From 8fc03fa9217c2d92ed3e3eebfa0db1503a47fe49 Mon Sep 17 00:00:00 2001 From: andyj <87074272+andyjpaddle@users.noreply.github.com> Date: Wed, 19 Oct 2022 17:24:14 +0800 Subject: [PATCH] [CP]update visionlan (#7991) * update visionlan * update visionlan --- doc/doc_ch/algorithm_overview.md | 6 +++--- doc/doc_ch/algorithm_rec_visionlan.md | 4 ++-- doc/doc_en/algorithm_overview_en.md | 6 +++--- doc/doc_en/algorithm_rec_visionlan_en.md | 4 ++-- ppocr/data/imaug/label_ops.py | 7 ------- ppocr/postprocess/rec_postprocess.py | 7 ------- 6 files changed, 10 insertions(+), 24 deletions(-) diff --git a/doc/doc_ch/algorithm_overview.md b/doc/doc_ch/algorithm_overview.md index ecb0e9df..dd21f4ed 100755 --- a/doc/doc_ch/algorithm_overview.md +++ b/doc/doc_ch/algorithm_overview.md @@ -99,9 +99,9 @@ PaddleOCR将**持续新增**支持OCR领域前沿算法与模型，**欢迎广 |SVTR|SVTR-Tiny| 89.25% | rec_svtr_tiny_none_ctc_en | [训练模型](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/rec_svtr_tiny_none_ctc_en_train.tar) | |ViTSTR|ViTSTR| 79.82% | rec_vitstr_none_ce | [训练模型](https://paddleocr.bj.bcebos.com/rec_vitstr_none_ce_train.tar) | |ABINet|Resnet45| 90.75% | rec_r45_abinet | [训练模型](https://paddleocr.bj.bcebos.com/rec_r45_abinet_train.tar) | -|VisionLAN|Resnet45| 90.30% | rec_r45_visionlan | [训练模型](https://paddleocr.bj.bcebos.com/rec_r45_visionlan_train.tar) | -|SPIN|ResNet32| 90.00% | rec_r32_gaspin_bilstm_att | coming soon | -|RobustScanner|ResNet31| 87.77% | rec_r31_robustscanner | coming soon | +|VisionLAN|Resnet45| 90.30% | rec_r45_visionlan | [训练模型](https://paddleocr.bj.bcebos.com/VisionLAN/rec_r45_visionlan_train.tar) | +|SPIN|ResNet32| 90.00% | rec_r32_gaspin_bilstm_att | [训练模型](https://paddleocr.bj.bcebos.com/contribution/rec_r32_gaspin_bilstm_att.tar) | +|RobustScanner|ResNet31| 87.77% | rec_r31_robustscanner | [训练模型](https://paddleocr.bj.bcebos.com/contribution/rec_r31_robustscanner.tar)| diff --git a/doc/doc_ch/algorithm_rec_visionlan.md b/doc/doc_ch/algorithm_rec_visionlan.md index 84b5ef68..b4474c29 100644 --- a/doc/doc_ch/algorithm_rec_visionlan.md +++ b/doc/doc_ch/algorithm_rec_visionlan.md @@ -27,7 +27,7 @@ |模型|骨干网络|配置文件|Acc|下载链接| | --- | --- | --- | --- | --- | -|VisionLAN|ResNet45|[rec_r45_visionlan.yml](../../configs/rec/rec_r45_visionlan.yml)|90.3%|[预训练、训练模型](https://paddleocr.bj.bcebos.com/rec_r45_visionlan_train.tar)| +|VisionLAN|ResNet45|[rec_r45_visionlan.yml](../../configs/rec/rec_r45_visionlan.yml)|90.3%|[预训练、训练模型](https://paddleocr.bj.bcebos.com/VisionLAN/rec_r45_visionlan_train.tar)| ## 2. 环境配置 @@ -80,7 +80,7 @@ python3 tools/infer_rec.py -c configs/rec/rec_r45_visionlan.yml -o Global.infer_ ### 4.1 Python推理 -首先将训练得到best模型，转换成inference model。这里以训练完成的模型为例（[模型下载地址](https://paddleocr.bj.bcebos.com/rec_r45_visionlan_train.tar))，可以使用如下命令进行转换： +首先将训练得到best模型，转换成inference model。这里以训练完成的模型为例（[模型下载地址](https://paddleocr.bj.bcebos.com/VisionLAN/rec_r45_visionlan_train.tar))，可以使用如下命令进行转换： ```shell # 注意将pretrained_model的路径设置为本地路径。 diff --git a/doc/doc_en/algorithm_overview_en.md b/doc/doc_en/algorithm_overview_en.md index bca22f78..42ccbe93 100755 --- a/doc/doc_en/algorithm_overview_en.md +++ b/doc/doc_en/algorithm_overview_en.md @@ -96,9 +96,9 @@ Refer to [DTRB](https://arxiv.org/abs/1904.01906), the training and evaluation r |SVTR|SVTR-Tiny| 89.25% | rec_svtr_tiny_none_ctc_en | [trained model](https://paddleocr.bj.bcebos.com/PP-OCRv3/chinese/rec_svtr_tiny_none_ctc_en_train.tar) | |ViTSTR|ViTSTR| 79.82% | rec_vitstr_none_ce | [trained model](https://paddleocr.bj.bcebos.com/rec_vitstr_none_none_train.tar) | |ABINet|Resnet45| 90.75% | rec_r45_abinet | [trained model](https://paddleocr.bj.bcebos.com/rec_r45_abinet_train.tar) | -|VisionLAN|Resnet45| 90.30% | rec_r45_visionlan | [trained model](https://paddleocr.bj.bcebos.com/rec_r45_visionlan_train.tar) | -|SPIN|ResNet32| 90.00% | rec_r32_gaspin_bilstm_att | coming soon | -|RobustScanner|ResNet31| 87.77% | rec_r31_robustscanner | coming soon | +|VisionLAN|Resnet45| 90.30% | rec_r45_visionlan | [trained model](https://paddleocr.bj.bcebos.com/VisionLAN/rec_r45_visionlan_train.tar) | +|SPIN|ResNet32| 90.00% | rec_r32_gaspin_bilstm_att | [trained model](https://paddleocr.bj.bcebos.com/contribution/rec_r32_gaspin_bilstm_att.tar) | +|RobustScanner|ResNet31| 87.77% | rec_r31_robustscanner | [trained model](https://paddleocr.bj.bcebos.com/contribution/rec_r31_robustscanner.tar)| diff --git a/doc/doc_en/algorithm_rec_visionlan_en.md b/doc/doc_en/algorithm_rec_visionlan_en.md index cf2293b3..f67aa3c6 100644 --- a/doc/doc_en/algorithm_rec_visionlan_en.md +++ b/doc/doc_en/algorithm_rec_visionlan_en.md @@ -25,7 +25,7 @@ Using MJSynth and SynthText two text recognition datasets for training, and eval |Model|Backbone|config|Acc|Download link| | --- | --- | --- | --- | --- | -|VisionLAN|ResNet45|[rec_r45_visionlan.yml](../../configs/rec/rec_r45_visionlan.yml)|90.3%|[预训练、训练模型](https://paddleocr.bj.bcebos.com/rec_r45_visionlan_train.tar)| +|VisionLAN|ResNet45|[rec_r45_visionlan.yml](../../configs/rec/rec_r45_visionlan.yml)|90.3%|[预训练、训练模型](https://paddleocr.bj.bcebos.com/VisionLAN/rec_r45_visionlan_train.tar)| ## 2. Environment @@ -68,7 +68,7 @@ python3 tools/infer_rec.py -c configs/rec/rec_r45_visionlan.yml -o Global.infer_ ### 4.1 Python Inference -First, the model saved during the VisionLAN text recognition training process is converted into an inference model. ( [Model download link](https://paddleocr.bj.bcebos.com/rec_r45_visionlan_train.tar)) ), you can use the following command to convert: +First, the model saved during the VisionLAN text recognition training process is converted into an inference model. ( [Model download link](https://paddleocr.bj.bcebos.com/VisionLAN/rec_r45_visionlan_train.tar)) ), you can use the following command to convert: ``` python3 tools/export_model.py -c configs/rec/rec_r45_visionlan.yml -o Global.pretrained_model=./rec_r45_visionlan_train/best_accuracy Global.save_inference_dir=./inference/rec_r45_visionlan/ diff --git a/ppocr/data/imaug/label_ops.py b/ppocr/data/imaug/label_ops.py index 8191e4c3..a4027d1a 100644 --- a/ppocr/data/imaug/label_ops.py +++ b/ppocr/data/imaug/label_ops.py @@ -107,7 +107,6 @@ class BaseRecLabelEncode(object): self.beg_str = "sos" self.end_str = "eos" self.lower = lower - self.use_default_dict = False if character_dict_path is None: logger = get_logger() @@ -117,11 +116,8 @@ class BaseRecLabelEncode(object): self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz" dict_character = list(self.character_str) self.lower = True - self.use_default_dict = True else: self.character_str = [] - if 'ppocr/utils/ic15_dict.txt' in character_dict_path: - self.use_default_dict = True with open(character_dict_path, "rb") as fin: lines = fin.readlines() for line in lines: @@ -1348,9 +1344,6 @@ class VLLabelEncode(BaseRecLabelEncode): **kwargs): super(VLLabelEncode, self).__init__( max_text_length, character_dict_path, use_space_char, lower) - if self.use_default_dict: - self.character = self.character[10:] + self.character[ - 1:10] + [self.character[0]] self.dict = {} for i, char in enumerate(self.character): self.dict[char] = i diff --git a/ppocr/postprocess/rec_postprocess.py b/ppocr/postprocess/rec_postprocess.py index db9e20cb..631f158f 100644 --- a/ppocr/postprocess/rec_postprocess.py +++ b/ppocr/postprocess/rec_postprocess.py @@ -26,15 +26,11 @@ class BaseRecLabelDecode(object): self.end_str = "eos" self.reverse = False self.character_str = [] - self.use_default_dict = False if character_dict_path is None: self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz" dict_character = list(self.character_str) - self.use_default_dict = True else: - if 'ppocr/utils/ic15_dict.txt' in character_dict_path: - self.use_default_dict = True with open(character_dict_path, "rb") as fin: lines = fin.readlines() for line in lines: @@ -725,9 +721,6 @@ class VLLabelDecode(BaseRecLabelDecode): super(VLLabelDecode, self).__init__(character_dict_path, use_space_char) self.max_text_length = kwargs.get('max_text_length', 25) self.nclass = len(self.character) + 1 - if self.use_default_dict: - self.character = self.character[10:] + self.character[ - 1:10] + [self.character[0]] def decode(self, text_index, text_prob=None, is_remove_duplicate=False): """ convert text-index into text-label. """ -- GitLab