Merge remote-tracking branch 'origin/dygraph' into dygraph

PPOCRLabel/README.md

@@ -143,7 +143,7 @@ python PPOCRLabel.py
 ### 3.1 Shortcut keys
 
 | Shortcut keys            | Description                                      |
-| ------------------------ | ------------------------------------------------ |
+|--------------------------| ------------------------------------------------ |
 | Ctrl + Shift + R         | Re-recognize all the labels of the current image |
 | W                        | Create a rect box                                |
 | Q                        | Create a four-points box                         |
@@ -151,7 +151,7 @@ python PPOCRLabel.py
 | Ctrl + R                 | Re-recognize the selected box                    |
 | Ctrl + C                 | Copy and paste the selected box                  |
 | Ctrl + Left Mouse Button | Multi select the label box                       |
-| Backspace                | Delete the selected box                          |
+| Ctrl + X                 | Delete the selected box                          |
 | Ctrl + V                 | Check image                                      |
 | Ctrl + Shift + d         | Delete image                                     |
 | D                        | Next image                                       |

PPOCRLabel/README_ch.md

@@ -131,16 +131,16 @@ python PPOCRLabel.py --lang ch
 
 ### 3.1 快捷键
 
-| 快捷键           | 说明                         |
-| ---------------- | ---------------------------- |
+| 快捷键              | 说明                         |
+|------------------| ---------------------------- |
 | Ctrl + shift + R | 对当前图片的所有标记重新识别 |
 | W                | 新建矩形框                   |
 | Q                | 新建四点框                   |
 | Ctrl + E         | 编辑所选框标签               |
 | Ctrl + R         | 重新识别所选标记             |
 | Ctrl + C         | 复制并粘贴选中的标记框       |
-| Ctrl + 鼠标左键  | 多选标记框                   |
-| Backspace        | 删除所选框                   |
+| Ctrl + 鼠标左键   | 多选标记框                   |
+| Ctrl + X         | 删除所选框                   |
 | Ctrl + V         | 确认本张图片标记             |
 | Ctrl + Shift + d | 删除本张图片                 |
 | D                | 下一张图片                   |

PPOCRLabel/libs/autoDialog.py

@@ -6,6 +6,8 @@ except ImportError:
     from PyQt4.QtGui import *
     from PyQt4.QtCore import *
 
+import time
+import datetime
 import json
 import cv2
 import numpy as np
@@ -80,8 +82,9 @@ class AutoDialog(QDialog):
         self.parent = parent
         self.ocr = ocr
         self.mImgList = mImgList
+        self.lender = lenbar
         self.pb = QProgressBar()
-        self.pb.setRange(0, lenbar)
+        self.pb.setRange(0, self.lender)
         self.pb.setValue(0)
 
         layout = QVBoxLayout()
@@ -108,10 +111,16 @@ class AutoDialog(QDialog):
         self.thread_1.progressBarValue.connect(self.handleProgressBarSingal)
         self.thread_1.listValue.connect(self.handleListWidgetSingal)
         self.thread_1.endsignal.connect(self.handleEndsignalSignal)
+        self.time_start = time.time()  # save start time
 
     def handleProgressBarSingal(self, i):
         self.pb.setValue(i)
 
+        # calculate time left of auto labeling
+        avg_time = (time.time() - self.time_start) / i  # Use average time to prevent time fluctuations
+        time_left = str(datetime.timedelta(seconds=avg_time * (self.lender - i))).split(".")[0]  # Remove microseconds
+        self.setWindowTitle("PPOCRLabel  --  " + f"Time Left: {time_left}")  # show
+
     def handleListWidgetSingal(self, i):
         self.listWidget.addItem(i)
         titem = self.listWidget.item(self.listWidget.count() - 1)

PPOCRLabel/libs/canvas.py

@@ -87,6 +87,10 @@ class Canvas(QWidget):
         #initialisation for panning
         self.pan_initial_pos = QPoint()
 
+        #lockedshapes related 
+        self.lockedShapes = []
+        self.isInTheSameImage = False
+
     def setDrawingColor(self, qColor):
         self.drawingLineColor = qColor
         self.drawingRectColor = qColor

PPOCRLabel/libs/shape.py

@@ -30,6 +30,7 @@ DEFAULT_SELECT_LINE_COLOR = QColor(255, 255, 255)
 DEFAULT_SELECT_FILL_COLOR = QColor(0, 128, 255, 155)
 DEFAULT_VERTEX_FILL_COLOR = QColor(0, 255, 0, 255)
 DEFAULT_HVERTEX_FILL_COLOR = QColor(255, 0, 0)
+DEFAULT_LOCK_COLOR = QColor(255, 0, 255)
 MIN_Y_LABEL = 10
 
 
@@ -57,7 +58,7 @@ class Shape(object):
         self.selected = False
         self.difficult = difficult
         self.paintLabel = paintLabel
-
+        self.locked = False
         self._highlightIndex = None
         self._highlightMode = self.NEAR_VERTEX
         self._highlightSettings = {

PPOCRLabel/resources/strings/strings-en.properties

@@ -104,4 +104,6 @@ singleRe=Re-recognition RectBox
 labelDialogOption=Pop-up Label Input Dialog
 undo=Undo
 undoLastPoint=Undo Last Point
-autoSaveMode=Auto Export Label Mode
+autoSaveMode=Auto Export Label Mode
\ No newline at end of file
+lockBox=Lock selected box/Unlock all box
+lockBoxDetail=Lock selected box/Unlock all box
\ No newline at end of file

PPOCRLabel/resources/strings/strings-zh-CN.properties

@@ -104,4 +104,6 @@ singleRe=重识别此区块
 labelDialogOption=弹出标记输入框
 undo=撤销
 undoLastPoint=撤销上个点
-autoSaveMode=自动导出标记结果
+autoSaveMode=自动导出标记结果
\ No newline at end of file
+lockBox=锁定框/解除锁定框
+lockBoxDetail=若当前没有框处于锁定状态则锁定选中的框，若存在锁定框则解除所有锁定框的锁定状态

README.md

@@ -33,17 +33,17 @@ PaddleOCR aims to create multilingual, awesome, leading, and practical OCR tools
 - [more](./doc/doc_en/update_en.md)
 
 ## Features
-- PP-OCR series of high-quality pre-trained models, comparable to commercial effects
+- PP-OCR - A series of high-quality pre-trained models, comparable to commercial products
     - Ultra lightweight PP-OCRv2 series models: detection (3.1M) + direction classifier (1.4M) + recognition 8.5M) = 13.0M
     - Ultra lightweight PP-OCR mobile series models: detection (3.0M) + direction classifier (1.4M) + recognition (5.0M) = 9.4M
     - General PP-OCR server series models: detection (47.1M) + direction classifier (1.4M) + recognition (94.9M) = 143.4M
     - Support Chinese, English, and digit recognition, vertical text recognition, and long text recognition
-    - Support multi-language recognition: about 80 languages like Korean, Japanese, German, French, etc
+    - Support multi-lingual recognition: about 80 languages like Korean, Japanese, German, French, etc
 - PP-Structure: a document structurize system
-    - support layout analysis and table recognition (support export to Excel)
-    - support key information extraction
-    - support DocVQA
-- Rich toolkits related to the OCR areas
+    - Support layout analysis and table recognition (support export to Excel)
+    - Support key information extraction
+    - Support DocVQA
+- Rich OCR toolkit
     - Semi-automatic data annotation tool, i.e., PPOCRLabel: support fast and efficient data annotation
     - Data synthesis tool, i.e., Style-Text: easy to synthesize a large number of images which are similar to the target scene image
 - Support user-defined training, provides rich predictive inference deployment solutions
@@ -62,7 +62,7 @@ The above pictures are the visualizations of the general ppocr_server model. For
 
 <a name="Community"></a>
 ## Community
-- Scan the QR code below with your Wechat, you can access to official technical exchange group. Look forward to your participation.
+- Scan the QR code below with your Wechat, you can join the official technical discussion group. Looking forward to your participation.
 
 <div align="center">
 <img src="https://raw.githubusercontent.com/PaddlePaddle/PaddleOCR/dygraph/doc/joinus.PNG"  width = "200" height = "200" />
@@ -120,8 +120,8 @@ For a new language request, please refer to [Guideline for new language_requests
 - [PP-Structure: Information Extraction](./ppstructure/README.md)
     - [Layout Parser](./ppstructure/layout/README.md)
     - [Table Recognition](./ppstructure/table/README.md)
-    - [DocVQA](https://github.com/PaddlePaddle/PaddleOCR/tree/release/2.4/ppstructure/vqa)
-    - [Key Information Extraction](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.4/ppstructure/docs/kie.md)
+    - [DocVQA](./ppstructure/vqa/README.md)
+    - [Key Information Extraction](./ppstructure/docs/kie.md)
 - Academic Circles
     - [Two-stage Algorithm](./doc/doc_en/algorithm_overview_en.md)
     - [PGNet Algorithm](./doc/doc_en/pgnet_en.md)

README_ch.md

@@ -99,8 +99,8 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力
 - [PP-Structure信息提取](./ppstructure/README_ch.md)
     - [版面分析](./ppstructure/layout/README_ch.md)
     - [表格识别](./ppstructure/table/README_ch.md)
-    - [DocVQA](https://github.com/PaddlePaddle/PaddleOCR/tree/release/2.4/ppstructure/vqa)
-    - [关键信息提取](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.4/ppstructure/docs/kie.md)
+    - [DocVQA](./ppstructure/vqa/README_ch.md)
+    - [关键信息提取](./ppstructure/docs/kie.md)
 - OCR学术圈
     - [两阶段模型介绍与下载](./doc/doc_ch/algorithm_overview.md)
     - [端到端PGNet算法](./doc/doc_ch/pgnet.md)

configs/vqa/re/layoutxlm.yml

+Global:
+  use_gpu: True
+  epoch_num: &epoch_num 200
+  log_smooth_window: 10
+  print_batch_step: 10
+  save_model_dir: ./output/re_layoutxlm/
+  save_epoch_step: 2000
+  # evaluation is run every 10 iterations after the 0th iteration
+  eval_batch_step: [ 0, 19 ]
+  cal_metric_during_train: False
+  save_inference_dir:
+  use_visualdl: False
+  seed: 2022
+  infer_img: doc/vqa/input/zh_val_21.jpg
+  save_res_path: ./output/re/
+
+Architecture:
+  model_type: vqa
+  algorithm: &algorithm "LayoutXLM"
+  Transform:
+  Backbone:
+    name: LayoutXLMForRe
+    pretrained: True
+    checkpoints: 
+
+Loss:
+  name: LossFromOutput
+  key: loss
+  reduction: mean
+
+Optimizer:
+  name: AdamW
+  beta1: 0.9
+  beta2: 0.999
+  clip_norm: 10
+  lr:
+    learning_rate: 0.00005
+  regularizer:
+    name: L2
+    factor: 0.00000
+    
+PostProcess:
+  name: VQAReTokenLayoutLMPostProcess
+
+Metric:
+  name: VQAReTokenMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: train_data/XFUND/zh_train/image
+    label_file_list: 
+      - train_data/XFUND/zh_train/xfun_normalize_train.json
+    ratio_list: [ 1.0 ]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: RGB
+          channel_first: False
+      - VQATokenLabelEncode: # Class handling label
+          contains_re: True
+          algorithm: *algorithm
+          class_path: &class_path ppstructure/vqa/labels/labels_ser.txt
+      - VQATokenPad:
+          max_seq_len: &max_seq_len 512
+          return_attention_mask: True
+      - VQAReTokenRelation:
+      - VQAReTokenChunk:
+          max_seq_len: *max_seq_len
+      - Resize:
+          size: [224,224]
+      - NormalizeImage:
+          scale: 1
+          mean: [ 123.675, 116.28, 103.53 ]
+          std: [ 58.395, 57.12, 57.375 ]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: [ 'input_ids', 'bbox', 'image', 'attention_mask', 'token_type_ids','entities', 'relations'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 8
+    num_workers: 4
+    collate_fn: ListCollator
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: train_data/XFUND/zh_val/image
+    label_file_list:
+      - train_data/XFUND/zh_val/xfun_normalize_val.json
+    transforms:
+      - DecodeImage: # load image
+          img_mode: RGB
+          channel_first: False
+      - VQATokenLabelEncode: # Class handling label
+          contains_re: True
+          algorithm: *algorithm
+          class_path: *class_path
+      - VQATokenPad:
+          max_seq_len: *max_seq_len
+          return_attention_mask: True
+      - VQAReTokenRelation:
+      - VQAReTokenChunk:
+          max_seq_len: *max_seq_len
+      - Resize:
+          size: [224,224]
+      - NormalizeImage:
+          scale: 1
+          mean: [ 123.675, 116.28, 103.53 ]
+          std: [ 58.395, 57.12, 57.375 ]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: [ 'input_ids', 'bbox', 'image', 'attention_mask', 'token_type_ids','entities', 'relations'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 8
+    num_workers: 4
+    collate_fn: ListCollator

configs/vqa/ser/layoutlm.yml

+Global:
+  use_gpu: True
+  epoch_num: &epoch_num 200
+  log_smooth_window: 10
+  print_batch_step: 10
+  save_model_dir: ./output/ser_layoutlm/
+  save_epoch_step: 2000
+  # evaluation is run every 10 iterations after the 0th iteration
+  eval_batch_step: [ 0, 19 ]
+  cal_metric_during_train: False
+  save_inference_dir:
+  use_visualdl: False
+  seed: 2022
+  infer_img: doc/vqa/input/zh_val_0.jpg
+  save_res_path: ./output/ser/
+
+Architecture:
+  model_type: vqa
+  algorithm: &algorithm "LayoutLM"
+  Transform:
+  Backbone:
+    name: LayoutLMForSer
+    pretrained: True
+    checkpoints:
+    num_classes: &num_classes 7
+
+Loss:
+  name: VQASerTokenLayoutLMLoss
+  num_classes: *num_classes
+
+Optimizer:
+  name: AdamW
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Linear
+    learning_rate: 0.00005
+    epochs: *epoch_num
+    warmup_epoch: 2
+  regularizer:
+    name: L2
+    factor: 0.00000
+    
+PostProcess:
+  name: VQASerTokenLayoutLMPostProcess
+  class_path: &class_path ppstructure/vqa/labels/labels_ser.txt
+
+Metric:
+  name: VQASerTokenMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: train_data/XFUND/zh_train/image
+    label_file_list: 
+      - train_data/XFUND/zh_train/xfun_normalize_train.json
+    transforms:
+      - DecodeImage: # load image
+          img_mode: RGB
+          channel_first: False
+      - VQATokenLabelEncode: # Class handling label
+          contains_re: False
+          algorithm: *algorithm
+          class_path: *class_path
+      - VQATokenPad:
+          max_seq_len: &max_seq_len 512
+          return_attention_mask: True
+      - VQASerTokenChunk:
+          max_seq_len: *max_seq_len
+      - Resize:
+          size: [224,224]
+      - NormalizeImage:
+          scale: 1
+          mean: [ 123.675, 116.28, 103.53 ]
+          std: [ 58.395, 57.12, 57.375 ]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: [ 'input_ids','labels', 'bbox', 'image', 'attention_mask', 'token_type_ids'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 8
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: train_data/XFUND/zh_val/image
+    label_file_list:
+      - train_data/XFUND/zh_val/xfun_normalize_val.json
+    transforms:
+      - DecodeImage: # load image
+          img_mode: RGB
+          channel_first: False
+      - VQATokenLabelEncode: # Class handling label
+          contains_re: False
+          algorithm: *algorithm
+          class_path: *class_path
+      - VQATokenPad:
+          max_seq_len: *max_seq_len
+          return_attention_mask: True
+      - VQASerTokenChunk:
+          max_seq_len: *max_seq_len
+      - Resize:
+          size: [224,224]
+      - NormalizeImage:
+          scale: 1
+          mean: [ 123.675, 116.28, 103.53 ]
+          std: [ 58.395, 57.12, 57.375 ]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: [ 'input_ids', 'labels', 'bbox', 'image', 'attention_mask', 'token_type_ids'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 8
+    num_workers: 4

configs/vqa/ser/layoutxlm.yml

+Global:
+  use_gpu: True
+  epoch_num: &epoch_num 200
+  log_smooth_window: 10
+  print_batch_step: 10
+  save_model_dir: ./output/ser_layoutxlm/
+  save_epoch_step: 2000
+  # evaluation is run every 10 iterations after the 0th iteration
+  eval_batch_step: [ 0, 19 ]
+  cal_metric_during_train: False
+  save_inference_dir:
+  use_visualdl: False
+  seed: 2022
+  infer_img: doc/vqa/input/zh_val_42.jpg
+  save_res_path: ./output/ser
+
+Architecture:
+  model_type: vqa
+  algorithm: &algorithm "LayoutXLM"
+  Transform:
+  Backbone:
+    name: LayoutXLMForSer
+    pretrained: True
+    checkpoints:
+    num_classes: &num_classes 7
+
+Loss:
+  name: VQASerTokenLayoutLMLoss
+  num_classes: *num_classes
+
+Optimizer:
+  name: AdamW
+  beta1: 0.9
+  beta2: 0.999
+  lr:
+    name: Linear
+    learning_rate: 0.00005
+    epochs: *epoch_num
+    warmup_epoch: 2
+  regularizer:
+    name: L2
+    factor: 0.00000
+    
+PostProcess:
+  name: VQASerTokenLayoutLMPostProcess
+  class_path: &class_path ppstructure/vqa/labels/labels_ser.txt
+
+Metric:
+  name: VQASerTokenMetric
+  main_indicator: hmean
+
+Train:
+  dataset:
+    name: SimpleDataSet
+    data_dir: train_data/XFUND/zh_train/image
+    label_file_list: 
+      - train_data/XFUND/zh_train/xfun_normalize_train.json
+    ratio_list: [ 1.0 ]
+    transforms:
+      - DecodeImage: # load image
+          img_mode: RGB
+          channel_first: False
+      - VQATokenLabelEncode: # Class handling label
+          contains_re: False
+          algorithm: *algorithm
+          class_path: *class_path
+      - VQATokenPad:
+          max_seq_len: &max_seq_len 512
+          return_attention_mask: True
+      - VQASerTokenChunk:
+          max_seq_len: *max_seq_len
+      - Resize:
+          size: [224,224]
+      - NormalizeImage:
+          scale: 1
+          mean: [ 123.675, 116.28, 103.53 ]
+          std: [ 58.395, 57.12, 57.375 ]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: [ 'input_ids','labels', 'bbox', 'image', 'attention_mask', 'token_type_ids'] # dataloader will return list in this order
+  loader:
+    shuffle: True
+    drop_last: False
+    batch_size_per_card: 8
+    num_workers: 4
+
+Eval:
+  dataset:
+    name: SimpleDataSet
+    data_dir: train_data/XFUND/zh_val/image
+    label_file_list:
+      - train_data/XFUND/zh_val/xfun_normalize_val.json
+    transforms:
+      - DecodeImage: # load image
+          img_mode: RGB
+          channel_first: False
+      - VQATokenLabelEncode: # Class handling label
+          contains_re: False
+          algorithm: *algorithm
+          class_path: *class_path
+      - VQATokenPad:
+          max_seq_len: *max_seq_len
+          return_attention_mask: True
+      - VQASerTokenChunk:
+          max_seq_len: *max_seq_len
+      - Resize:
+          size: [224,224]
+      - NormalizeImage:
+          scale: 1
+          mean: [ 123.675, 116.28, 103.53 ]
+          std: [ 58.395, 57.12, 57.375 ]
+          order: 'hwc'
+      - ToCHWImage:
+      - KeepKeys:
+          keep_keys: [ 'input_ids', 'labels', 'bbox', 'image', 'attention_mask', 'token_type_ids'] # dataloader will return list in this order
+  loader:
+    shuffle: False
+    drop_last: False
+    batch_size_per_card: 8
+    num_workers: 4

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

@@ -160,6 +160,7 @@ public class Predictor {
             for (String content : contents) {
                 wordLabels.add(content);
             }
+            wordLabels.add(" ");
             Log.i(TAG, "Word label size: " + wordLabels.size());
         } catch (Exception e) {
             Log.e(TAG, e.getMessage());

deploy/cpp_infer/readme_en.md

 # Server-side C++ Inference
 
-This chapter introduces the C++ deployment method of the PaddleOCR model, and the corresponding python predictive deployment method refers to [document](../../doc/doc_ch/inference.md).
-C++ is better than python in terms of performance calculation. Therefore, in most CPU and GPU deployment scenarios, C++ deployment is mostly used.
-This section will introduce how to configure the C++ environment and complete it in the Linux\Windows (CPU\GPU) environment
-PaddleOCR model deployment.
+This chapter introduces the C++ deployment steps of the PaddleOCR model. The corresponding Python predictive deployment method refers to [document](../../doc/doc_ch/inference.md).
+C++ is better than python in terms of performance. Therefore, in CPU and GPU deployment scenarios, C++ deployment is mostly used.
+This section will introduce how to configure the C++ environment and deploy PaddleOCR in Linux (CPU\GPU) environment. For Windows deployment please refer to [Windows](./docs/windows_vs2019_build.md) compilation guidelines.
 
 
 ## 1. Prepare the Environment
@@ -15,7 +14,7 @@ PaddleOCR model deployment.
 
 ### 1.1 Compile OpenCV
 
-* 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.
+* First of all, you need to download the source code compiled package in the Linux environment from the OpenCV official website. Taking OpenCV 3.4.7 as an example, the download command is as follows.
 
 ```bash
 cd deploy/cpp_infer
@@ -23,9 +22,9 @@ wget https://paddleocr.bj.bcebos.com/libs/opencv/opencv-3.4.7.tar.gz
 tar -xf opencv-3.4.7.tar.gz
 ```
 
-Finally, you can see the folder of `opencv-3.4.7/` in the current directory.
+Finally, you will see the folder of `opencv-3.4.7/` in the current directory.
 
-* Compile opencv, the opencv source path (`root_path`) and installation path (`install_path`) should be set by yourself. Enter the opencv source code path and compile it in the following way.
+* Compile OpenCV, the OpenCV source path (`root_path`) and installation path (`install_path`) should be set by yourself. Enter the OpenCV source code path and compile it in the following way.
 
 
 ```shell
@@ -58,11 +57,11 @@ make -j
 make install
 ```
 
-Among them, `root_path` is the downloaded opencv source code path, and `install_path` is the installation path of opencv. After `make install` is completed, the opencv header file and library file will be generated in this folder for later OCR source code compilation.
+In the above commands, `root_path` is the downloaded OpenCV source code path, and `install_path` is the installation path of OpenCV. After `make install` is completed, the OpenCV header file and library file will be generated in this folder for later OCR source code compilation.
 
 
 
-The final file structure under the opencv installation path is as follows.
+The final file structure under the OpenCV installation path is as follows.
 
 ```
 opencv3/
@@ -79,20 +78,20 @@ opencv3/
 
 #### 1.2.1 Direct download and installation
 
-[Paddle inference library official website](https://paddle-inference.readthedocs.io/en/latest/user_guides/download_lib.html). You can view and select the appropriate version of the inference library on the official website.
+[Paddle inference library official website](https://paddle-inference.readthedocs.io/en/latest/user_guides/download_lib.html). You can review and select the appropriate version of the inference library on the official website.
 
 
-* After downloading, use the following method to uncompress.
+* After downloading, use the following command to extract files.
 
 ```
 tar -xf paddle_inference.tgz
 ```
 
-Finally you can see the following files in the folder of `paddle_inference/`.
+Finally you will see the the folder of `paddle_inference/` in the current path.
 
-#### 1.2.2 Compile from the source code
-* If you want to get the latest Paddle inference library features, you can download the latest code from Paddle github repository and compile the inference library from the source code. It is recommended to download the inference library with paddle version greater than or equal to 2.0.1.
-* You can refer to [Paddle inference library] (https://www.paddlepaddle.org.cn/documentation/docs/en/advanced_guide/inference_deployment/inference/build_and_install_lib_en.html) to get the Paddle source code from github, and then compile To generate the latest inference library. The method of using git to access the code is as follows.
+#### 1.2.2 Compile the inference source code
+* If you want to get the latest Paddle inference library features, you can download the latest code from Paddle GitHub repository and compile the inference library from the source code. It is recommended to download the inference library with paddle version greater than or equal to 2.0.1.
+* You can refer to [Paddle inference library] (https://www.paddlepaddle.org.cn/documentation/docs/en/advanced_guide/inference_deployment/inference/build_and_install_lib_en.html) to get the Paddle source code from GitHub, and then compile To generate the latest inference library. The method of using git to access the code is as follows.
 
 
 ```shell
@@ -100,7 +99,7 @@ git clone https://github.com/PaddlePaddle/Paddle.git
 git checkout develop
 ```
 
-* After entering the Paddle directory, the commands to compile the paddle inference library are as follows.
+* Enter the Paddle directory and run the following commands to compile the paddle inference library.
 
 ```shell
 rm -rf build
@@ -133,14 +132,14 @@ build/paddle_inference_install_dir/
 |-- version.txt
 ```
 
-Among them, `paddle` is the Paddle library required for C++ prediction later, and `version.txt` contains the version information of the current inference library.
+`paddle` is the Paddle library required for C++ prediction later, and `version.txt` contains the version information of the current inference library.
 
 
 ## 2. Compile and Run the Demo
 
 ### 2.1 Export the inference model
 
-* You can refer to [Model inference](../../doc/doc_ch/inference.md)，export the inference model. After the model is exported, assuming it is placed in the `inference` directory, the directory structure is as follows.
+* You can refer to [Model inference](../../doc/doc_ch/inference.md) and export the inference model. After the model is exported, assuming it is placed in the `inference` directory, the directory structure is as follows.
 
 ```
 inference/
@@ -171,20 +170,28 @@ CUDA_LIB_DIR=your_cuda_lib_dir
 CUDNN_LIB_DIR=your_cudnn_lib_dir
 ```
 
-`OPENCV_DIR` is the opencv installation path; `LIB_DIR` is the download (`paddle_inference` folder)
+`OPENCV_DIR` is the OpenCV installation path; `LIB_DIR` is the download (`paddle_inference` folder)
 or the generated Paddle inference library path (`build/paddle_inference_install_dir` folder);
-`CUDA_LIB_DIR` is the cuda library file path, in docker; it is `/usr/local/cuda/lib64`; `CUDNN_LIB_DIR` is the cudnn library file path, in docker it is `/usr/lib/x86_64-linux-gnu/`.
+`CUDA_LIB_DIR` is the CUDA library file path, in docker; it is `/usr/local/cuda/lib64`; `CUDNN_LIB_DIR` is the cuDNN library file path, in docker it is `/usr/lib/x86_64-linux-gnu/`.
 
 
 * After the compilation is completed, an executable file named `ppocr` will be generated in the `build` folder.
 
 
 ### Run the demo
-Execute the built executable file:  
+Execute the built executable file:
 ```shell
 ./build/ppocr <mode> [--param1] [--param2] [...]
 ```
-Here, `mode` is a required parameter，and the value range is ['det', 'rec', 'system'], representing using detection only, using recognition only and using the end-to-end system respectively. Specifically,
+`mode` is a required parameter，and the valid values are
+
+mode value | Model used
+-----|------
+det  | Detection only
+rec  | Recognition only
+system | End-to-end system
+
+Specifically,
 
 ##### 1. run det demo:
 ```shell
@@ -214,9 +221,9 @@ Here, `mode` is a required parameter，and the value range is ['det', 'rec', 'sy
     --image_dir=../../doc/imgs/12.jpg
 ```
 
-More parameters are as follows,  
+More parameters are as follows,
 
-- common parameters
+- Common parameters
 
 |parameter|data type|default|meaning|
 | --- | --- | --- | --- |
@@ -226,7 +233,7 @@ More parameters are as follows,
 |cpu_math_library_num_threads|int|10|Number of threads when using CPU inference. When machine cores is enough, the large the value, the faster the inference speed|
 |use_mkldnn|bool|true|Whether to use mkdlnn library|
 
-- detection related parameters
+- Detection related parameters
 
 |parameter|data type|default|meaning|
 | --- | --- | --- | --- |
@@ -238,7 +245,7 @@ More parameters are as follows,
 |use_polygon_score|bool|false|Whether to use polygon box to calculate bbox score, false means to use rectangle box to calculate. Use rectangular box to calculate faster, and polygonal box more accurate for curved text area.|
 |visualize|bool|true|Whether to visualize the results，when it is set as true, The prediction result will be save in the image file `./ocr_vis.png`.|
 
-- classifier related parameters
+- Classifier related parameters
 
 |parameter|data type|default|meaning|
 | --- | --- | --- | --- |
@@ -246,7 +253,7 @@ More parameters are as follows,
 |cls_model_dir|string|-|Address of direction classifier inference model|
 |cls_thresh|float|0.9|Score threshold of the  direction classifier|
 
-- recogniton related parameters
+- Recognition related parameters
 
 |parameter|data type|default|meaning|
 | --- | --- | --- | --- |
@@ -265,4 +272,4 @@ The detection results will be shown on the screen, which is as follows.
 
 ### 2.3 Notes
 
-* Paddle2.0.0 inference model library is recommended for this toturial.
+* Paddle 2.0.0 inference model library is recommended for this tutorial.

deploy/docker/hubserving/README.md

 English | [简体中文](README_cn.md)
 
 ## Introduction
-Many users hope package the PaddleOCR service into a docker image, so that it can be quickly released and used in the docker or k8s environment.
+Many users hope package the PaddleOCR service into a docker image, so that it can be quickly released and used in the docker or K8s environment.
 
-This page provides some standardized code to achieve this goal. You can quickly publish the PaddleOCR project into a callable Restful API service through the following steps. (At present, the deployment based on the HubServing mode is implemented first, and author plans to increase the deployment of the PaddleServing mode in the futrue)
+This page provides some standardized code to achieve this goal. You can quickly publish the PaddleOCR project into a callable Restful API service through the following steps. (At present, the deployment based on the HubServing mode is implemented first, and author plans to increase the deployment of the PaddleServing mode in the future)
 
 ## 1. Prerequisites
 
@@ -14,7 +14,7 @@ c. NVIDIA Container Toolkit（GPU，Docker 19.03+ can skip this）
 d. cuDNN 7.6+（GPU）
 
 ## 2. Build Image
-a. Goto Dockerfile directory（ps：Need to distinguish between cpu and gpu version, the following takes cpu as an example, gpu version needs to replace the keyword）
+a. Go to Dockerfile directory（PS: Need to distinguish between CPU and GPU version, the following takes CPU as an example, GPU version needs to replace the keyword）
 ```
 cd deploy/docker/hubserving/cpu
 ```
@@ -42,13 +42,13 @@ docker logs -f paddle_ocr
 ```
 
 ## 4. Test
-a. Calculate the Base64 encoding of the picture to be recognized (if you just test, you can use a free online tool, like：https://freeonlinetools24.com/base64-image/）
+a. Calculate the Base64 encoding of the picture to be recognized (For test purpose, you can use a free online tool such as https://freeonlinetools24.com/base64-image/ )
 b. Post a service request（sample request in sample_request.txt）
 
 ```
 curl -H "Content-Type:application/json" -X POST --data "{\"images\": [\"Input image Base64 encode(need to delete the code 'data:image/jpg;base64,'）\"]}" http://localhost:8868/predict/ocr_system
 ```
-c. Get resposne（If the call is successful, the following result will be returned）
+c. Get response（If the call is successful, the following result will be returned）
 ```
 {"msg":"","results":[[{"confidence":0.8403433561325073,"text":"约定","text_region":[[345,377],[641,390],[634,540],[339,528]]},{"confidence":0.8131805658340454,"text":"最终相遇","text_region":[[356,532],[624,530],[624,596],[356,598]]}]],"status":"0"}
 ```

deploy/lite/readme_en.md

 # Tutorial of PaddleOCR Mobile deployment
 
-This tutorial will introduce how to use [Paddle Lite](https://github.com/PaddlePaddle/Paddle-Lite) to deploy paddleOCR ultra-lightweight Chinese and English detection models on mobile phones.
+This tutorial will introduce how to use [Paddle Lite](https://github.com/PaddlePaddle/Paddle-Lite) to deploy PaddleOCR ultra-lightweight Chinese and English detection models on mobile phones.
 
-paddle-lite is a lightweight inference engine for PaddlePaddle. It provides efficient inference capabilities for mobile phones and IoTs, and extensively integrates cross-platform hardware to provide lightweight deployment solutions for end-side deployment issues.
+paddle-lite is a lightweight inference engine for PaddlePaddle. It provides efficient inference capabilities for mobile phones and IoT, and extensively integrates cross-platform hardware to provide lightweight deployment solutions for end-side deployment issues.
 
 ## 1. Preparation
 

deploy/pdserving/README_CN.md

@@ -22,6 +22,7 @@ PaddleOCR提供2种服务部署方式：
 - [环境准备](#环境准备)
 - [模型转换](#模型转换)
 - [Paddle Serving pipeline部署](#部署)
+- [Windows用户](#Windows用户)
 - [FAQ](#FAQ)
 
 <a name="环境准备"></a>
@@ -187,9 +188,10 @@ python3 -m paddle_serving_client.convert --dirname ./ch_PP-OCRv2_rec_infer/ \
     2021-05-13 03:42:36,979         chl2(In: ['rec'], Out: ['@DAGExecutor']) size[0/0]
     ```
 
-## WINDOWS用户
+<a name="Windows用户"></a>
+## Windows用户
 
-Windows用户不能使用上述的启动方式，需要使用Web Service，详情参见[Windows平台使用Paddle Serving指导](https://github.com/PaddlePaddle/Serving/blob/develop/doc/WINDOWS_TUTORIAL_CN.md)
+Windows用户不能使用上述的启动方式，需要使用Web Service，详情参见[Windows平台使用Paddle Serving指导](https://github.com/PaddlePaddle/Serving/blob/develop/doc/Windows_Tutorial_CN.md)
 
 **WINDOWS只能使用0.5.0版本的CPU模式**
 

deploy/slim/prune/README_en.md

@@ -28,14 +28,14 @@ python3 setup.py install
 ```
 
 
-### 2. Download Pretrain Model
+### 2. Download Pre-trained Model
 Model prune needs to load pre-trained models.
 PaddleOCR also provides a series of [models](../../../doc/doc_en/models_list_en.md). Developers can choose their own models or use their own models according to their needs.
 
 
 ### 3. Pruning sensitivity analysis
 
-  After the pre-training model is loaded, sensitivity analysis is performed on each network layer of the model to understand the redundancy of each network layer, and save a sensitivity file which named: sen.pickle.  After that, user could load the sensitivity file via the [methods provided by PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim/blob/develop/paddleslim/prune/sensitive.py#L221) and determining the pruning ratio of each network layer automatically. For specific details of sensitivity analysis, see：[Sensitivity analysis](https://github.com/PaddlePaddle/PaddleSlim/blob/develop/docs/zh_cn/tutorials/image_classification_sensitivity_analysis_tutorial.md)
+  After the pre-trained model is loaded, sensitivity analysis is performed on each network layer of the model to understand the redundancy of each network layer, and save a sensitivity file which named: sen.pickle.  After that, user could load the sensitivity file via the [methods provided by PaddleSlim](https://github.com/PaddlePaddle/PaddleSlim/blob/develop/paddleslim/prune/sensitive.py#L221) and determining the pruning ratio of each network layer automatically. For specific details of sensitivity analysis, see：[Sensitivity analysis](https://github.com/PaddlePaddle/PaddleSlim/blob/develop/docs/zh_cn/tutorials/image_classification_sensitivity_analysis_tutorial.md)
   The data format of sensitivity file：
       sen.pickle(Dict){
               'layer_weight_name_0': sens_of_each_ratio(Dict){'pruning_ratio_0': acc_loss, 'pruning_ratio_1': acc_loss}
@@ -47,7 +47,7 @@ PaddleOCR also provides a series of [models](../../../doc/doc_en/models_list_en.
               'conv10_expand_weights': {0.1: 0.006509952684312718, 0.2: 0.01827734339798862, 0.3: 0.014528405644659832, 0.6: 0.06536008804270439, 0.8: 0.11798612250664964, 0.7: 0.12391408417493704, 0.4: 0.030615754498018757, 0.5: 0.047105205602406594}
               'conv10_linear_weights': {0.1: 0.05113190831455035, 0.2: 0.07705573833558801, 0.3: 0.12096721757739311, 0.6: 0.5135061352930738, 0.8: 0.7908166677143281, 0.7: 0.7272187676899062, 0.4: 0.1819252083008504, 0.5: 0.3728054727792405}
           }
-  The function would return a dict after loading the sensitivity file. The keys of the dict are name of parameters in each layer. And the value of key is the information about pruning sensitivity of correspoding layer. In example, pruning 10% filter of the layer corresponding to conv10_expand_weights would lead to 0.65% degradation of model performance. The details could be seen at: [Sensitivity analysis](https://github.com/PaddlePaddle/PaddleSlim/blob/develop/docs/zh_cn/algo/algo.md#2-%E5%8D%B7%E7%A7%AF%E6%A0%B8%E5%89%AA%E8%A3%81%E5%8E%9F%E7%90%86)
+  The function would return a dict after loading the sensitivity file. The keys of the dict are name of parameters in each layer. And the value of key is the information about pruning sensitivity of corresponding layer. In example, pruning 10% filter of the layer corresponding to conv10_expand_weights would lead to 0.65% degradation of model performance. The details could be seen at: [Sensitivity analysis](https://github.com/PaddlePaddle/PaddleSlim/blob/develop/docs/zh_cn/algo/algo.md#2-%E5%8D%B7%E7%A7%AF%E6%A0%B8%E5%89%AA%E8%A3%81%E5%8E%9F%E7%90%86)
 
 
 Enter the PaddleOCR root directory，perform sensitivity analysis on the model with the following command：