[Fix] Being more conservative on Dataset Preparer (#1520)

* [Fix] Being more conservative on Dataset Preparer

* update

configs/textdet/_base_/datasets/icdar2015.py

@@ -1,15 +1,17 @@
-ic15_det_data_root = 'data/icdar2015'
+ic15_det_data_root = 'data/det/icdar2015'
 
 ic15_det_train = dict(
     type='OCRDataset',
     data_root=ic15_det_data_root,
-    ann_file='textdet_train.json',
+    ann_file='instances_training.json',
+    data_prefix=dict(img_path='imgs/'),
     filter_cfg=dict(filter_empty_gt=True, min_size=32),
     pipeline=None)
 
 ic15_det_test = dict(
     type='OCRDataset',
     data_root=ic15_det_data_root,
-    ann_file='textdet_test.json',
+    ann_file='instances_test.json',
+    data_prefix=dict(img_path='imgs/'),
     test_mode=True,
     pipeline=None)

configs/textrecog/_base_/datasets/icdar2015.py

@@ -1,15 +1,15 @@
-ic15_rec_data_root = 'data/icdar2015/'
+ic15_rec_data_root = 'data/rec/icdar_2015/'
 
 ic15_rec_train = dict(
     type='OCRDataset',
     data_root=ic15_rec_data_root,
-    ann_file='textrecog_train.json',
+    ann_file='train_labels.json',
     test_mode=False,
     pipeline=None)
 
 ic15_rec_test = dict(
     type='OCRDataset',
     data_root=ic15_rec_data_root,
-    ann_file='textrecog_test.json',
+    ann_file='test_labels.json',
     test_mode=True,
     pipeline=None)

docs/en/user_guides/data_prepare/dataset_preparer.md

@@ -1,4 +1,9 @@
-# Dataset Preparer
+# Dataset Preparer (Beta)
+
+```{note}
+Dataset Preparer is still in beta version and might not be stable enough. You
+are welcome to try it out and report any issues to us.
+```
 
 ## One-click data preparation script
 

docs/en/user_guides/data_prepare/det.md

@@ -1,6 +1,6 @@
-# Text Detection\[Deprecated\]
+# Text Detection
 
-```{warning}
+```{note}
 This page is deprecated and all these scripts will be eventually migrated into dataset preparer, a brand new module designed to ease these lengthy dataset preparation steps. [Check it out](./dataset_preparer.md)!
 ```
 

docs/en/user_guides/data_prepare/kie.md

@@ -1,6 +1,6 @@
-# Key Information Extraction\[Deprecated\]
+# Key Information Extraction
 
-```{warning}
+```{note}
 This page is deprecated and all these scripts will be eventually migrated into dataset preparer, a brand new module designed to ease these lengthy dataset preparation steps. [Check it out](./dataset_preparer.md)!
 ```
 

docs/en/user_guides/data_prepare/recog.md

@@ -1,6 +1,6 @@
-# Text Recognition\[Deprecated\]
+# Text Recognition
 
-```{warning}
+```{note}
 This page is deprecated and all these scripts will be eventually migrated into dataset preparer, a brand new module designed to ease these lengthy dataset preparation steps. [Check it out](./dataset_preparer.md)!
 ```
 

docs/zh_cn/user_guides/data_prepare/dataset_preparer.md

@@ -1,4 +1,8 @@
-# 数据准备
+# 数据准备 (Beta)
+
+```{note}
+Dataset Preparer 目前仍处在公测阶段，欢迎尝鲜试用！如遇到任何问题，请及时向我们反馈。
+```
 
 ## 一键式数据准备脚本
 

docs/zh_cn/user_guides/data_prepare/det.md

@@ -1,6 +1,6 @@
-# 文字检测\[过时\]
+# 文字检测
 
-```{warning}
+```{note}
 该页面内容已经过时，所有有关数据格式转换相关的脚本都将最终迁移至数据准备器 **dataset preparer**，这个全新设计的模块能够极大地方便用户完成冗长的数据准备步骤，详见[相关文档](./dataset_preparer.md)。
 ```
 

docs/zh_cn/user_guides/data_prepare/kie.md

@@ -1,6 +1,6 @@
-# 关键信息提取\[过时\]
+# 关键信息提取
 
-```{warning}
+```{note}
 该页面内容已经过时，所有有关数据格式转换相关的脚本都将最终迁移至数据准备器 **dataset preparer**，这个全新设计的模块能够极大地方便用户完成冗长的数据准备步骤，详见[相关文档](./dataset_preparer.md)。
 ```
 

docs/zh_cn/user_guides/data_prepare/recog.md

@@ -1,6 +1,6 @@
-# 文字识别\[过时\]
+# 文字识别
 
-```{warning}
+```{note}
 该页面内容已经过时，所有有关数据格式转换相关的脚本都将最终迁移至数据准备器 **dataset preparer**，这个全新设计的模块能够极大地方便用户完成冗长的数据准备步骤，详见[相关文档](./dataset_preparer.md)。
 ```
 

mmocr/datasets/preparers/data_converter.py

@@ -119,14 +119,21 @@ class BaseDataConverter:
             return
         cfg_path = osp.join(self.config_path, self.task, '_base_', 'datasets',
                             f'{self.dataset_name}.py')
-        if not osp.exists(cfg_path):
-            with open(cfg_path, 'w') as f:
-                f.write(
-                    f'{self.dataset_name}_{self.task}_data_root = \'{self.data_root}\'\n'  # noqa: E501
-                )
-            for split in self.splits:
-                with open(cfg_path, 'a') as f:
-                    f.write(dataset_config[split])
+        if osp.exists(cfg_path):
+            while True:
+                c = input(f'{cfg_path} already exists, overwrite? (Y/n) ') \
+                    or 'Y'
+                if c.lower() == 'y':
+                    break
+                if c.lower() == 'n':
+                    return
+        with open(cfg_path, 'w') as f:
+            f.write(
+                f'{self.dataset_name}_{self.task}_data_root = \'{self.data_root}\'\n'  # noqa: E501
+            )
+        for split in self.splits:
+            with open(cfg_path, 'a') as f:
+                f.write(dataset_config[split])
 
     @abstractmethod
     def pack_instance(self, sample: Tuple, split: str) -> Dict: