update visionlan (#7989)
andyj
GitHub
parent
b0a6a6260e
commit
38290a2853
|
|
@ -102,7 +102,7 @@ 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) |
|
||||
|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)|
|
||||
|RFL|ResNetRFL| 88.63% | rec_resnet_rfl_att | [训练模型](https://paddleocr.bj.bcebos.com/contribution/rec_resnet_rfl_att_train.tar) |
|
||||
|
|
|
|||
|
|
@ -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)|
|
||||
|
||||
<a name="2"></a>
|
||||
## 2. 环境配置
|
||||
|
|
@ -80,7 +80,7 @@ python3 tools/infer_rec.py -c configs/rec/rec_r45_visionlan.yml -o Global.infer_
|
|||
|
||||
<a name="4-1"></a>
|
||||
### 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。
|
||||
|
|
|
|||
|
|
@ -99,7 +99,7 @@ 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) |
|
||||
|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)|
|
||||
|RFL|ResNetRFL| 88.63% | rec_resnet_rfl_att | [trained model](https://paddleocr.bj.bcebos.com/contribution/rec_resnet_rfl_att_train.tar) |
|
||||
|
|
|
|||
|
|
@ -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)|
|
||||
|
||||
<a name="2"></a>
|
||||
## 2. Environment
|
||||
|
|
@ -68,7 +68,7 @@ python3 tools/infer_rec.py -c configs/rec/rec_r45_visionlan.yml -o Global.infer_
|
|||
|
||||
<a name="4-1"></a>
|
||||
### 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/
|
||||
|
|
|
|||
|
|
@ -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:
|
||||
|
|
@ -1404,9 +1400,6 @@ 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
|
||||
|
|
|
|||
|
|
@ -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:
|
||||
|
|
@ -810,9 +806,6 @@ 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. """
|
||||
|
|
|
|||
Loading…
Reference in New Issue