This is a combination of 59 commits from v2.7.0 to v2.7.1 in (#11831)

release/2.7.1 branch

Co-authored-by: ToddBear <43341135+ToddBear@users.noreply.github.com>

.github/ISSUE_TEMPLATE/newfeature.md

@@ -0,0 +1,17 @@
+---
+name: New Feature Issue template
+about: Issue template for new features.
+title: ''
+labels: 'Code PR is needed'
+assignees: 'shiyutang'
+
+---
+
+## 背景
+
+经过需求征集https://github.com/PaddlePaddle/PaddleOCR/issues/10334 和每周技术研讨会 https://github.com/PaddlePaddle/PaddleOCR/issues/10223 讨论，我们确定了XXXX任务。
+
+## 解决步骤
+1. 根据开源代码进行网络结构、评估指标转换。代码链接：XXXX
+2. 结合[论文复现指南](https://github.com/PaddlePaddle/models/blob/release%2F2.2/tutorials/article-implementation/ArticleReproduction_CV.md)，进行前反向对齐等操作，达到论文Table.1中的指标。
+3. 参考[PR提交规范](https://github.com/PaddlePaddle/PaddleOCR/blob/release/2.6/doc/doc_ch/code_and_doc.md)提交代码PR到ppocr中。

.pre-commit-config.yaml

@@ -40,4 +40,3 @@ repos:
     hooks:
     -   id: ruff
         args: [--fix, --exit-non-zero-on-fix, --no-cache]
-

PPOCRLabel/gen_ocr_train_val_test.py

@@ -17,48 +17,43 @@ def isCreateOrDeleteFolder(path, flag):
     return flagAbsPath
 
 
-def splitTrainVal(root, absTrainRootPath, absValRootPath, absTestRootPath, trainTxt, valTxt, testTxt, flag):
-    # 按照指定的比例划分训练集、验证集、测试集
-    dataAbsPath = os.path.abspath(root)
-
-    if flag == "det":
-        labelFilePath = os.path.join(dataAbsPath, args.detLabelFileName)
-    elif flag == "rec":
-        labelFilePath = os.path.join(dataAbsPath, args.recLabelFileName)
-
-    labelFileRead = open(labelFilePath, "r", encoding="UTF-8")
-    labelFileContent = labelFileRead.readlines()
-    random.shuffle(labelFileContent)
-    labelRecordLen = len(labelFileContent)
-
-    for index, labelRecordInfo in enumerate(labelFileContent):
-        imageRelativePath = labelRecordInfo.split('\t')[0]
-        imageLabel = labelRecordInfo.split('\t')[1]
-        imageName = os.path.basename(imageRelativePath)
-
-        if flag == "det":
-            imagePath = os.path.join(dataAbsPath, imageName)
-        elif flag == "rec":
-            imagePath = os.path.join(dataAbsPath, "{}\\{}".format(args.recImageDirName, imageName))
-
-        # 按预设的比例划分训练集、验证集、测试集
-        trainValTestRatio = args.trainValTestRatio.split(":")
-        trainRatio = eval(trainValTestRatio[0]) / 10
-        valRatio = trainRatio + eval(trainValTestRatio[1]) / 10
-        curRatio = index / labelRecordLen
-
-        if curRatio < trainRatio:
-            imageCopyPath = os.path.join(absTrainRootPath, imageName)
-            shutil.copy(imagePath, imageCopyPath)
-            trainTxt.write("{}\t{}".format(imageCopyPath, imageLabel))
-        elif curRatio >= trainRatio and curRatio < valRatio:
-            imageCopyPath = os.path.join(absValRootPath, imageName)
-            shutil.copy(imagePath, imageCopyPath)
-            valTxt.write("{}\t{}".format(imageCopyPath, imageLabel))
-        else:
-            imageCopyPath = os.path.join(absTestRootPath, imageName)
-            shutil.copy(imagePath, imageCopyPath)
-            testTxt.write("{}\t{}".format(imageCopyPath, imageLabel))
+def splitTrainVal(root, abs_train_root_path, abs_val_root_path, abs_test_root_path, train_txt, val_txt, test_txt, flag):
+
+    data_abs_path = os.path.abspath(root)
+    label_file_name = args.detLabelFileName if flag == "det" else args.recLabelFileName
+    label_file_path = os.path.join(data_abs_path, label_file_name)
+
+    with open(label_file_path, "r", encoding="UTF-8") as label_file:
+        label_file_content = label_file.readlines()
+        random.shuffle(label_file_content)
+        label_record_len = len(label_file_content)
+
+        for index, label_record_info in enumerate(label_file_content):
+            image_relative_path, image_label = label_record_info.split('\t')
+            image_name = os.path.basename(image_relative_path)
+
+            if flag == "det":
+                image_path = os.path.join(data_abs_path, image_name)
+            elif flag == "rec":
+                image_path = os.path.join(data_abs_path, args.recImageDirName, image_name)
+
+            train_val_test_ratio = args.trainValTestRatio.split(":")
+            train_ratio = eval(train_val_test_ratio[0]) / 10
+            val_ratio = train_ratio + eval(train_val_test_ratio[1]) / 10
+            cur_ratio = index / label_record_len
+
+            if cur_ratio < train_ratio:
+                image_copy_path = os.path.join(abs_train_root_path, image_name)
+                shutil.copy(image_path, image_copy_path)
+                train_txt.write("{}\t{}\n".format(image_copy_path, image_label))
+            elif cur_ratio >= train_ratio and cur_ratio < val_ratio:
+                image_copy_path = os.path.join(abs_val_root_path, image_name)
+                shutil.copy(image_path, image_copy_path)
+                val_txt.write("{}\t{}\n".format(image_copy_path, image_label))
+            else:
+                image_copy_path = os.path.join(abs_test_root_path, image_name)
+                shutil.copy(image_path, image_copy_path)
+                test_txt.write("{}\t{}\n".format(image_copy_path, image_label))
 
 
 # 删掉存在的文件
@@ -148,4 +143,4 @@ def genDetRecTrainVal(args):
         help="the name of the folder where the cropped recognition dataset is located"
     )
     args = parser.parse_args()
-    genDetRecTrainVal(args)
+    genDetRecTrainVal(args)

README.md

@@ -68,12 +68,10 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力
 
 <a name="技术交流合作"></a>
 ## 📖 技术交流合作
-
-- 飞桨低代码开发工具（PaddleX）—— 面向国内外主流AI硬件的飞桨精选模型一站式开发工具。包含如下核心优势：
-  - 【产业高精度模型库】：覆盖10个主流AI任务 40+精选模型，丰富齐全。
-  - 【特色模型产线】：提供融合大小模型的特色模型产线，精度更高，效果更好。
-  - 【低代码开发模式】：图形化界面支持统一开发范式，便捷高效。
-  - 【私有化部署多硬件支持】：适配国内外主流AI硬件，支持本地纯离线使用，满足企业安全保密需要。
+- 飞桨AI套件([PaddleX](http://10.136.157.23:8080/paddle/paddleX))提供了飞桨模型训压推一站式全流程高效率开发平台，其使命是助力AI技术快速落地，愿景是使人人成为AI Developer！
+   - PaddleX 目前覆盖图像分类、目标检测、图像分割、3D、OCR和时序预测等领域方向，已内置了36种基础单模型，例如RT-DETR、PP-YOLOE、PP-HGNet、PP-LCNet、PP-LiteSeg等；集成了12种实用的产业方案，例如PP-OCRv4、PP-ChatOCR、PP-ShiTu、PP-TS、车载路面垃圾检测、野生动物违禁制品识别等。
+   - PaddleX 提供了“工具箱”和“开发者”两种AI开发模式。工具箱模式可以无代码调优关键超参，开发者模式可以低代码进行单模型训压推和多模型串联推理，同时支持云端和本地端。
+   - PaddleX 还支持联创开发，利润分成！目前 PaddleX 正在快速迭代，欢迎广大的个人开发者和企业开发者参与进来，共创繁荣的 AI 技术生态！
 
 - PaddleX官网地址：https://aistudio.baidu.com/intro/paddlex