiled package in the Linux environment from the opencv official website. Taking opencv3.4.7 as an example, the download command is as follows.
 
 ```
+cd deploy/cpp_infer
 wget https://github.com/opencv/opencv/archive/3.4.7.tar.gz
 tar -xf 3.4.7.tar.gz
 ```

deploy/hubserving/readme.md

@@ -29,6 +29,7 @@ deploy/hubserving/ocr_system/
 ### 1. 准备环境
 ```shell
 # 安装paddlehub  
+# paddlehub 需要 python>3.6.2
 pip3 install paddlehub==2.1.0 --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple
 ```
 

deploy/hubserving/readme_en.md

@@ -30,6 +30,7 @@ The following steps take the 2-stage series service as an example. If only the d
 ### 1. Prepare the environment
 ```shell
 # Install paddlehub  
+# python>3.6.2 is required bt paddlehub
 pip3 install paddlehub==2.1.0 --upgrade -i https://pypi.tuna.tsinghua.edu.cn/simple
 ```
 

doc/doc_ch/detection.md

@@ -18,9 +18,9 @@ PaddleOCR 也提供了数据格式转换脚本，可以将官网 label 转换支
 
 ```
 # 将官网下载的标签文件转换为 train_icdar2015_label.txt
-python gen_label.py --mode="det" --root_path="icdar_c4_train_imgs/"  \
-                    --input_path="ch4_training_localization_transcription_gt" \
-                    --output_label="train_icdar2015_label.txt"
+python gen_label.py --mode="det" --root_path="/path/to/icdar_c4_train_imgs/"  \
+                    --input_path="/path/to/ch4_training_localization_transcription_gt" \
+                    --output_label="/path/to/train_icdar2015_label.txt"
 ```
 
 解压数据集和下载标注文件后，PaddleOCR/train_data/ 有两个文件夹和两个文件，分别是：

doc/doc_ch/inference.md

@@ -221,7 +221,7 @@ python3 tools/export_model.py -c configs/det/det_r50_vd_sast_totaltext.yml -o Gl
 
 ```
 
-**SAST文本检测模型推理，需要设置参数`--det_algorithm="SAST"`，同时，还需要增加参数`--det_sast_polygon=True`，**可以执行如下命令：
+SAST文本检测模型推理，需要设置参数`--det_algorithm="SAST"`，同时，还需要增加参数`--det_sast_polygon=True`，可以执行如下命令：
 ```
 python3 tools/infer/predict_det.py --det_algorithm="SAST" --image_dir="./doc/imgs_en/img623.jpg" --det_model_dir="./inference/det_sast_tt/" --det_sast_polygon=True
 ```

doc/doc_ch/recognition.md

@@ -330,6 +330,8 @@ PaddleOCR目前已支持80种（除中文外）语种识别，`configs/rec/multi
 
     ```
 
+意大利文由拉丁字母组成，因此执行完命令后会得到名为 rec_latin_lite_train.yml 的配置文件。
+
 2. 手动修改配置文件
 
    您也可以手动修改模版中的以下几个字段:

doc/doc_en/inference_en.md

@@ -230,7 +230,7 @@ First, convert the model saved in the SAST text detection training process into
 python3 tools/export_model.py -c configs/det/det_r50_vd_sast_totaltext.yml -o Global.pretrained_model=./det_r50_vd_sast_totaltext_v2.0_train/best_accuracy  Global.save_inference_dir=./inference/det_sast_tt
 ```
 
-**For SAST curved text detection model inference, you need to set the parameter `--det_algorithm="SAST"` and `--det_sast_polygon=True`**, run the following command:
+For SAST curved text detection model inference, you need to set the parameter `--det_algorithm="SAST"` and `--det_sast_polygon=True`, run the following command:
 
 ```
 python3 tools/infer/predict_det.py --det_algorithm="SAST" --image_dir="./doc/imgs_en/img623.jpg" --det_model_dir="./inference/det_sast_tt/" --det_sast_polygon=True

doc/doc_en/recognition_en.md

@@ -329,6 +329,7 @@ There are two ways to create the required configuration file:：
     ...
 
     ```
+Italian is made up of Latin letters, so after executing the command, you will get the rec_latin_lite_train.yml.
 
 2. Manually modify the configuration file
 

ppocr/data/simple_dataset.py

@@ -14,7 +14,6 @@
 import numpy as np
 import os
 import random
-import traceback
 from paddle.io import Dataset
 
 from .imaug import transform, create_operators
@@ -46,7 +45,6 @@ class SimpleDataSet(Dataset):
         self.seed = seed
         logger.info("Initialize indexs of datasets:%s" % label_file_list)
         self.data_lines = self.get_image_info_list(label_file_list, ratio_list)
-        self.check_data()
         self.data_idx_order_list = list(range(len(self.data_lines)))
         if self.mode == "train" and self.do_shuffle:
             self.shuffle_data_random()
@@ -103,18 +101,25 @@ class SimpleDataSet(Dataset):
 
     def __getitem__(self, idx):
         file_idx = self.data_idx_order_list[idx]
-        data = self.data_lines[file_idx]
+        data_line = self.data_lines[file_idx]
         try:
+            data_line = data_line.decode('utf-8')
+            substr = data_line.strip("\n").split(self.delimiter)
+            file_name = substr[0]
+            label = substr[1]
+            img_path = os.path.join(self.data_dir, file_name)
+            data = {'img_path': img_path, 'label': label}
+            if not os.path.exists(img_path):
+                raise Exception("{} does not exist!".format(img_path))
             with open(data['img_path'], 'rb') as f:
                 img = f.read()
                 data['image'] = img
             data['ext_data'] = self.get_ext_data()
             outs = transform(data, self.ops)
-        except:
-            error_meg = traceback.format_exc()
+        except Exception as e:
             self.logger.error(
-                "When parsing file {} and label {}, error happened with msg: {}".format(
-                    data['img_path'],data['label'], error_meg))
+                "When parsing line {}, error happened with msg: {}".format(
+                    data_line, e))
             outs = None
         if outs is None:
             # during evaluation, we should fix the idx to get same results for many times of evaluation.
@@ -125,17 +130,3 @@ class SimpleDataSet(Dataset):
 
     def __len__(self):
         return len(self.data_idx_order_list)
-
-    def check_data(self):
-        new_data_lines = []
-        for data_line in self.data_lines:
-            data_line = data_line.decode('utf-8')
-            substr = data_line.strip("\n").strip("\r").split(self.delimiter)
-            file_name = substr[0]
-            label = substr[1]
-            img_path = os.path.join(self.data_dir, file_name)
-            if os.path.exists(img_path):
-                new_data_lines.append({'img_path': img_path, 'label': label})
-            else:
-                self.logger.info("{} does not exist!".format(img_path))
-        self.data_lines = new_data_lines
\ No newline at end of file

ppocr/modeling/architectures/distillation_model.py

@@ -46,7 +46,7 @@ class DistillationModel(nn.Layer):
                 pretrained = model_config.pop("pretrained")
             model = BaseModel(model_config)
             if pretrained is not None:
-                model = load_pretrained_params(model, pretrained)
+                load_pretrained_params(model, pretrained)
             if freeze_params:
                 for param in model.parameters():
                     param.trainable = False