Merge branch 'dygraph' into pgnet-v1

doc/doc_ch/algorithm_overview.md

@@ -28,7 +28,9 @@ PaddleOCR开源的文本检测算法列表：
 | --- | --- | --- | --- | --- | --- |
 |SAST|ResNet50_vd|89.63%|78.44%|83.66%|[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_totaltext_v2.0_train.tar)|
 
-**说明：** SAST模型训练额外加入了icdar2013、icdar2017、COCO-Text、ArT等公开数据集进行调优。PaddleOCR用到的经过整理格式的英文公开数据集下载：[百度云地址](https://pan.baidu.com/s/12cPnZcVuV1zn5DOd4mqjVw) (提取码: 2bpi)
+**说明：** SAST模型训练额外加入了icdar2013、icdar2017、COCO-Text、ArT等公开数据集进行调优。PaddleOCR用到的经过整理格式的英文公开数据集下载：
+* [百度云地址](https://pan.baidu.com/s/12cPnZcVuV1zn5DOd4mqjVw) (提取码: 2bpi)
+* [Google Drive下载地址](https://drive.google.com/drive/folders/1ll2-XEVyCQLpJjawLDiRlvo_i4BqHCJe?usp=sharing)
 
 PaddleOCR文本检测算法的训练和使用请参考文档教程中[模型训练/评估中的文本检测部分](./detection.md)。
 

doc/doc_en/algorithm_overview_en.md

@@ -31,7 +31,9 @@ On Total-Text dataset, the text detection result is as follows:
 | --- | --- | --- | --- | --- | --- |
 |SAST|ResNet50_vd|89.63%|78.44%|83.66%|[Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/det_r50_vd_sast_totaltext_v2.0_train.tar)|
 
-**Note：** Additional data, like icdar2013, icdar2017, COCO-Text, ArT, was added to the model training of SAST. Download English public dataset in organized format used by PaddleOCR from [Baidu Drive](https://pan.baidu.com/s/12cPnZcVuV1zn5DOd4mqjVw) (download code: 2bpi).
+**Note：** Additional data, like icdar2013, icdar2017, COCO-Text, ArT, was added to the model training of SAST. Download English public dataset in organized format used by PaddleOCR from:
+* [Baidu Drive](https://pan.baidu.com/s/12cPnZcVuV1zn5DOd4mqjVw) (download code: 2bpi).
+* [Google Drive](https://drive.google.com/drive/folders/1ll2-XEVyCQLpJjawLDiRlvo_i4BqHCJe?usp=sharing)
 
 For the training guide and use of PaddleOCR text detection algorithms, please refer to the document [Text detection model training/evaluation/prediction](./detection_en.md)
 

paddleocr.py

@@ -236,7 +236,9 @@ class PaddleOCR(predict_system.TextSystem):
         assert lang in model_urls[
             'rec'], 'param lang must in {}, but got {}'.format(
                 model_urls['rec'].keys(), lang)
+        use_inner_dict = False
         if postprocess_params.rec_char_dict_path is None:
+            use_inner_dict = True
             postprocess_params.rec_char_dict_path = model_urls['rec'][lang][
                 'dict_path']
 
@@ -263,7 +265,7 @@ class PaddleOCR(predict_system.TextSystem):
         if postprocess_params.rec_algorithm not in SUPPORT_REC_MODEL:
             logger.error('rec_algorithm must in {}'.format(SUPPORT_REC_MODEL))
             sys.exit(0)
-
+        if use_inner_dict:
             postprocess_params.rec_char_dict_path = str(
                 Path(__file__).parent / postprocess_params.rec_char_dict_path)
 
@@ -282,8 +284,13 @@ class PaddleOCR(predict_system.TextSystem):
         if isinstance(img, list) and det == True:
             logger.error('When input a list of images, det must be false')
             exit(0)
+        if cls == False:
+            self.use_angle_cls = False
+        elif cls == True and self.use_angle_cls == False:
+            logger.warning(
+                'Since the angle classifier is not initialized, the angle classifier will not be uesd during the forward process'
+            )
 
-        self.use_angle_cls = cls
         if isinstance(img, str):
             # download net image
             if img.startswith('http'):

ppocr/modeling/heads/rec_att_head.py

@@ -38,7 +38,7 @@ class AttentionHead(nn.Layer):
         return input_ont_hot
 
     def forward(self, inputs, targets=None, batch_max_length=25):
-        batch_size = inputs.shape[0]
+        batch_size = paddle.shape(inputs)[0]
         num_steps = batch_max_length
 
         hidden = paddle.zeros((batch_size, self.hidden_size))

setup.py

@@ -32,7 +32,7 @@ setup(
     package_dir={'paddleocr': ''},
     include_package_data=True,
     entry_points={"console_scripts": ["paddleocr= paddleocr.paddleocr:main"]},
-    version='2.0.2',
+    version='2.0.3',
     install_requires=requirements,
     license='Apache License 2.0',
     description='Awesome OCR toolkits based on PaddlePaddle （8.6M ultra-lightweight pre-trained model, support training and deployment among server, mobile, embeded and IoT devices',