update nrtr metric

doc/doc_ch/algorithm_overview.md

@@ -44,7 +44,7 @@ PaddleOCR基于动态图开源的文本识别算法列表：
 - [x]  STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html))[11]
 - [x]  RARE([paper](https://arxiv.org/abs/1603.03915v1))[12]
 - [x]  SRN([paper](https://arxiv.org/abs/2003.12294))[5]
-- [x]  NRTR([paper](https://arxiv.org/abs/1806.00926v2)
+- [x]  NRTR([paper](https://arxiv.org/abs/1806.00926v2))
 
 参考[DTRB][3](https://arxiv.org/abs/1904.01906)文字识别训练和评估流程，使用MJSynth和SynthText两个文字识别数据集训练，在IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE数据集上进行评估，算法效果如下：
 
@@ -59,7 +59,7 @@ PaddleOCR基于动态图开源的文本识别算法列表：
 |RARE|MobileNetV3|82.5%|rec_mv3_tps_bilstm_att |[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_tps_bilstm_att_v2.0_train.tar)|
 |RARE|Resnet34_vd|83.6%|rec_r34_vd_tps_bilstm_att |[下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_tps_bilstm_att_v2.0_train.tar)|
 |SRN|Resnet50_vd_fpn| 88.52% | rec_r50fpn_vd_none_srn | [下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r50_vd_srn_train.tar) |
-|NRTR|NRTR_MTB| 84.1% | rec_mtb_nrtr | [下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mtb_nrtr_train.tar) |
+|NRTR|NRTR_MTB| 84.3% | rec_mtb_nrtr | [下载链接](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mtb_nrtr_train.tar) |
 
 
 PaddleOCR文本识别算法的训练和使用请参考文档教程中[模型训练/评估中的文本识别部分](./recognition.md)。

doc/doc_en/algorithm_overview_en.md

@@ -46,6 +46,7 @@ PaddleOCR open-source text recognition algorithms list:
 - [x]  STAR-Net([paper](http://www.bmva.org/bmvc/2016/papers/paper043/index.html))[11]
 - [x]  RARE([paper](https://arxiv.org/abs/1603.03915v1))[12]
 - [x]  SRN([paper](https://arxiv.org/abs/2003.12294))[5]
+- [x]  NRTR([paper](https://arxiv.org/abs/1806.00926v2))
 
 Refer to [DTRB](https://arxiv.org/abs/1904.01906), the training and evaluation result of these above text recognition (using MJSynth and SynthText for training, evaluate on IIIT, SVT, IC03, IC13, IC15, SVTP, CUTE) is as follow:
 
@@ -60,6 +61,6 @@ Refer to [DTRB](https://arxiv.org/abs/1904.01906), the training and evaluation r
 |RARE|MobileNetV3|82.5%|rec_mv3_tps_bilstm_att |[Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mv3_tps_bilstm_att_v2.0_train.tar)|
 |RARE|Resnet34_vd|83.6%|rec_r34_vd_tps_bilstm_att |[Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r34_vd_tps_bilstm_att_v2.0_train.tar)|
 |SRN|Resnet50_vd_fpn| 88.52% | rec_r50fpn_vd_none_srn |[Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_r50_vd_srn_train.tar)|
-|NRTR|NRTR_MTB| 84.1% | rec_mtb_nrtr | [Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mtb_nrtr_train.tar) |
+|NRTR|NRTR_MTB| 84.3% | rec_mtb_nrtr | [Download link](https://paddleocr.bj.bcebos.com/dygraph_v2.0/en/rec_mtb_nrtr_train.tar) |
 
 Please refer to the document for training guide and use of PaddleOCR text recognition algorithms [Text recognition model training/evaluation/prediction](./recognition_en.md)

ppocr/modeling/necks/__init__.py

@@ -21,7 +21,7 @@ def build_neck(config):
     from .sast_fpn import SASTFPN
     from .rnn import SequenceEncoder
     from .pg_fpn import PGFPN
-    support_dict = ['DBFPN', 'EASTFPN', 'SASTFPN', 'SequenceEncoder', 'PGFPN','TFEncoder']
+    support_dict = ['DBFPN', 'EASTFPN', 'SASTFPN', 'SequenceEncoder', 'PGFPN']
 
     module_name = config.pop('name')
     assert module_name in support_dict, Exception('neck only support {}'.format(

tools/program.py

@@ -387,7 +387,7 @@ def preprocess(is_train=False):
     alg = config['Architecture']['algorithm']
     assert alg in [
         'EAST', 'DB', 'SAST', 'Rosetta', 'CRNN', 'STARNet', 'RARE', 'SRN',
-        'CLS', 'PGNet', 'Distillation','NRTR'
+        'CLS', 'PGNet', 'Distillation', 'NRTR'
     ]
 
     device = 'gpu:{}'.format(dist.ParallelEnv().dev_id) if use_gpu else 'cpu'