merge upstream

README_ch.md

@@ -140,11 +140,7 @@ PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库，助力
     - [文本识别算法](./doc/doc_ch/algorithm_overview.md#12-%E6%96%87%E6%9C%AC%E8%AF%86%E5%88%AB%E7%AE%97%E6%B3%95)
     - [端到端算法](./doc/doc_ch/algorithm_overview.md#2-%E6%96%87%E6%9C%AC%E8%AF%86%E5%88%AB%E7%AE%97%E6%B3%95)
     - [使用PaddleOCR架构添加新算法](./doc/doc_ch/add_new_algorithm.md)
-- [场景应用](./doc/doc_ch/application.md)
-    - [金融场景（表单/票据等）]()
-    - [工业场景（电表度数/车牌等）]()
-    - [教育场景（手写体/公式等）]()
-    - [医疗场景（化验单等）]()
+- [场景应用](./applications)
 - 数据标注与合成
     - [半自动标注工具PPOCRLabel](./PPOCRLabel/README_ch.md)
     - [数据合成工具Style-Text](./StyleText/README_ch.md)

doc/doc_ch/application.md

@@ -1 +0,0 @@
-# 场景应用

doc/doc_en/ocr_book_en.md

@@ -1,6 +1,6 @@
 # E-book: *Dive Into OCR*
 
-"Dive Into OCR" is a textbook that combines OCR theory and practice, written by the PaddleOCR team, Chen Zhineng, a Junior Research Fellow at Fudan University, Huang Wenhui, a senior expert in the field of vision at China Mobile Research Institute, and other industry-university-research colleagues, as well as OCR developers. The main features are as follows:
+"Dive Into OCR" is a textbook that combines OCR theory and practice, written by the PaddleOCR team, Chen Zhineng, a Pre-tenure Professor at Fudan University, Huang Wenhui, a senior expert in the field of vision at China Mobile Research Institute, and other industry-university-research colleagues, as well as OCR developers. The main features are as follows:
 
 - OCR full-stack technology covering text detection, recognition and document analysis
 - Closely integrate theory and practice, cross the code implementation gap, and supporting instructional videos

paddleocr.py

@@ -47,8 +47,8 @@ __all__ = [
 ]
 
 SUPPORT_DET_MODEL = ['DB']
-VERSION = '2.5.0.1'
-SUPPORT_REC_MODEL = ['CRNN']
+VERSION = '2.5.0.3'
+SUPPORT_REC_MODEL = ['CRNN', 'SVTR_LCNet']
 BASE_DIR = os.path.expanduser("~/.paddleocr/")
 
 DEFAULT_OCR_MODEL_VERSION = 'PP-OCRv3'

tools/infer/utility.py

@@ -79,7 +79,7 @@ def init_args():
     parser.add_argument("--det_fce_box_type", type=str, default='poly')
 
     # params for text recognizer
-    parser.add_argument("--rec_algorithm", type=str, default='CRNN')
+    parser.add_argument("--rec_algorithm", type=str, default='SVTR_LCNet')
     parser.add_argument("--rec_model_dir", type=str)
     parser.add_argument("--rec_image_shape", type=str, default="3, 48, 320")
     parser.add_argument("--rec_batch_num", type=int, default=6)
@@ -269,11 +269,11 @@ def create_predictor(args, mode, logger):
                 max_input_shape.update(max_pact_shape)
                 opt_input_shape.update(opt_pact_shape)
             elif mode == "rec":
-                if args.rec_algorithm != "CRNN":
+                if args.rec_algorithm not in ["CRNN", "SVTR_LCNet"]:
                     use_dynamic_shape = False
                 imgH = int(args.rec_image_shape.split(',')[-2])
                 min_input_shape = {"x": [1, 3, imgH, 10]}
-                max_input_shape = {"x": [args.rec_batch_num, 3, imgH, 1536]}
+                max_input_shape = {"x": [args.rec_batch_num, 3, imgH, 2304]}
                 opt_input_shape = {"x": [args.rec_batch_num, 3, imgH, 320]}
             elif mode == "cls":
                 min_input_shape = {"x": [1, 3, 48, 10]}
@@ -320,7 +320,7 @@ def create_predictor(args, mode, logger):
 def get_output_tensors(args, mode, predictor):
     output_names = predictor.get_output_names()
     output_tensors = []
-    if mode == "rec" and args.rec_algorithm == "CRNN":
+    if mode == "rec" and args.rec_algorithm in ["CRNN", "SVTR_LCNet"]:
         output_name = 'softmax_0.tmp_0'
         if output_name in output_names:
             return [predictor.get_output_handle(output_name)]