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

PPOCRLabel/libs/dataPartitionDialog.py

+try:
+    from PyQt5.QtGui import *
+    from PyQt5.QtCore import *
+    from PyQt5.QtWidgets import *
+except ImportError:
+    from PyQt4.QtGui import *
+    from PyQt4.QtCore import *
+
+from libs.utils import newIcon
+
+import time
+import datetime
+import json
+import cv2
+import numpy as np
+
+
+BB = QDialogButtonBox
+
+class DataPartitionDialog(QDialog):
+    def __init__(self, parent=None):
+        super().__init__()
+        self.parnet = parent
+        self.title = 'DATA PARTITION'
+
+        self.train_ratio = 70
+        self.val_ratio = 15
+        self.test_ratio = 15
+        
+        self.initUI()
+
+    def initUI(self):
+        self.setWindowTitle(self.title)
+        self.setWindowModality(Qt.ApplicationModal)
+
+        self.flag_accept = True
+
+        if self.parnet.lang == 'ch':
+            msg = "导出JSON前请保存所有图像的标注且关闭EXCEL!"
+        else:
+            msg = "Please save all the annotations and close the EXCEL before exporting JSON!"
+
+        info_msg = QLabel(msg, self)
+        info_msg.setWordWrap(True)
+        info_msg.setStyleSheet("color: red")
+        info_msg.setFont(QFont('Arial', 12))
+
+        train_lbl = QLabel('Train split: ', self)
+        train_lbl.setFont(QFont('Arial', 15))
+        val_lbl = QLabel('Valid split: ', self)
+        val_lbl.setFont(QFont('Arial', 15))
+        test_lbl = QLabel('Test split: ', self)
+        test_lbl.setFont(QFont('Arial', 15))
+
+        self.train_input = QLineEdit(self)
+        self.train_input.setFont(QFont('Arial', 15))
+        self.val_input = QLineEdit(self)
+        self.val_input.setFont(QFont('Arial', 15))
+        self.test_input = QLineEdit(self)
+        self.test_input.setFont(QFont('Arial', 15))
+
+        self.train_input.setText(str(self.train_ratio))
+        self.val_input.setText(str(self.val_ratio))
+        self.test_input.setText(str(self.test_ratio))
+
+        validator = QIntValidator(0, 100)
+        self.train_input.setValidator(validator)
+        self.val_input.setValidator(validator)
+        self.test_input.setValidator(validator)
+
+        gridlayout = QGridLayout()
+        gridlayout.addWidget(info_msg, 0, 0, 1, 2)
+        gridlayout.addWidget(train_lbl, 1, 0)
+        gridlayout.addWidget(val_lbl, 2, 0)
+        gridlayout.addWidget(test_lbl, 3, 0)
+        gridlayout.addWidget(self.train_input, 1, 1)
+        gridlayout.addWidget(self.val_input, 2, 1)
+        gridlayout.addWidget(self.test_input, 3, 1)
+
+        bb = BB(BB.Ok | BB.Cancel, Qt.Horizontal, self)
+        bb.button(BB.Ok).setIcon(newIcon('done'))
+        bb.button(BB.Cancel).setIcon(newIcon('undo'))
+        bb.accepted.connect(self.validate)
+        bb.rejected.connect(self.cancel)
+        gridlayout.addWidget(bb, 4, 0, 1, 2)
+
+        self.setLayout(gridlayout)
+        
+        self.show()
+
+    def validate(self):
+        self.flag_accept = True
+        self.accept()
+
+    def cancel(self):
+        self.flag_accept = False
+        self.reject()
+    
+    def getStatus(self):
+        return self.flag_accept
+
+    def getDataPartition(self):
+        self.train_ratio = int(self.train_input.text())
+        self.val_ratio = int(self.val_input.text())
+        self.test_ratio = int(self.test_input.text())
+
+        return self.train_ratio, self.val_ratio, self.test_ratio
+
+    def closeEvent(self, event):
+        self.flag_accept = False
+        self.reject()
+
+

PPOCRLabel/libs/utils.py

@@ -161,6 +161,77 @@ def get_rotate_crop_image(img, points):
         print(e)
 
 
+def boxPad(box, imgShape, pad : int) -> np.array:
+    """
+    Pad a box with [pad] pixels on each side.
+    """
+    box = np.array(box, dtype=np.int32)
+    box[0][0], box[0][1] = box[0][0] - pad, box[0][1] - pad
+    box[1][0], box[1][1] = box[1][0] + pad, box[1][1] - pad
+    box[2][0], box[2][1] = box[2][0] + pad, box[2][1] + pad
+    box[3][0], box[3][1] = box[3][0] - pad, box[3][1] + pad
+    h, w, _ = imgShape
+    box[:,0] = np.clip(box[:,0], 0, w)
+    box[:,1] = np.clip(box[:,1], 0, h)
+    return box
+
+
+def OBB2HBB(obb) -> np.array:
+    """
+    Convert Oriented Bounding Box to Horizontal Bounding Box.
+    """
+    hbb = np.zeros(4, dtype=np.int32)
+    hbb[0] = min(obb[:, 0])
+    hbb[1] = min(obb[:, 1])
+    hbb[2] = max(obb[:, 0])
+    hbb[3] = max(obb[:, 1])
+    return hbb
+
+
+def expand_list(merged, html_list):
+    '''
+    Fill blanks according to merged cells
+    '''
+    sr, er, sc, ec = merged
+    for i in range(sr, er):
+        for j in range(sc, ec):
+            html_list[i][j] = None
+    html_list[sr][sc] = ''
+    if ec - sc > 1:
+        html_list[sr][sc] += " colspan={}".format(ec - sc)
+    if er - sr > 1:
+        html_list[sr][sc] += " rowspan={}".format(er - sr)
+    return html_list
+
+
+def convert_token(html_list):
+    '''
+    Convert raw html to label format
+    '''
+    token_list = ["<tbody>"]
+    # final html list:
+    for row in html_list:
+        token_list.append("<tr>")
+        for col in row:
+            if col == None:
+                continue
+            elif col == 'td':
+                token_list.extend(["<td>", "</td>"])
+            else:
+                token_list.append("<td")
+                if 'colspan' in col:
+                    _, n = col.split('colspan=')
+                    token_list.append(" colspan=\"{}\"".format(n))
+                if 'rowspan' in col:
+                    _, n = col.split('rowspan=')
+                    token_list.append(" rowspan=\"{}\"".format(n))
+                token_list.extend([">", "</td>"])
+        token_list.append("</tr>")
+    token_list.append("</tbody>")
+
+    return token_list
+
+
 def stepsInfo(lang='en'):
     if lang == 'ch':
         msg = "1. 安装与运行：使用上述命令安装与运行程序。\n" \

PPOCRLabel/resources/strings/strings-en.properties

@@ -84,7 +84,7 @@ mhelp=Help
 iconList=Icon List
 detectionBoxposition=Detection box position
 recognitionResult=Recognition result
-creatPolygon=Create Quadrilateral
+creatPolygon=Create PolygonBox
 rotateLeft=Left turn 90 degrees
 rotateRight=Right turn 90 degrees
 drawSquares=Draw Squares
@@ -110,3 +110,6 @@ lockBoxDetail=Lock selected box/Unlock all box
 keyListTitle=Key List
 keyDialogTip=Enter object label
 keyChange=Change Box Key
+TableRecognition=Table Recognition
+cellreRecognition=Cell Re-Recognition
+exportJSON=export JSON(PubTabNet)

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

@@ -84,7 +84,7 @@ mhelp=帮助
 iconList=缩略图
 detectionBoxposition=检测框位置
 recognitionResult=识别结果
-creatPolygon=四点标注
+creatPolygon=多边形标注
 drawSquares=正方形标注
 rotateLeft=图片左旋转90度
 rotateRight=图片右旋转90度
@@ -109,4 +109,7 @@ 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
 keyListTitle=关键词列表
 keyDialogTip=请输入类型名称
-keyChange=更改Box关键字类别
+keyChange=更改Box关键字类别
\ No newline at end of file
+TableRecognition=表格识别
+cellreRecognition=单元格重识别
+exportJSON=导出表格JSON标注
\ No newline at end of file

README.md

@@ -19,12 +19,9 @@ PaddleOCR aims to create multilingual, awesome, leading, and practical OCR tools
 
 
 **Recent updates**
-- 2021.12.21 OCR open source online course starts. The lesson starts at 8:30 every night and lasts for ten days. Free registration: https://aistudio.baidu.com/aistudio/course/introduce/25207
-- 2021.12.21 release PaddleOCR v2.4, release 1 text detection algorithm (PSENet), 3 text recognition algorithms (NRTR、SEED、SAR), 1 key information extraction algorithm (SDMGR, [tutorial](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.4/ppstructure/docs/kie.md)) and 3 DocVQA algorithms (LayoutLM, LayoutLMv2, LayoutXLM, [tutorial](https://github.com/PaddlePaddle/PaddleOCR/tree/release/2.4/ppstructure/vqa)).
-- PaddleOCR R&D team would like to share the key points of PP-OCRv2, at 20:15 pm on September 8th, [Course Address](https://aistudio.baidu.com/aistudio/education/group/info/6758).
-- 2021.9.7 release PaddleOCR v2.3, [PP-OCRv2](#PP-OCRv2) is proposed. The inference speed of PP-OCRv2 is 220% higher than that of PP-OCR server in CPU device. The F-score of PP-OCRv2 is 7% higher than that of PP-OCR mobile.
-- 2021.8.3 released PaddleOCR v2.2, add a new structured documents analysis toolkit, i.e., [PP-Structure](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.2/ppstructure/README.md), support layout analysis and table recognition (One-key to export chart images to Excel files).
-- 2021.4.8 release end-to-end text recognition algorithm [PGNet](https://www.aaai.org/AAAI21Papers/AAAI-2885.WangP.pdf) which is published in AAAI 2021. Find tutorial [here](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/pgnet_en.md)；release multi language recognition [models](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/multi_languages_en.md), support more than 80 languages recognition; especically, the performance of [English recognition model](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.1/doc/doc_en/models_list_en.md#English) is Optimized.
+- 2021.12.21 release PaddleOCR v2.4, release 1 text detection algorithm (PSENet), 3 text recognition algorithms (NRTR、SEED、SAR), 1 key information extraction algorithm (SDMGR, [tutorial](./ppstructure/docs/kie_en.md)) and 3 DocVQA algorithms (LayoutLM, LayoutLMv2, LayoutXLM, [tutorial](./ppstructure/vqa)).
+- 2021.9.7 release PaddleOCR v2.3, [PP-OCRv2](./doc/doc_en/ppocr_introduction_en.md#pp-ocrv2) is proposed. The inference speed of PP-OCRv2 is 220% higher than that of PP-OCR server in CPU device. The F-score of PP-OCRv2 is 7% higher than that of PP-OCR mobile.
+- 2021.8.3 released PaddleOCR v2.2, add a new structured documents analysis toolkit, i.e., [PP-Structure](./ppstructure/README.md), support layout analysis and table recognition (One-key to export chart images to Excel files).
 
 - [more](./doc/doc_en/update_en.md)
 
@@ -81,7 +78,6 @@ PaddleOCR support a variety of cutting-edge algorithms related to OCR, and devel
 
 ## Tutorials
 - [Environment Preparation](./doc/doc_en/environment_en.md)
-- [Quick Start](./doc/doc_en/quickstart_en.md)
 - [PP-OCR 🔥](./doc/doc_en/ppocr_introduction_en.md)
     - [Quick Start](./doc/doc_en/quickstart_en.md)
     - [Model Zoo](./doc/doc_en/models_en.md)

README_ch.md

@@ -27,10 +27,9 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力
 
 ## 近期更新
 
-- 2021.12.21《动手学OCR · 十讲》课程开讲，12月21日起每晚八点半线上授课！[免费报名地址](https://aistudio.baidu.com/aistudio/course/introduce/25207)。
-- 2021.12.21 发布PaddleOCR v2.4。OCR算法新增1种文本检测算法（PSENet），3种文本识别算法（NRTR、SEED、SAR）；文档结构化算法新增1种关键信息提取算法（SDMGR，[文档](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.4/ppstructure/docs/kie.md)），3种DocVQA算法（LayoutLM、LayoutLMv2，LayoutXLM，[文档](https://github.com/PaddlePaddle/PaddleOCR/tree/release/2.4/ppstructure/vqa)）。
-- 2021.9.7 发布PaddleOCR v2.3与[PP-OCRv2](#PP-OCRv2)，CPU推理速度相比于PP-OCR server提升220%；效果相比于PP-OCR mobile 提升7%。
-- 2021.8.3 发布PaddleOCR v2.2，新增文档结构分析[PP-Structure](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.2/ppstructure/README_ch.md)工具包，支持版面分析与表格识别（含Excel导出）。
+- 2021.12.21 发布PaddleOCR v2.4。OCR算法新增1种文本检测算法（PSENet），3种文本识别算法（NRTR、SEED、SAR）；文档结构化算法新增1种关键信息提取算法（SDMGR，[文档](./ppstructure/docs/kie.md)），3种DocVQA算法（LayoutLM、LayoutLMv2，LayoutXLM，[文档](./ppstructure/vqa)）。
+- 2021.9.7 发布PaddleOCR v2.3与[PP-OCRv2](./doc/doc_ch/ppocr_introduction.md#pp-ocrv2)，CPU推理速度相比于PP-OCR server提升220%；效果相比于PP-OCR mobile 提升7%。
+- 2021.8.3 发布PaddleOCR v2.2，新增文档结构分析[PP-Structure](./ppstructure/README_ch.md)工具包，支持版面分析与表格识别（含Excel导出）。
 
 > [更多](./doc/doc_ch/update.md)
 
@@ -83,7 +82,6 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力
 ## 文档教程
 
 - [运行环境准备](./doc/doc_ch/environment.md)
-- [快速开始（中英文/多语言/文档分析）](./doc/doc_ch/quickstart.md)
 - [PP-OCR文本检测识别🔥](./doc/doc_ch/ppocr_introduction.md)
     - [快速开始](./doc/doc_ch/quickstart.md)
     - [模型库](./doc/doc_ch/models_list.md)

configs/rec/PP-OCRv3/ch_PP-OCRv3_rec_distillation.yml

@@ -129,7 +129,7 @@ Loss:
       key: head_out
       multi_head: True
   - DistillationSARLoss:
-      weight: 0.5
+      weight: 1.0
       model_name_list: ["Student", "Teacher"]
       key: head_out
       multi_head: True

deploy/cpp_infer/src/ocr_rec.cpp

@@ -166,6 +166,10 @@ void CRNNRecognizer::LoadModel(const std::string &model_dir) {
     config.SetCpuMathLibraryNumThreads(this->cpu_math_library_num_threads_);
   }
 
+  // get pass_builder object
+  auto pass_builder = config.pass_builder();
+  // delete "matmul_transpose_reshape_fuse_pass"
+  pass_builder->DeletePass("matmul_transpose_reshape_fuse_pass");
   config.SwitchUseFeedFetchOps(false);
   // true for multiple input
   config.SwitchSpecifyInputNames(true);

deploy/pdserving/config.yml

@@ -36,8 +36,8 @@ op:
             #det模型路径
             model_config: ./ppocr_det_v3_serving
 
-            #Fetch结果列表，以client_config中fetch_var的alias_name为准
-            fetch_list: ["sigmoid_0.tmp_0"]
+            #Fetch结果列表，以client_config中fetch_var的alias_name为准，不设置默认取全部输出变量
+            #fetch_list: ["sigmoid_0.tmp_0"]
 
             #计算硬件ID，当devices为""或不写时为CPU预测；当devices为"0", "0,1,2"时为GPU预测，表示使用的GPU卡
             devices: "0"
@@ -62,8 +62,8 @@ op:
             #rec模型路径
             model_config: ./ppocr_rec_v3_serving
 
-            #Fetch结果列表，以client_config中fetch_var的alias_name为准
-            fetch_list: ["softmax_5.tmp_0"]
+            #Fetch结果列表，以client_config中fetch_var的alias_name为准, 不设置默认取全部输出变量
+            #fetch_list: 
 
             #计算硬件ID，当devices为""或不写时为CPU预测；当devices为"0", "0,1,2"时为GPU预测，表示使用的GPU卡
             devices: "0"

deploy/pdserving/ocr_reader.py

@@ -393,7 +393,7 @@ class OCRReader(object):
         return norm_img_batch[0]
 
     def postprocess(self, outputs, with_score=False):
-        preds = outputs["softmax_5.tmp_0"]
+        preds = list(outputs.values())[0]
         try:
             preds = preds.numpy()
         except:
@@ -404,8 +404,11 @@ class OCRReader(object):
             preds_idx, preds_prob, is_remove_duplicate=True)
         return text
 
-from argparse import ArgumentParser,RawDescriptionHelpFormatter
+
+from argparse import ArgumentParser, RawDescriptionHelpFormatter
 import yaml
+
+
 class ArgsParser(ArgumentParser):
     def __init__(self):
         super(ArgsParser, self).__init__(
@@ -441,16 +444,16 @@ class ArgsParser(ArgumentParser):
             s = s.strip()
             k, v = s.split('=')
             v = self._parse_helper(v)
-            print(k,v, type(v))
+            print(k, v, type(v))
             cur = config
             parent = cur
             for kk in k.split("."):
                 if kk not in cur:
-                     cur[kk] = {}
-                     parent = cur
-                     cur = cur[kk]
+                    cur[kk] = {}
+                    parent = cur
+                    cur = cur[kk]
                 else:
-                     parent = cur
-                     cur = cur[kk]
+                    parent = cur
+                    cur = cur[kk]
             parent[k.split(".")[-1]] = v
-        return config
+        return config
\ No newline at end of file

deploy/pdserving/web_service.py

@@ -56,7 +56,7 @@ class DetOp(Op):
         return {"x": det_img[np.newaxis, :].copy()}, False, None, ""
 
     def postprocess(self, input_dicts, fetch_dict, data_id, log_id):
-        det_out = fetch_dict["sigmoid_0.tmp_0"]
+        det_out = list(fetch_dict.values())[0]
         ratio_list = [
             float(self.new_h) / self.ori_h, float(self.new_w) / self.ori_w
         ]

deploy/pdserving/web_service_det.py

@@ -55,7 +55,7 @@ class DetOp(Op):
         return {"x": det_img[np.newaxis, :].copy()}, False, None, ""
 
     def postprocess(self, input_dicts, fetch_dict, data_id, log_id):
-        det_out = fetch_dict["sigmoid_0.tmp_0"]
+        det_out = list(fetch_dict.values())[0]
         ratio_list = [
             float(self.new_h) / self.ori_h, float(self.new_w) / self.ori_w
         ]

doc/doc_ch/ppocr_introduction.md

@@ -38,8 +38,9 @@ PP-OCRv2在PP-OCR的基础上，进一步在5个方面重点优化，检测模
 
 #### PP-OCRv3
 
-PP-OCRv3在PP-OCRv2的基础上进一步升级。检测模型仍然基于DB算法，优化策略采用了带残差注意力机制的FPN结构RSEFPN、增大感受野的PAN结构LKPAN、基于DML训练的更优的教师模型；识别模型将base模型从CRNN替换成了IJCAI 2022论文[SVTR](https://arxiv.org/abs/2205.00159)，并采用SVTR轻量化、带指导训练CTC、数据增广策略RecConAug、自监督训练的更好的预训练模型、无标签数据的使用进行模型加速和效果提升。更多细节请参考PP-OCRv3[技术报告](./PP-OCRv3_introduction.md)。
-
+PP-OCRv3在PP-OCRv2的基础上，针对检测模型和识别模型，进行了共计9个方面的升级：
+- PP-OCRv3检测模型对PP-OCRv2中的CML协同互学习文本检测蒸馏策略进行了升级，分别针对教师模型和学生模型进行进一步效果优化。其中，在对教师模型优化时，提出了大感受野的PAN结构LK-PAN和引入了DML蒸馏策略；在对学生模型优化时，提出了残差注意力机制的FPN结构RSE-FPN。
+- PP-OCRv3的识别模块是基于文本识别算法[SVTR](https://arxiv.org/abs/2205.00159)优化。SVTR不再采用RNN结构，通过引入Transformers结构更加有效地挖掘文本行图像的上下文信息，从而提升文本识别能力。PP-OCRv3通过轻量级文本识别网络SVTR_LCNet、Attention损失指导CTC损失训练策略、挖掘文字上下文信息的数据增广策略TextConAug、TextRotNet自监督预训练模型、UDML联合互学习策略、UIM无标注数据挖掘方案，6个方面进行模型加速和效果提升。
 
 PP-OCRv3系统pipeline如下：
 
@@ -47,6 +48,9 @@ PP-OCRv3系统pipeline如下：
     <img src="../ppocrv3_framework.png" width="800">
 </div>
 
+更多细节请参考PP-OCRv3[技术报告](./PP-OCRv3_introduction.md)。
+
+
 <a name="2"></a>
 ## 2. 特性
 

doc/doc_ch/quickstart.md

@@ -59,15 +59,13 @@ cd /path/to/ppocr_img
 
 如果不使用提供的测试图片，可以将下方`--image_dir`参数替换为相应的测试图片路径。
 
-**注意** whl包默认使用`PP-OCRv3`模型，识别模型使用的输入shape为`3,48,320`, 因此如果使用识别功能，需要添加参数`--rec_image_shape 3,48,320`，如果不使用默认的`PP-OCRv3`模型，则无需设置该参数。
-
 <a name="211"></a>
 #### 2.1.1 中英文模型
 
 * 检测+方向分类器+识别全流程：`--use_angle_cls true`设置使用方向分类器识别180度旋转文字，`--use_gpu false`设置不使用GPU
 
   ```bash
-  paddleocr --image_dir ./imgs/11.jpg --use_angle_cls true --use_gpu false --rec_image_shape 3,48,320
+  paddleocr --image_dir ./imgs/11.jpg --use_angle_cls true --use_gpu false
   ```
 
   结果是一个list，每个item包含了文本框，文字和识别置信度
@@ -94,7 +92,7 @@ cd /path/to/ppocr_img
 - 单独使用识别：设置`--det`为`false`
 
   ```bash
-  paddleocr --image_dir ./imgs_words/ch/word_1.jpg --det false --rec_image_shape 3,48,320
+  paddleocr --image_dir ./imgs_words/ch/word_1.jpg --det false
   ```
 
   结果是一个list，每个item只包含识别结果和识别置信度
@@ -104,16 +102,16 @@ cd /path/to/ppocr_img
   ```
 
 
-如需使用2.0模型，请指定参数`--version PP-OCR`，paddleocr默认使用PP-OCRv3模型(`--versioin PP-OCRv3`)。更多whl包使用可参考[whl包文档](./whl.md)
+如需使用2.0模型，请指定参数`--ocr_version PP-OCR`，paddleocr默认使用PP-OCRv3模型(`--ocr_version PP-OCRv3`)。更多whl包使用可参考[whl包文档](./whl.md)
 
 <a name="212"></a>
 
 #### 2.1.2 多语言模型
 
-Paddleocr目前支持80个语种，可以通过修改`--lang`参数进行切换，对于英文模型，指定`--lang=en`, PP-OCRv3目前只支持中文和英文模型，其他多语言模型会陆续更新。
+PaddleOCR目前支持80个语种，可以通过修改`--lang`参数进行切换，对于英文模型，指定`--lang=en`。
 
 ``` bash
-paddleocr --image_dir ./imgs_en/254.jpg --lang=en --rec_image_shape 3,48,320
+paddleocr --image_dir ./imgs_en/254.jpg --lang=en
 ```
 
 <div align="center">

doc/doc_ch/update.md

 # 更新
+- 2022.5.7 添加对[Weights & Biases](https://docs.wandb.ai/)训练日志记录工具的支持。
 - 2021.12.21 《OCR十讲》课程开讲，12月21日起每晚八点半线上授课！ 【免费】报名地址：https://aistudio.baidu.com/aistudio/course/introduce/25207
 - 2021.12.21 发布PaddleOCR v2.4。OCR算法新增1种文本检测算法（PSENet），3种文本识别算法（NRTR、SEED、SAR）；文档结构化算法新增1种关键信息提取算法（SDMGR），3种DocVQA算法（LayoutLM、LayoutLMv2，LayoutXLM）。
 - 2021.9.7 发布PaddleOCR v2.3，发布[PP-OCRv2](#PP-OCRv2)，CPU推理速度相比于PP-OCR server提升220%；效果相比于PP-OCR mobile 提升7%。

doc/doc_ch/whl.md

@@ -199,12 +199,10 @@ for line in result:
 paddleocr -h
 ```
 
-**注意** whl包默认使用`PP-OCRv3`模型，识别模型使用的输入shape为`3,48,320`, 因此如果使用识别功能，需要添加参数`--rec_image_shape 3,48,320`，如果不使用默认的`PP-OCRv3`模型，则无需设置该参数。
-
 * 检测+方向分类器+识别全流程
 
 ```bash
-paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --use_angle_cls true --rec_image_shape 3,48,320
+paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --use_angle_cls true
 ```
 
 结果是一个list，每个item包含了文本框，文字和识别置信度
@@ -217,7 +215,7 @@ paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --use_angle_cls true --rec_image
 * 检测+识别
 
 ```bash
-paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --rec_image_shape 3,48,320
+paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg
 ```
 
 结果是一个list，每个item包含了文本框，文字和识别置信度
@@ -230,7 +228,7 @@ paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --rec_image_shape 3,48,320
 * 方向分类器+识别
 
 ```bash
-paddleocr --image_dir PaddleOCR/doc/imgs_words/ch/word_1.jpg --use_angle_cls true --det false --rec_image_shape 3,48,320
+paddleocr --image_dir PaddleOCR/doc/imgs_words/ch/word_1.jpg --use_angle_cls true --det false
 ```
 
 结果是一个list，每个item只包含识别结果和识别置信度
@@ -256,7 +254,7 @@ paddleocr --image_dir PaddleOCR/doc/imgs/11.jpg --rec false
 * 单独执行识别
 
 ```bash
-paddleocr --image_dir PaddleOCR/doc/imgs_words/ch/word_1.jpg --det false --rec_image_shape 3,48,320
+paddleocr --image_dir PaddleOCR/doc/imgs_words/ch/word_1.jpg --det false
 ```
 
 结果是一个list，每个item只包含识别结果和识别置信度
@@ -416,4 +414,4 @@ im_show.save('result.jpg')
 | cls                     | 前向时是否启动分类 (命令行模式下使用use_angle_cls控制前向是否启动分类)                                                                                                                                                                                                | FALSE                    |
 | show_log                     | 是否打印logger信息                                                                                                                                               | FALSE                    |
 | type                     | 执行ocr或者表格结构化, 值可选['ocr','structure']                                                                                                                                                                                             | ocr                    |
-| ocr_version                     | OCR模型版本，可选PP-OCRv3, PP-OCRv2, PP-OCR。PP-OCRv3 目前仅支持中、英文的检测和识别模型，方向分类器模型；PP-OCRv2 目前仅支持中文的检测和识别模型；PP-OCR支持中文的检测，识别，多语种识别，方向分类器等模型                                                                                                                                        | PP-OCRv3                   |
+| ocr_version                     | OCR模型版本，可选PP-OCRv3, PP-OCRv2, PP-OCR。PP-OCRv3 支持中、英文的检测、识别、多语种识别，方向分类器等模型；PP-OCRv2 目前仅支持中文的检测和识别模型；PP-OCR支持中文的检测，识别，多语种识别，方向分类器等模型                                                                                                                                        | PP-OCRv3                   |

doc/doc_en/config_en.md

@@ -36,6 +36,7 @@ Take rec_chinese_lite_train_v2.0.yml as an example
 |      pretrained_model    |    Set the path of the pre-trained model      |  ./pretrain_models/CRNN/best_accuracy  |  \          |
 |      checkpoints         |    set model parameter path            |       None        |   Used to load parameters after interruption to continue training|
 |      use_visualdl  |    Set whether to enable visualdl for visual log display |          False        |    [Tutorial](https://www.paddlepaddle.org.cn/paddle/visualdl) |
+|      use_wandb     |    Set whether to enable W&B for visual log display      | False | [Documentation](https://docs.wandb.ai/)
 |      infer_img            |    Set inference image path or folder path     |       ./infer_img | \||
 |      character_dict_path |    Set dictionary path            |  ./ppocr/utils/ppocr_keys_v1.txt  | If the character_dict_path is None, model can only recognize number and lower letters |
 |      max_text_length     |    Set the maximum length of text        |       25          |                \                 |
@@ -66,7 +67,7 @@ In PaddleOCR, the network is divided into four stages: Transform, Backbone, Neck
 | :---------------------: |  :---------------------:   | :--------------:  |   :--------------------:   |
 |      model_type        |         Network Type          |  rec  |  Currently support`rec`,`det`,`cls`  |
 |      algorithm           |    Model name  |       CRNN         |               See [algorithm_overview](./algorithm_overview_en.md) for the support list             |
-|      **Transform**           |    Set the transformation method  |       -       |               Currently only recognition algorithms are supported, see [ppocr/modeling/transforms](../../ppocr/modeling/transforms) for details            |
+|      **Transform**           |    Set the transformation method  |       -       |               Currently only recognition algorithms are supported, see [ppocr/modeling/transform](../../ppocr/modeling/transforms) for details            |
 |        name    |      Transformation class name   |         TPS       | Currently supports `TPS` |
 |        num_fiducial      |   Number of TPS control points        |       20      |  Ten on the top and bottom       |
 |        loc_lr      |    Localization network learning rate        |       0.1      |  \      |
@@ -130,6 +131,17 @@ In PaddleOCR, the network is divided into four stages: Transform, Backbone, Neck
 |      drop_last        |        Whether to discard the last incomplete mini-batch because the number of samples in the data set cannot be divisible by batch_size        |  True | \  |
 |      num_workers        |        The number of sub-processes used to load data, if it is 0, the sub-process is not started, and the data is loaded in the main process       |  8 | \  |
 
+### Weights & Biases ([W&B](../../ppocr/utils/loggers/wandb_logger.py))
+|         Parameter             |            Use            |      Defaults        |            Note             |
+| :---------------------: |  :---------------------:   | :--------------:  |   :--------------------:   |
+|          project              |     Project to which the run is to be logged | uncategorized | \
+|          name                 |     Alias/Name of the run | Randomly generated by wandb | \ 
+|          id                   |     ID of the run    | Randomly generated by wandb     | \
+|          entity               | User or team to which the run is being logged         | The logged in user | \
+|          save_dir             | local directory in which all the models and other data is saved | wandb | \
+|          config               | model configuration | None | \
+
+
 <a name="3-multilingual-config-file-generation"></a>
 
 ## 3. Multilingual Config File Generation
@@ -233,4 +245,4 @@ For more supported languages, please refer to : [Multi-language model](https://g
 
 The multi-language model training method is the same as the Chinese model. The training data set is 100w synthetic data. A small amount of fonts and test data can be downloaded using the following two methods.
 * [Baidu Netdisk](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA),Extraction code:frgi.
-* [Google drive](https://drive.google.com/file/d/18cSWX7wXSy4G0tbKJ0d9PuIaiwRLHpjA/view)
+* [Google drive](https://drive.google.com/file/d/18cSWX7wXSy4G0tbKJ0d9PuIaiwRLHpjA/view)
\ No newline at end of file

doc/doc_en/logging_en.md

+## Logging metrics and models 
+
+PaddleOCR comes with two metric logging tools integrated directly into the training API: [VisualDL](https://readthedocs.org/projects/visualdl/) and [Weights & Biases](https://docs.wandb.ai/). 
+
+### VisualDL
+VisualDL is a visualization analysis tool of PaddlePaddle. The integration allows all training metrics to be logged to a VisualDL dashboard. To use it, add the following line to the `Global` section of the config yaml file -
+
+```
+Global:
+    use_visualdl: True
+```
+
+To see the visualizations run the following command in your terminal
+
+```shell
+visualdl --logdir <save_model_dir>
+```
+
+Now open `localhost:8040` in your browser of choice!
+
+### Weights & Biases
+W&B is a MLOps tool that can be used for experiment tracking, dataset/model versioning, visualizing results and collaborating with colleagues. A W&B logger is integrated directly into PaddleOCR and to use it, first you need to install the `wandb` sdk and login to your wandb account.
+
+```shell
+pip install wandb
+wandb login
+```
+
+If you do not have a wandb account, you can make one [here](https://wandb.ai/site).
+
+To visualize and track your model training add the following flag to your config yaml file under the `Global` section -
+
+```
+Global:
+    use_wandb: True
+```
+
+To add more arguments to the `WandbLogger` listed [here](./config_en.md) add the header `wandb` to the yaml file and add the arguments under it - 
+
+```
+wandb:
+    project: my_project
+    entity: my_team
+```
+
+These config variables from the yaml file are used to instantiate the `WandbLogger` object with the project name, entity name (the logged in user by default), directory to store metadata (`./wandb` by default) and more. During the training process, the `log_metrics` function is called to log training and evaluation metrics at the training and evaluation steps respectively from the rank 0 process only.
+
+At every model saving step, the WandbLogger, logs the model using the `log_model` function along with relavant metadata and tags showing the epoch in which the model is saved, the model is best or not and so on.
+
+All the logging mentioned above is integrated into the `program.train` function and will generate dashboards like this -
+
+![W&B Dashboard](../imgs_en/wandb_metrics.png)
+
+![W&B Models](../imgs_en/wandb_models.png)
+
+For more advanced usage to log images, audios, videos or any other form of data, you can use `WandbLogger().run.log`. More examples on how to log different kinds of data are available [here](https://docs.wandb.ai/examples).
+
+To view the dashboard, the link to the dashboard is printed to the console at the beginning and end of every training job and you can also access it by logging into your W&B account on your browser.
+
+### Using Multiple Loggers
+Both VisualDL and W&B can also be used simultaneously by just setting both the aforementioned flags to True.
\ No newline at end of file

doc/doc_en/models_list_en.md

@@ -16,13 +16,13 @@
   - [3. Text Angle Classification Model](#3-text-angle-classification-model)
   - [4. Paddle-Lite Model](#4-paddle-lite-model)
 
-The downloadable models provided by PaddleOCR include `inference model`, `trained model`, `pre-trained model` and `slim model`. The differences between the models are as follows:
+The downloadable models provided by PaddleOCR include `inference model`, `trained model`, `pre-trained model` and `nb model`. The differences between the models are as follows:
 
 |model type|model format|description|
 |--- | --- | --- |
 |inference model|inference.pdmodel、inference.pdiparams|Used for inference based on Paddle inference engine，[detail](./inference_en.md)|
 |trained model, pre-trained model|\*.pdparams、\*.pdopt、\*.states |The checkpoints model saved in the training process, which stores the parameters of the model, mostly used for model evaluation and continuous training.|
-|slim model|\*.nb| Model compressed by PaddleSlim (a model compression tool using PaddlePaddle), which is suitable for mobile-side deployment scenarios (Paddle-Lite is needed for slim model deployment). |
+|nb model|\*.nb| Model optimized by Paddle-Lite, which is suitable for mobile-side deployment scenarios (Paddle-Lite is needed for nb model deployment). |
 
 Relationship of the above models is as follows.
 
@@ -37,7 +37,7 @@ Relationship of the above models is as follows.
 
 |model name|description|config|model size|download|
 | --- | --- | --- | --- | --- |
-|ch_PP-OCRv3_det_slim| [New] slim quantization with distillation lightweight model, supporting Chinese, English, multilingual text detection |[ch_PP-OCRv3_det_cml.yml](../../configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml)| 1.1M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_infer.tar) / [trained model (coming soon)](https://paddleocr.bj.bcebos.com/PP-OCRv3/ch/ch_PP-OCRv3_det_slim_distill_train.tar) / [slim model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_infer.nb)|
+|ch_PP-OCRv3_det_slim| [New] slim quantization with distillation lightweight model, supporting Chinese, English, multilingual text detection |[ch_PP-OCRv3_det_cml.yml](../../configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml)| 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/ch/ch_PP-OCRv3_det_slim_distill_train.tar) / [nb model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_det_slim_infer.nb)|
 |ch_PP-OCRv3_det| [New] Original lightweight model, supporting Chinese, English, multilingual text detection |[ch_PP-OCRv3_det_cml.yml](../../configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml)| 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-OCRv2_det_slim| [New] slim quantization with distillation lightweight model, supporting Chinese, English, multilingual text detection|[ch_PP-OCRv2_det_cml.yml](../../configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_cml.yml)| 3M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_slim_quant_infer.tar)|
 |ch_PP-OCRv2_det| [New] Original lightweight model, supporting Chinese, English, multilingual text detection|[ch_PP-OCRv2_det_cml.yml](../../configs/det/ch_PP-OCRv2/ch_PP-OCRv2_det_cml.yml)|3M|[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_det_distill_train.tar)|
@@ -51,7 +51,7 @@ Relationship of the above models is as follows.
 
 |model name|description|config|model size|download|
 | --- | --- | --- | --- | --- |
-|en_PP-OCRv3_det_slim | [New] Slim qunatization with distillation lightweight detection model, supporting English | [ch_PP-OCRv3_det_cml.yml](../../configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml) | 1.1M |[inference model(coming soon)](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_slim_infer.tar) / [trained model (coming soon)](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_slim_distill_train.tar) / [slim model(coming soon)](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_slim_infer.nb) |
+|en_PP-OCRv3_det_slim | [New] Slim qunatization with distillation lightweight detection model, supporting English | [ch_PP-OCRv3_det_cml.yml](../../configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml) | 1.1M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_slim_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_slim_distill_train.tar) / [nb model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_slim_infer.nb) |
 |ch_PP-OCRv3_det | [New] Original lightweight detection model, supporting English |[ch_PP-OCRv3_det_cml.yml](../../configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml)| 3.8M | [inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_distill_train.tar) |
 
 * Note: English configuration file is same as Chinese except training data, here we only provide one configuration file.
@@ -62,7 +62,7 @@ Relationship of the above models is as follows.
 
 |model name|description|config|model size|download|
 | --- | --- | --- | --- | --- |
-| ml_PP-OCRv3_det_slim | [New] Slim qunatization with distillation lightweight detection model, supporting English | [ch_PP-OCRv3_det_cml.yml](../../configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml) | 1.1M | [inference model(coming soon)](https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/Multilingual_PP-OCRv3_det_slim_infer.tar) / [trained model (coming soon)](https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/Multilingual_PP-OCRv3_det_slim_distill_train.tar) / [slim model(coming soon)](https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/Multilingual_PP-OCRv3_det_slim_infer.nb) |
+| ml_PP-OCRv3_det_slim | [New] Slim qunatization with distillation lightweight detection model, supporting English | [ch_PP-OCRv3_det_cml.yml](../../configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml) | 1.1M | [inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/Multilingual_PP-OCRv3_det_slim_infer.tar) / [trained model ](https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/Multilingual_PP-OCRv3_det_slim_distill_train.tar) / [nb model](https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/Multilingual_PP-OCRv3_det_slim_infer.nb) |
 | ml_PP-OCRv3_det |[New] Original lightweight detection model, supporting English | [ch_PP-OCRv3_det_cml.yml](../../configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml)| 3.8M | [inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/Multilingual_PP-OCRv3_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/Multilingual_PP-OCRv3_det_distill_train.tar) |
 
 * Note: English configuration file is same as Chinese except training data, here we only provide one configuration file.
@@ -75,7 +75,7 @@ Relationship of the above models is as follows.
 
 |model name|description|config|model size|download|
 | --- | --- | --- | --- | --- |
-|ch_PP-OCRv3_rec_slim | [New] Slim qunatization with distillation lightweight model, supporting Chinese, English text recognition |[ch_PP-OCRv3_rec_distillation.yml](../../configs/rec/PP-OCRv3/ch_PP-OCRv3_rec_distillation.yml)| 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/ch/ch_PP-OCRv3_rec_slim_train.tar) / [slim model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.nb) |
+|ch_PP-OCRv3_rec_slim | [New] Slim qunatization with distillation lightweight model, supporting Chinese, English text recognition |[ch_PP-OCRv3_rec_distillation.yml](../../configs/rec/PP-OCRv3/ch_PP-OCRv3_rec_distillation.yml)| 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/ch/ch_PP-OCRv3_rec_slim_train.tar) / [nb model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/ch_PP-OCRv3_rec_slim_infer.nb) |
 |ch_PP-OCRv3_rec| [New] Original lightweight model, supporting Chinese, English, multilingual text recognition |[ch_PP-OCRv3_rec_distillation.yml](../../configs/rec/PP-OCRv3/ch_PP-OCRv3_rec_distillation.yml)| 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_PP-OCRv2_rec_slim| Slim qunatization with distillation lightweight model, supporting Chinese, English text recognition|[ch_PP-OCRv2_rec.yml](../../configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec.yml)| 9M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_slim_quant_train.tar) |
 |ch_PP-OCRv2_rec| Original lightweight model, supporting Chinese, English, multilingual text recognition |[ch_PP-OCRv2_rec_distillation.yml](../../configs/rec/ch_PP-OCRv2/ch_PP-OCRv2_rec_distillation.yml)|8.5M|[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv2/chinese/ch_PP-OCRv2_rec_train.tar) |
@@ -91,8 +91,8 @@ Relationship of the above models is as follows.
 
 |model name|description|config|model size|download|
 | --- | --- | --- | --- | --- |
-|en_PP-OCRv3_rec_slim | [New] Slim qunatization with distillation lightweight model, supporting english, English text recognition |[en_PP-OCRv3_rec_distillation.yml](../../configs/rec/PP-OCRv3/en_PP-OCRv3_rec_distillation.yml)| 4.9M |[inference model(coming soon)](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_slim_infer.tar) / [trained model (coming soon)](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_slim_train.tar) / [slim model(coming soon)](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_slim_infer.nb) |
-|en_PP-OCRv3_rec| [New] Original lightweight model, supporting english, English, multilingual text recognition |[en_PP-OCRv3_rec_distillation.yml](../../configs/rec/PP-OCRv3/en_PP-OCRv3_rec_distillation.yml)| 12.4M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_train.tar) |
+|en_PP-OCRv3_rec_slim | [New] Slim qunatization with distillation lightweight model, supporting english, English text recognition |[en_PP-OCRv3_rec.yml](../../configs/rec/PP-OCRv3/en_PP-OCRv3_rec.yml)| 3.2M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_slim_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_slim_train.tar) / [nb model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_slim_infer.nb) |
+|en_PP-OCRv3_rec| [New] Original lightweight model, supporting english, English, multilingual text recognition |[en_PP-OCRv3_rec.yml](../../configs/rec/PP-OCRv3/en_PP-OCRv3_rec.yml)| 9.6M |[inference model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_train.tar) |
 |en_number_mobile_slim_v2.0_rec|Slim pruned and quantized lightweight model, supporting English and number recognition|[rec_en_number_lite_train.yml](../../configs/rec/multi_language/rec_en_number_lite_train.yml)| 2.7M | [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/en_number_mobile_v2.0_rec_slim_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/en_number_mobile_v2.0_rec_slim_train.tar) |
 |en_number_mobile_v2.0_rec|Original lightweight model, supporting English and number recognition|[rec_en_number_lite_train.yml](../../configs/rec/multi_language/rec_en_number_lite_train.yml)|2.6M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_train.tar) |
 
@@ -122,11 +122,16 @@ For more supported languages, please refer to : [Multi-language model](./multi_l
 
 |model name|description|config|model size|download|
 | --- | --- | --- | --- | --- |
-|ch_ppocr_mobile_slim_v2.0_cls|Slim quantized model for text angle classification|[cls_mv3.yml](../../configs/cls/cls_mv3.yml)| 2.1M | [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_slim_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_slim_train.tar) |
+|ch_ppocr_mobile_slim_v2.0_cls|Slim quantized model for text angle classification|[cls_mv3.yml](../../configs/cls/cls_mv3.yml)| 2.1M | [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_slim_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_slim_train.tar) / [nb model](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_ppocr_mobile_v2.0_cls_infer_opt.nb) |
 |ch_ppocr_mobile_v2.0_cls|Original model for text angle classification|[cls_mv3.yml](../../configs/cls/cls_mv3.yml)|1.38M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |
 
 <a name="Paddle-Lite"></a>
 ## 4. Paddle-Lite Model
+
+Paddle Lite is an updated version of Paddle-Mobile, an open-open source deep learning framework designed to make it easy to perform inference on mobile, embeded, and IoT devices. It can further optimize the inference model and generate `nb model` used for edge devices. It's suggested to optimize the quantization model using Paddle-Lite because `INT8` format is used for the model storage and inference.
+
+This chapter lists OCR nb models with PP-OCRv2 or earlier versions. You can access to the latest nb models from the above tables.
+
 |Version|Introduction|Model size|Detection model|Text Direction model|Recognition model|Paddle-Lite branch|
 |---|---|---|---|---|---|---|
 |PP-OCRv2|extra-lightweight chinese OCR optimized model|11M|[download link](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_PP-OCRv2_det_infer_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_ppocr_mobile_v2.0_cls_infer_opt.nb)|[download link](https://paddleocr.bj.bcebos.com/PP-OCRv2/lite/ch_PP-OCRv2_rec_infer_opt.nb)|v2.10|

doc/doc_en/ppocr_introduction_en.md

@@ -17,6 +17,7 @@ English | [简体中文](../doc_ch/ppocr_introduction.md)
 
 PP-OCR is a self-developed practical ultra-lightweight OCR system, which is slimed and optimized based on the reimplemented [academic algorithms](algorithm_en.md), considering the balance between **accuracy** and **speed**.
 
+#### PP-OCR
 PP-OCR is a two-stage OCR system, in which the text detection algorithm is [DB](algorithm_det_db_en.md), and the text recognition algorithm is [CRNN](algorithm_rec_crnn_en.md). Besides, a [text direction classifier](angle_class_en.md) is added between the detection and recognition modules to deal with text in different directions.
 
 PP-OCR pipeline is as follows:
@@ -28,11 +29,16 @@ PP-OCR pipeline is as follows:
 
 PP-OCR system is in continuous optimization. At present, PP-OCR and PP-OCRv2 have been released:
 
-[1] PP-OCR adopts 19 effective strategies from 8 aspects including backbone network selection and adjustment, prediction head design, data augmentation, learning rate transformation strategy, regularization parameter selection, pre-training model use, and automatic model tailoring and quantization to optimize and slim down the models of each module (as shown in the green box above). The final results are an ultra-lightweight Chinese and English OCR model with an overall size of 3.5M and a 2.8M English digital OCR model. For more details, please refer to the PP-OCR technical article (https://arxiv.org/abs/2009.09941).
+PP-OCR adopts 19 effective strategies from 8 aspects including backbone network selection and adjustment, prediction head design, data augmentation, learning rate transformation strategy, regularization parameter selection, pre-training model use, and automatic model tailoring and quantization to optimize and slim down the models of each module (as shown in the green box above). The final results are an ultra-lightweight Chinese and English OCR model with an overall size of 3.5M and a 2.8M English digital OCR model. For more details, please refer to the PP-OCR technical article (https://arxiv.org/abs/2009.09941).
 
-[2] On the basis of PP-OCR, PP-OCRv2 is further optimized in five aspects. The detection model adopts CML(Collaborative Mutual Learning) knowledge distillation strategy and CopyPaste data expansion strategy. The recognition model adopts LCNet lightweight backbone network, U-DML knowledge distillation strategy and enhanced CTC loss function improvement (as shown in the red box above), which further improves the inference speed and prediction effect. For more details, please refer to the technical report of PP-OCRv2 (https://arxiv.org/abs/2109.03144).
+#### PP-OCRv2
+On the basis of PP-OCR, PP-OCRv2 is further optimized in five aspects. The detection model adopts CML(Collaborative Mutual Learning) knowledge distillation strategy and CopyPaste data expansion strategy. The recognition model adopts LCNet lightweight backbone network, U-DML knowledge distillation strategy and enhanced CTC loss function improvement (as shown in the red box above), which further improves the inference speed and prediction effect. For more details, please refer to the technical report of PP-OCRv2 (https://arxiv.org/abs/2109.03144).
 
-[3] PP-OCRv3 is further upgraded on the basis of PP-OCRv2. The detection model is still based on DB algorithm, and the optimization strategies include a newly proposed FPN structure with residual attention mechanism named with RSEFPN, a PAN structure with enlarged receptive field named with LKPAN, and better teacher model based on DML training; The recognition model replaces the base model from CRNN with IJCAI 2022 paper [SVTR](https://arxiv.org/abs/2205.00159), and adopts lightweight SVTR, guided training of CTC, data augmentation strategy RecConAug, better pre-trained model by self-supervised training, and the use of unlabeled data to accelerate the model and improve the effect. For more details, please refer to PP-OCRv3 [technical report](./PP-OCRv3_introduction_en.md).
+#### PP-OCRv3
+
+PP-OCRv3 upgraded the detection model and recognition model in 9 aspects based on PP-OCRv2:
+- PP-OCRv3 detector upgrades the CML(Collaborative Mutual Learning) text detection strategy proposed in PP-OCRv2, and further optimizes the effect of teacher model and student model respectively. In the optimization of teacher model, a pan module with large receptive field named LK-PAN is proposed and the DML distillation strategy is adopted; In the optimization of student model, a FPN module with residual attention mechanism named RSE-FPN is proposed.
+- PP-OCRv3 recognizer is optimized based on text recognition algorithm [SVTR](https://arxiv.org/abs/2205.00159). SVTR no longer adopts RNN by introducing transformers structure, which can mine the context information of text line image more effectively, so as to improve the ability of text recognition. PP-OCRv3 adopts lightweight text recognition network SVTR_LCNet, guided training of CTC loss by attention loss, data augmentation strategy TextConAug, better pre-trained model by self-supervised TextRotNet, UDML(Unified Deep Mutual Learning), and UIM (Unlabeled Images Mining) to accelerate the model and improve the effect.
 
 PP-OCRv3 pipeline is as follows:
 
@@ -40,6 +46,8 @@ PP-OCRv3 pipeline is as follows:
     <img src="../ppocrv3_framework.png" width="800">
 </div>
 
+For more details, please refer to [PP-OCRv3 technical report](./PP-OCRv3_introduction_en.md).
+
 <a name="2"></a>
 ## 2. Features
 

doc/doc_en/quickstart_en.md

-- [PaddleOCR Quick Start](#paddleocr-quick-start)
-  - [1. Installation](#1-installation)
+# PaddleOCR Quick Start
+
+**Note:** This tutorial mainly introduces the usage of PP-OCR series models, please refer to [PP-Structure Quick Start](../../ppstructure/docs/quickstart_en.md) for the quick use of document analysis related functions.
+
+- [1. Installation](#1-installation)
     - [1.1 Install PaddlePaddle](#11-install-paddlepaddle)
     - [1.2 Install PaddleOCR Whl Package](#12-install-paddleocr-whl-package)
-  - [2. Easy-to-Use](#2-easy-to-use)
+- [2. Easy-to-Use](#2-easy-to-use)
     - [2.1 Use by Command Line](#21-use-by-command-line)
       - [2.1.1 Chinese and English Model](#211-chinese-and-english-model)
       - [2.1.2 Multi-language Model](#212-multi-language-model)
-      - [2.1.3 Layout Analysis](#213-layout-analysis)
     - [2.2 Use by Code](#22-use-by-code)
       - [2.2.1 Chinese & English Model and Multilingual Model](#221-chinese--english-model-and-multilingual-model)
-      - [2.2.2 Layout Analysis](#222-layout-analysis)
-  - [3. Summary](#3-summary)
+- [3. Summary](#3-summary)
 
-# PaddleOCR Quick Start
 
 
 <a name="1nstallation"></a>
@@ -73,8 +73,6 @@ cd /path/to/ppocr_img
 
 If you do not use the provided test image, you can replace the following `--image_dir` parameter with the corresponding test image path
 
-**Note**: The whl package uses the `PP-OCRv3` model by default, and the input shape used by the recognition model is `3,48,320`, so if you use the recognition function, you need to add the parameter `--rec_image_shape 3,48,320`, if you do not use the default `PP- OCRv3` model, you do not need to set this parameter.
-
 <a name="211-english-and-chinese-model"></a>
 
 #### 2.1.1 Chinese and English Model
@@ -82,7 +80,7 @@ If you do not use the provided test image, you can replace the following `--imag
 * Detection, direction classification and recognition: set the parameter`--use_gpu false` to disable the gpu device
 
   ```bash
-  paddleocr --image_dir ./imgs_en/img_12.jpg --use_angle_cls true --lang en --use_gpu false --rec_image_shape 3,48,320
+  paddleocr --image_dir ./imgs_en/img_12.jpg --use_angle_cls true --lang en --use_gpu false
   ```
 
   Output will be a list, each item contains bounding box, text and recognition confidence
@@ -112,7 +110,7 @@ If you do not use the provided test image, you can replace the following `--imag
 * Only recognition: set `--det` to `false`
 
   ```bash
-  paddleocr --image_dir ./imgs_words_en/word_10.png --det false --lang en --rec_image_shape 3,48,320
+  paddleocr --image_dir ./imgs_words_en/word_10.png --det false --lang en
   ```
 
   Output will be a list, each item contains text and recognition confidence
@@ -121,15 +119,15 @@ If you do not use the provided test image, you can replace the following `--imag
   ['PAIN', 0.9934559464454651]
   ```
 
-If you need to use the 2.0 model, please specify the parameter `--version PP-OCR`, paddleocr uses the PP-OCRv3 model by default(`--versioin PP-OCRv3`). More whl package usage can be found in [whl package](./whl_en.md)
+If you need to use the 2.0 model, please specify the parameter `--ocr_version PP-OCR`, paddleocr uses the PP-OCRv3 model by default(`--ocr_version PP-OCRv3`). More whl package usage can be found in [whl package](./whl_en.md)
 <a name="212-multi-language-model"></a>
 
 #### 2.1.2 Multi-language Model
 
-Paddleocr currently supports 80 languages, which can be switched by modifying the `--lang` parameter. PP-OCRv3 currently only supports Chinese and English models, and other multilingual models will be updated one after another.
+PaddleOCR currently supports 80 languages, which can be switched by modifying the `--lang` parameter.
 
 ``` bash
-paddleocr --image_dir ./doc/imgs_en/254.jpg --lang=en --rec_image_shape 3,48,320
+paddleocr --image_dir ./doc/imgs_en/254.jpg --lang=en
 ```
 
 <div align="center">
@@ -154,48 +152,7 @@ Commonly used multilingual abbreviations include
 | Chinese Traditional | chinese_cht  |      | Italian  | it           |      | Russian  | ru           |
 
 A list of all languages and their corresponding abbreviations can be found in [Multi-Language Model Tutorial](./multi_languages_en.md)
-<a name="213-layoutAnalysis"></a>
-
-#### 2.1.3 Layout Analysis
-
-Layout analysis refers to the division of 5 types of areas of the document, including text, title, list, picture and table. For the first three types of regions, directly use the OCR model to complete the text detection and recognition of the corresponding regions, and save the results in txt. For the table area, after the table structuring process, the table picture is converted into an Excel file of the same table style. The picture area will be individually cropped into an image.
-
-To use the layout analysis function of PaddleOCR, you need to specify `--type=structure`
-
-```bash
-paddleocr --image_dir=../doc/table/1.png --type=structure
-```
-
-- **Results Format**
-
-  The returned results of PP-Structure is a list composed of a dict, an example is as follows
-
-  ```shell
-  [
-    {   'type': 'Text',
-        'bbox': [34, 432, 345, 462],
-        'res': ([[36.0, 437.0, 341.0, 437.0, 341.0, 446.0, 36.0, 447.0], [41.0, 454.0, 125.0, 453.0, 125.0, 459.0, 41.0, 460.0]],
-                  [('Tigure-6. The performance of CNN and IPT models using difforen', 0.90060663), ('Tent  ', 0.465441)])
-    }
-  ]
-  ```
-
-  The description of each field in dict is as follows
 
-  | Parameter | Description                                                  |
-  | --------- | ------------------------------------------------------------ |
-  | type      | Type of image area                                           |
-  | bbox      | The coordinates of the image area in the original image, respectively [left upper x, left upper y, right bottom x, right bottom y] |
-  | res       | OCR or table recognition result of image area。<br> Table: HTML string of the table; <br> OCR: A tuple containing the detection coordinates and recognition results of each single line of text |
-
-- **Parameter Description：**
-
-  | Parameter       | Description                                                  | Default value                                |
-  | --------------- | ------------------------------------------------------------ | -------------------------------------------- |
-  | output          | The path where excel and recognition results are saved       | ./output/table                               |
-  | table_max_len   | The long side of the image is resized in table structure model | 488                                          |
-  | table_model_dir | inference model path of table structure model                | None                                         |
-  | table_char_dict_path | dict path of table structure model                           | ../ppocr/utils/dict/table_structure_dict.txt |
 
 <a name="22-use-by-code"></a>
 
@@ -243,40 +200,12 @@ Visualization of results
 <div align="center">
     <img src="../imgs_results/whl/12_det_rec.jpg" width="800">
 </div>
-<a name="222-layoutAnalysis"></a>
-
-#### 2.2.2 Layout Analysis
-
-```python
-import os
-import cv2
-from paddleocr import PPStructure,draw_structure_result,save_structure_res
-
-table_engine = PPStructure(show_log=True)
-
-save_folder = './output/table'
-img_path = './table/1.png'
-img = cv2.imread(img_path)
-result = table_engine(img)
-save_structure_res(result, save_folder,os.path.basename(img_path).split('.')[0])
-
-for line in result:
-    line.pop('img')
-    print(line)
-
-from PIL import Image
 
-font_path = './fonts/simfang.ttf'
-image = Image.open(img_path).convert('RGB')
-im_show = draw_structure_result(image, result,font_path=font_path)
-im_show = Image.fromarray(im_show)
-im_show.save('result.jpg')
-```
 
 <a name="3"></a>
 
 ## 3. Summary
 
-In this section, you have mastered the use of PaddleOCR whl packages and obtained results.
+In this section, you have mastered the use of PaddleOCR whl package.
 
-PaddleOCR is a rich and practical OCR tool library that opens up the whole process of data, model training, compression and inference deployment, so in the [next section](./paddleOCR_overview_en.md) we will first introduce you to the overview of PaddleOCR, and then clone the PaddleOCR project to start the application journey of PaddleOCR.
+PaddleOCR is a rich and practical OCR tool library that get through the whole process of data production, model training, compression, inference and deployment, please refer to the [tutorials](../../README.md#tutorials) to start the journey of PaddleOCR.

doc/doc_en/update_en.md

 # RECENT UPDATES
+- 2022.5.7 Add support for metric and model logging during training to [Weights & Biases](https://docs.wandb.ai/).
 - 2021.12.21 OCR open source online course starts. The lesson starts at 8:30 every night and lasts for ten days. Free registration: https://aistudio.baidu.com/aistudio/course/introduce/25207
 - 2021.12.21 release PaddleOCR v2.4, release 1 text detection algorithm (PSENet), 3 text recognition algorithms (NRTR、SEED、SAR), 1 key information extraction algorithm (SDMGR) and 3 DocVQA algorithms (LayoutLM、LayoutLMv2，LayoutXLM).
 - 2021.9.7 release PaddleOCR v2.3, [PP-OCRv2](#PP-OCRv2) is proposed. The CPU inference speed of PP-OCRv2 is 220% higher than that of PP-OCR server. The F-score of PP-OCRv2 is 7% higher than that of PP-OCR mobile.

doc/doc_en/whl_en.md

@@ -172,11 +172,9 @@ show help information
 paddleocr -h
 ```
 
-**Note**: The whl package uses the `PP-OCRv3` model by default, and the input shape used by the recognition model is `3,48,320`, so if you use the recognition function, you need to add the parameter `--rec_image_shape 3,48,320`, if you do not use the default `PP- OCRv3` model, you do not need to set this parameter.
-
 * detection classification and recognition
 ```bash
-paddleocr --image_dir PaddleOCR/doc/imgs_en/img_12.jpg --use_angle_cls true --lang en --rec_image_shape 3,48,320
+paddleocr --image_dir PaddleOCR/doc/imgs_en/img_12.jpg --use_angle_cls true --lang en
 ```
 
 Output will be a list, each item contains bounding box, text and recognition confidence
@@ -189,7 +187,7 @@ Output will be a list, each item contains bounding box, text and recognition con
 
 * detection and recognition
 ```bash
-paddleocr --image_dir PaddleOCR/doc/imgs_en/img_12.jpg --lang en --rec_image_shape 3,48,320
+paddleocr --image_dir PaddleOCR/doc/imgs_en/img_12.jpg --lang en
 ```
 
 Output will be a list, each item contains bounding box, text and recognition confidence
@@ -202,7 +200,7 @@ Output will be a list, each item contains bounding box, text and recognition con
 
 * classification and recognition
 ```bash
-paddleocr --image_dir PaddleOCR/doc/imgs_words_en/word_10.png --use_angle_cls true --det false --lang en --rec_image_shape 3,48,320
+paddleocr --image_dir PaddleOCR/doc/imgs_words_en/word_10.png --use_angle_cls true --det false --lang en
 ```
 
 Output will be a list, each item contains text and recognition confidence
@@ -225,7 +223,7 @@ Output will be a list, each item only contains bounding box
 
 * only recognition
 ```bash
-paddleocr --image_dir PaddleOCR/doc/imgs_words_en/word_10.png --det false --lang en --rec_image_shape 3,48,320
+paddleocr --image_dir PaddleOCR/doc/imgs_words_en/word_10.png --det false --lang en
 ```
 
 Output will be a list, each item contains text and recognition confidence
@@ -368,4 +366,4 @@ im_show.save('result.jpg')
 | cls                     | Enable classification when `ppocr.ocr` func exec((Use use_angle_cls in command line mode to control whether to start classification in the forward direction)                                                                                                                                                                                                   | FALSE                    |
 | show_log                     | Whether to print log| FALSE                    |
 | type                     | Perform ocr or table structuring, the value is selected in ['ocr','structure']                                                                                                                                                                                             | ocr                    |
-| ocr_version                     | OCR Model version number, the current model support list is as follows: PP-OCRv3 support Chinese and English detection and recognition model and direction classifier model, PP-OCRv2 support Chinese detection and recognition model, PP-OCR support Chinese detection, recognition and direction classifier, multilingual recognition model | PP-OCRv3                 |
+| ocr_version                     | OCR Model version number, the current model support list is as follows: PP-OCRv3 supports Chinese and English detection, recognition, multilingual recognition, direction classifier models, PP-OCRv2 support Chinese detection and recognition model, PP-OCR support Chinese detection, recognition and direction classifier, multilingual recognition model | PP-OCRv3                 |

paddleocr.py

@@ -67,6 +67,10 @@ MODEL_URLS = {
                     'url':
                     'https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_det_infer.tar',
                 },
+                'ml': {
+                    'url':
+                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/Multilingual_PP-OCRv3_det_infer.tar'
+                }
             },
             'rec': {
                 'ch': {
@@ -79,6 +83,56 @@ MODEL_URLS = {
                     'https://paddleocr.bj.bcebos.com/PP-OCRv3/english/en_PP-OCRv3_rec_infer.tar',
                     'dict_path': './ppocr/utils/en_dict.txt'
                 },
+                'korean': {
+                    'url':
+                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/korean_PP-OCRv3_rec_infer.tar',
+                    'dict_path': './ppocr/utils/dict/korean_dict.txt'
+                },
+                'japan': {
+                    'url':
+                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/japan_PP-OCRv3_rec_infer.tar',
+                    'dict_path': './ppocr/utils/dict/japan_dict.txt'
+                },
+                'chinese_cht': {
+                    'url':
+                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/chinese_cht_PP-OCRv3_rec_infer.tar',
+                    'dict_path': './ppocr/utils/dict/chinese_cht_dict.txt'
+                },
+                'ta': {
+                    'url':
+                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/ta_PP-OCRv3_rec_infer.tar',
+                    'dict_path': './ppocr/utils/dict/ta_dict.txt'
+                },
+                'te': {
+                    'url':
+                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/te_PP-OCRv3_rec_infer.tar',
+                    'dict_path': './ppocr/utils/dict/te_dict.txt'
+                },
+                'ka': {
+                    'url':
+                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/ka_PP-OCRv3_rec_infer.tar',
+                    'dict_path': './ppocr/utils/dict/ka_dict.txt'
+                },
+                'latin': {
+                    'url':
+                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/latin_PP-OCRv3_rec_infer.tar',
+                    'dict_path': './ppocr/utils/dict/latin_dict.txt'
+                },
+                'arabic': {
+                    'url':
+                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/arabic_PP-OCRv3_rec_infer.tar',
+                    'dict_path': './ppocr/utils/dict/arabic_dict.txt'
+                },
+                'cyrillic': {
+                    'url':
+                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/cyrillic_PP-OCRv3_rec_infer.tar',
+                    'dict_path': './ppocr/utils/dict/cyrillic_dict.txt'
+                },
+                'devanagari': {
+                    'url':
+                    'https://paddleocr.bj.bcebos.com/PP-OCRv3/multilingual/devanagari_PP-OCRv3_rec_infer.tar',
+                    'dict_path': './ppocr/utils/dict/devanagari_dict.txt'
+                },
             },
             'cls': {
                 'ch': {
@@ -259,7 +313,7 @@ def parse_lang(lang):
         'af', 'az', 'bs', 'cs', 'cy', 'da', 'de', 'es', 'et', 'fr', 'ga', 'hr',
         'hu', 'id', 'is', 'it', 'ku', 'la', 'lt', 'lv', 'mi', 'ms', 'mt', 'nl',
         'no', 'oc', 'pi', 'pl', 'pt', 'ro', 'rs_latin', 'sk', 'sl', 'sq', 'sv',
-        'sw', 'tl', 'tr', 'uz', 'vi'
+        'sw', 'tl', 'tr', 'uz', 'vi', 'french', 'german'
     ]
     arabic_lang = ['ar', 'fa', 'ug', 'ur']
     cyrillic_lang = [
@@ -285,8 +339,10 @@ def parse_lang(lang):
         det_lang = "ch"
     elif lang == 'structure':
         det_lang = 'structure'
-    else:
+    elif lang in ["en", "latin"]:
         det_lang = "en"
+    else:
+        det_lang = "ml"
     return lang, det_lang
 
 
@@ -356,6 +412,10 @@ class PaddleOCR(predict_system.TextSystem):
         params.cls_model_dir, cls_url = confirm_model_dir_url(
             params.cls_model_dir,
             os.path.join(BASE_DIR, 'whl', 'cls'), cls_model_config['url'])
+        if params.ocr_version == 'PP-OCRv3':
+            params.rec_image_shape = "3, 48, 320"
+        else:
+            params.rec_image_shape = "3, 32, 320"
         # download model
         maybe_download(params.det_model_dir, det_url)
         maybe_download(params.rec_model_dir, rec_url)

ppocr/modeling/heads/rec_sar_head.py

@@ -99,8 +99,8 @@ class SAREncoder(nn.Layer):
         if valid_ratios is not None:
             valid_hf = []
             T = holistic_feat.shape[1]
-            for i, valid_ratio in enumerate(valid_ratios):
-                valid_step = min(T, math.ceil(T * valid_ratio)) - 1
+            for i in range(len(valid_ratios)):
+                valid_step = min(T, math.ceil(T * valid_ratios[i])) - 1
                 valid_hf.append(holistic_feat[i, valid_step, :])
             valid_hf = paddle.stack(valid_hf, axis=0)
         else:
@@ -252,8 +252,8 @@ class ParallelSARDecoder(BaseDecoder):
 
         if valid_ratios is not None:
             # cal mask of attention weight
-            for i, valid_ratio in enumerate(valid_ratios):
-                valid_width = min(w, math.ceil(w * valid_ratio))
+            for i in range(len(valid_ratios)):
+                valid_width = min(w, math.ceil(w * valid_ratios[i]))
                 if valid_width < w:
                     attn_weight[i, :, :, valid_width:, :] = float('-inf')
 

ppocr/utils/loggers/__init__.py

+from .vdl_logger import VDLLogger
+from .wandb_logger import WandbLogger
+from .loggers import Loggers

ppocr/utils/loggers/base_logger.py

+import os
+from abc import ABC, abstractmethod
+
+class BaseLogger(ABC):
+    def __init__(self, save_dir):
+        self.save_dir = save_dir
+        os.makedirs(self.save_dir, exist_ok=True)
+
+    @abstractmethod
+    def log_metrics(self, metrics, prefix=None):
+        pass
+
+    @abstractmethod
+    def close(self):
+        pass
\ No newline at end of file

ppocr/utils/loggers/loggers.py

+from .wandb_logger import WandbLogger
+
+class Loggers(object):
+    def __init__(self, loggers):
+        super().__init__()
+        self.loggers = loggers
+
+    def log_metrics(self, metrics, prefix=None, step=None):
+        for logger in self.loggers:
+            logger.log_metrics(metrics, prefix=prefix, step=step)
+    
+    def log_model(self, is_best, prefix, metadata=None):
+        for logger in self.loggers:
+            logger.log_model(is_best=is_best, prefix=prefix, metadata=metadata)
+    
+    def close(self):
+        for logger in self.loggers:
+            logger.close()
\ No newline at end of file

ppocr/utils/loggers/vdl_logger.py

+from .base_logger import BaseLogger
+from visualdl import LogWriter
+
+class VDLLogger(BaseLogger):
+    def __init__(self, save_dir):
+        super().__init__(save_dir)
+        self.vdl_writer = LogWriter(logdir=save_dir)
+
+    def log_metrics(self, metrics, prefix=None, step=None):
+        if not prefix:
+            prefix = ""
+        updated_metrics = {prefix + "/" + k: v for k, v in metrics.items()}
+
+        for k, v in updated_metrics.items():
+            self.vdl_writer.add_scalar(k, v, step)
+    
+    def log_model(self, is_best, prefix, metadata=None):
+        pass
+    
+    def close(self):
+        self.vdl_writer.close() 
\ No newline at end of file

ppocr/utils/loggers/wandb_logger.py

+import os
+from .base_logger import BaseLogger
+
+class WandbLogger(BaseLogger):
+    def __init__(self, 
+        project=None, 
+        name=None, 
+        id=None, 
+        entity=None, 
+        save_dir=None, 
+        config=None,
+        **kwargs):
+        try:
+            import wandb
+            self.wandb = wandb
+        except ModuleNotFoundError:
+            raise ModuleNotFoundError(
+                "Please install wandb using `pip install wandb`"
+                )
+
+        self.project = project
+        self.name = name
+        self.id = id
+        self.save_dir = save_dir
+        self.config = config
+        self.kwargs = kwargs
+        self.entity = entity
+        self._run = None
+        self._wandb_init = dict(
+            project=self.project,
+            name=self.name,
+            id=self.id,
+            entity=self.entity,
+            dir=self.save_dir,
+            resume="allow"
+        )
+        self._wandb_init.update(**kwargs)
+
+        _ = self.run
+
+        if self.config:
+            self.run.config.update(self.config)
+
+    @property
+    def run(self):
+        if self._run is None:
+            if self.wandb.run is not None:
+                logger.info(
+                    "There is a wandb run already in progress "
+                    "and newly created instances of `WandbLogger` will reuse"
+                    " this run. If this is not desired, call `wandb.finish()`"
+                    "before instantiating `WandbLogger`."
+                )
+                self._run = self.wandb.run
+            else:
+                self._run = self.wandb.init(**self._wandb_init)
+        return self._run
+
+    def log_metrics(self, metrics, prefix=None, step=None):
+        if not prefix:
+            prefix = ""
+        updated_metrics = {prefix.lower() + "/" + k: v for k, v in metrics.items()}
+        
+        self.run.log(updated_metrics, step=step)
+
+    def log_model(self, is_best, prefix, metadata=None):
+        model_path = os.path.join(self.save_dir, prefix + '.pdparams')
+        artifact = self.wandb.Artifact('model-{}'.format(self.run.id), type='model', metadata=metadata)
+        artifact.add_file(model_path, name="model_ckpt.pdparams")
+
+        aliases = [prefix]
+        if is_best:
+            aliases.append("best")
+
+        self.run.log_artifact(artifact, aliases=aliases)
+
+    def close(self):
+        self.run.finish()
\ No newline at end of file

tools/program.py

@@ -31,6 +31,7 @@ from ppocr.utils.stats import TrainingStats
 from ppocr.utils.save_load import save_model
 from ppocr.utils.utility import print_dict, AverageMeter
 from ppocr.utils.logging import get_logger
+from ppocr.utils.loggers import VDLLogger, WandbLogger, Loggers
 from ppocr.utils import profiler
 from ppocr.data import build_dataloader
 
@@ -161,7 +162,7 @@ def train(config,
           eval_class,
           pre_best_model_dict,
           logger,
-          vdl_writer=None,
+          log_writer=None,
           scaler=None):
     cal_metric_during_train = config['Global'].get('cal_metric_during_train',
                                                    False)
@@ -300,10 +301,8 @@ def train(config,
             stats['lr'] = lr
             train_stats.update(stats)
 
-            if vdl_writer is not None and dist.get_rank() == 0:
-                for k, v in train_stats.get().items():
-                    vdl_writer.add_scalar('TRAIN/{}'.format(k), v, global_step)
-                vdl_writer.add_scalar('TRAIN/lr', lr, global_step)
+            if log_writer is not None and dist.get_rank() == 0:
+                log_writer.log_metrics(metrics=train_stats.get(), prefix="TRAIN", step=global_step)
 
             if dist.get_rank() == 0 and (
                 (global_step > 0 and global_step % print_batch_step == 0) or
@@ -349,11 +348,9 @@ def train(config,
                 logger.info(cur_metric_str)
 
                 # logger metric
-                if vdl_writer is not None:
-                    for k, v in cur_metric.items():
-                        if isinstance(v, (float, int)):
-                            vdl_writer.add_scalar('EVAL/{}'.format(k),
-                                                  cur_metric[k], global_step)
+                if log_writer is not None:
+                    log_writer.log_metrics(metrics=cur_metric, prefix="EVAL", step=global_step)
+
                 if cur_metric[main_indicator] >= best_model_dict[
                         main_indicator]:
                     best_model_dict.update(cur_metric)
@@ -374,10 +371,12 @@ def train(config,
                 ]))
                 logger.info(best_str)
                 # logger best metric
-                if vdl_writer is not None:
-                    vdl_writer.add_scalar('EVAL/best_{}'.format(main_indicator),
-                                          best_model_dict[main_indicator],
-                                          global_step)
+                if log_writer is not None:
+                    log_writer.log_metrics(metrics={
+                        "best_{}".format(main_indicator): best_model_dict[main_indicator]
+                        }, prefix="EVAL", step=global_step)
+                    
+                    log_writer.log_model(is_best=True, prefix="best_accuracy", metadata=best_model_dict)
 
             reader_start = time.time()
         if dist.get_rank() == 0:
@@ -392,6 +391,10 @@ def train(config,
                 best_model_dict=best_model_dict,
                 epoch=epoch,
                 global_step=global_step)
+
+            if log_writer is not None:
+                log_writer.log_model(is_best=False, prefix="latest")
+
         if dist.get_rank() == 0 and epoch > 0 and epoch % save_epoch_step == 0:
             save_model(
                 model,
@@ -404,11 +407,14 @@ def train(config,
                 best_model_dict=best_model_dict,
                 epoch=epoch,
                 global_step=global_step)
+            if log_writer is not None:
+                log_writer.log_model(is_best=False, prefix='iter_epoch_{}'.format(epoch))
+
     best_str = 'best metric, {}'.format(', '.join(
         ['{}: {}'.format(k, v) for k, v in best_model_dict.items()]))
     logger.info(best_str)
-    if dist.get_rank() == 0 and vdl_writer is not None:
-        vdl_writer.close()
+    if dist.get_rank() == 0 and log_writer is not None:
+        log_writer.close()
     return
 
 
@@ -565,15 +571,32 @@ def preprocess(is_train=False):
 
     config['Global']['distributed'] = dist.get_world_size() != 1
 
-    if config['Global']['use_visualdl'] and dist.get_rank() == 0:
-        from visualdl import LogWriter
+    loggers = []
+
+    if 'use_visualdl' in config['Global'] and config['Global']['use_visualdl']:
         save_model_dir = config['Global']['save_model_dir']
         vdl_writer_path = '{}/vdl/'.format(save_model_dir)
-        os.makedirs(vdl_writer_path, exist_ok=True)
-        vdl_writer = LogWriter(logdir=vdl_writer_path)
+        log_writer = VDLLogger(save_model_dir)
+        loggers.append(log_writer)
+    if ('use_wandb' in config['Global'] and config['Global']['use_wandb']) or 'wandb' in config:
+        save_dir = config['Global']['save_model_dir']
+        wandb_writer_path = "{}/wandb".format(save_dir)
+        if "wandb" in config:
+            wandb_params = config['wandb']
+        else:
+            wandb_params = dict()
+        wandb_params.update({'save_dir': save_model_dir})
+        log_writer = WandbLogger(**wandb_params, config=config)
+        loggers.append(log_writer)
     else:
-        vdl_writer = None
+        log_writer = None
     print_dict(config, logger)
+
+    if loggers:
+        log_writer = Loggers(loggers)
+    else:
+        log_writer = None
+
     logger.info('train with paddle {} and device {}'.format(paddle.__version__,
                                                             device))
-    return config, device, logger, vdl_writer
+    return config, device, logger, log_writer