未验证 提交 6ebbbfe4 编写于 作者: X xiaoting 提交者: GitHub

Merge branch 'dygraph' into dygraph_for_srn

...@@ -1031,7 +1031,7 @@ class MainWindow(QMainWindow, WindowMixin): ...@@ -1031,7 +1031,7 @@ class MainWindow(QMainWindow, WindowMixin):
for box in self.result_dic: for box in self.result_dic:
trans_dic = {"label": box[1][0], "points": box[0], 'difficult': False} trans_dic = {"label": box[1][0], "points": box[0], 'difficult': False}
if trans_dic["label"] is "" and mode == 'Auto': if trans_dic["label"] == "" and mode == 'Auto':
continue continue
shapes.append(trans_dic) shapes.append(trans_dic)
...@@ -1764,7 +1764,7 @@ class MainWindow(QMainWindow, WindowMixin): ...@@ -1764,7 +1764,7 @@ class MainWindow(QMainWindow, WindowMixin):
QMessageBox.information(self, "Information", msg) QMessageBox.information(self, "Information", msg)
return return
result = self.ocr.ocr(img_crop, cls=True, det=False) result = self.ocr.ocr(img_crop, cls=True, det=False)
if result[0][0] is not '': if result[0][0] != '':
result.insert(0, box) result.insert(0, box)
print('result in reRec is ', result) print('result in reRec is ', result)
self.result_dic.append(result) self.result_dic.append(result)
...@@ -1795,7 +1795,7 @@ class MainWindow(QMainWindow, WindowMixin): ...@@ -1795,7 +1795,7 @@ class MainWindow(QMainWindow, WindowMixin):
QMessageBox.information(self, "Information", msg) QMessageBox.information(self, "Information", msg)
return return
result = self.ocr.ocr(img_crop, cls=True, det=False) result = self.ocr.ocr(img_crop, cls=True, det=False)
if result[0][0] is not '': if result[0][0] != '':
result.insert(0, box) result.insert(0, box)
print('result in reRec is ', result) print('result in reRec is ', result)
if result[1][0] == shape.label: if result[1][0] == shape.label:
...@@ -1991,7 +1991,7 @@ if __name__ == '__main__': ...@@ -1991,7 +1991,7 @@ if __name__ == '__main__':
resource_file = './libs/resources.py' resource_file = './libs/resources.py'
if not os.path.exists(resource_file): if not os.path.exists(resource_file):
output = os.system('pyrcc5 -o libs/resources.py resources.qrc') output = os.system('pyrcc5 -o libs/resources.py resources.qrc')
assert output is 0, "operate the cmd have some problems ,please check whether there is a in the lib " \ assert output == 0, "operate the cmd have some problems ,please check whether there is a in the lib " \
"directory resources.py " "directory resources.py "
import libs.resources import libs.resources
sys.exit(main()) sys.exit(main())
...@@ -5,10 +5,11 @@ PaddleOCR aims to create multilingual, awesome, leading, and practical OCR tools ...@@ -5,10 +5,11 @@ PaddleOCR aims to create multilingual, awesome, leading, and practical OCR tools
## Notice ## Notice
PaddleOCR supports both dynamic graph and static graph programming paradigm PaddleOCR supports both dynamic graph and static graph programming paradigm
- Dynamic graph: dygraph branch (default), **supported by paddle 2.0rc1+ ([installation](./doc/doc_en/installation_en.md))** - Dynamic graph: dygraph branch (default), **supported by paddle 2.0.0 ([installation](./doc/doc_en/installation_en.md))**
- Static graph: develop branch - Static graph: develop branch
**Recent updates** **Recent updates**
- 2021.1.21 update more than 25+ multilingual recognition models [models list](./doc/doc_en/models_list_en.md), including:English, Chinese, German, French, Japanese,Spanish,Portuguese Russia Arabic and so on. Models for more languages will continue to be updated [Develop Plan](https://github.com/PaddlePaddle/PaddleOCR/issues/1048).
- 2020.12.15 update Data synthesis tool, i.e., [Style-Text](./StyleText/README.md),easy to synthesize a large number of images which are similar to the target scene image. - 2020.12.15 update Data synthesis tool, i.e., [Style-Text](./StyleText/README.md),easy to synthesize a large number of images which are similar to the target scene image.
- 2020.11.25 Update a new data annotation tool, i.e., [PPOCRLabel](./PPOCRLabel/README.md), which is helpful to improve the labeling efficiency. Moreover, the labeling results can be used in training of the PP-OCR system directly. - 2020.11.25 Update a new data annotation tool, i.e., [PPOCRLabel](./PPOCRLabel/README.md), which is helpful to improve the labeling efficiency. Moreover, the labeling results can be used in training of the PP-OCR system directly.
- 2020.9.22 Update the PP-OCR technical article, https://arxiv.org/abs/2009.09941 - 2020.9.22 Update the PP-OCR technical article, https://arxiv.org/abs/2009.09941
......
...@@ -4,11 +4,13 @@ ...@@ -4,11 +4,13 @@
PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库,助力使用者训练出更好的模型,并应用落地。 PaddleOCR旨在打造一套丰富、领先、且实用的OCR工具库,助力使用者训练出更好的模型,并应用落地。
## 注意 ## 注意
PaddleOCR同时支持动态图与静态图两种编程范式 PaddleOCR同时支持动态图与静态图两种编程范式
- 动态图版本:dygraph分支(默认),需将paddle版本升级至2.0rc1+[快速安装](./doc/doc_ch/installation.md) - 动态图版本:dygraph分支(默认),需将paddle版本升级至2.0.0[快速安装](./doc/doc_ch/installation.md)
- 静态图版本:develop分支 - 静态图版本:develop分支
**近期更新** **近期更新**
- 2021.1.26,28,29 PaddleOCR官方研发团队带来技术深入解读三日直播课,1月26日、28日、29日晚上19:30,[直播地址](https://live.bilibili.com/21689802)
- 2021.1.25 [FAQ](./doc/doc_ch/FAQ.md)新增5个高频问题,总数157个,每周一都会更新,欢迎大家持续关注。 - 2021.1.25 [FAQ](./doc/doc_ch/FAQ.md)新增5个高频问题,总数157个,每周一都会更新,欢迎大家持续关注。
- 2021.1.21 更新多语言识别模型,目前支持语种超过27种,[多语言模型下载](./doc/doc_ch/models_list.md),包括中文简体、中文繁体、英文、法文、德文、韩文、日文、意大利文、西班牙文、葡萄牙文、俄罗斯文、阿拉伯文等,后续计划可以参考[多语言研发计划](https://github.com/PaddlePaddle/PaddleOCR/issues/1048)
- 2020.12.15 更新数据合成工具[Style-Text](./StyleText/README_ch.md),可以批量合成大量与目标场景类似的图像,在多个场景验证,效果明显提升。 - 2020.12.15 更新数据合成工具[Style-Text](./StyleText/README_ch.md),可以批量合成大量与目标场景类似的图像,在多个场景验证,效果明显提升。
- 2020.11.25 更新半自动标注工具[PPOCRLabel](./PPOCRLabel/README_ch.md),辅助开发者高效完成标注任务,输出格式与PP-OCR训练任务完美衔接。 - 2020.11.25 更新半自动标注工具[PPOCRLabel](./PPOCRLabel/README_ch.md),辅助开发者高效完成标注任务,输出格式与PP-OCR训练任务完美衔接。
- 2020.9.22 更新PP-OCR技术文章,https://arxiv.org/abs/2009.09941 - 2020.9.22 更新PP-OCR技术文章,https://arxiv.org/abs/2009.09941
......
...@@ -72,7 +72,7 @@ fusion_generator: ...@@ -72,7 +72,7 @@ fusion_generator:
python3 tools/synth_image.py -c configs/config.yml --style_image examples/style_images/2.jpg --text_corpus PaddleOCR --language en python3 tools/synth_image.py -c configs/config.yml --style_image examples/style_images/2.jpg --text_corpus PaddleOCR --language en
``` ```
* Note 1: The language options is correspond to the corpus. Currently, the tool only supports English, Simplified Chinese and Korean. * Note 1: The language options is correspond to the corpus. Currently, the tool only supports English(en), Simplified Chinese(ch) and Korean(ko).
* Note 2: Synth-Text is mainly used to generate images for OCR recognition models. * Note 2: Synth-Text is mainly used to generate images for OCR recognition models.
So the height of style images should be around 32 pixels. Images in other sizes may behave poorly. So the height of style images should be around 32 pixels. Images in other sizes may behave poorly.
* Note 3: You can modify `use_gpu` in `configs/config.yml` to determine whether to use GPU for prediction. * Note 3: You can modify `use_gpu` in `configs/config.yml` to determine whether to use GPU for prediction.
...@@ -120,7 +120,7 @@ In actual application scenarios, it is often necessary to synthesize pictures in ...@@ -120,7 +120,7 @@ In actual application scenarios, it is often necessary to synthesize pictures in
* `with_label`:Whether the `label_file` is label file list. * `with_label`:Whether the `label_file` is label file list.
* `CorpusGenerator` * `CorpusGenerator`
* `method`:Method of CorpusGenerator,supports `FileCorpus` and `EnNumCorpus`. If `EnNumCorpus` is used,No other configuration is needed,otherwise you need to set `corpus_file` and `language`. * `method`:Method of CorpusGenerator,supports `FileCorpus` and `EnNumCorpus`. If `EnNumCorpus` is used,No other configuration is needed,otherwise you need to set `corpus_file` and `language`.
* `language`:Language of the corpus. * `language`:Language of the corpus. Currently, the tool only supports English(en), Simplified Chinese(ch) and Korean(ko).
* `corpus_file`: Filepath of the corpus. Corpus file should be a text file which will be split by line-endings('\n'). Corpus generator samples one line each time. * `corpus_file`: Filepath of the corpus. Corpus file should be a text file which will be split by line-endings('\n'). Corpus generator samples one line each time.
......
...@@ -63,10 +63,10 @@ fusion_generator: ...@@ -63,10 +63,10 @@ fusion_generator:
```python ```python
python3 tools/synth_image.py -c configs/config.yml --style_image examples/style_images/2.jpg --text_corpus PaddleOCR --language en python3 tools/synth_image.py -c configs/config.yml --style_image examples/style_images/2.jpg --text_corpus PaddleOCR --language en
``` ```
* 注1:语言选项和语料相对应,目前该工具只支持英文、简体中文和韩语 * 注1:语言选项和语料相对应,目前支持英文(en)、简体中文(ch)和韩语(ko)
* 注2:Style-Text生成的数据主要应用于OCR识别场景。基于当前PaddleOCR识别模型的设计,我们主要支持高度在32左右的风格图像。 * 注2:Style-Text生成的数据主要应用于OCR识别场景。基于当前PaddleOCR识别模型的设计,我们主要支持高度在32左右的风格图像。
如果输入图像尺寸相差过多,效果可能不佳。 如果输入图像尺寸相差过多,效果可能不佳。
* 注3:可以通过修改配置文件中的`use_gpu`(true或者false)参数来决定是否使用GPU进行预测。 * 注3:可以通过修改配置文件`configs/config.yml`中的`use_gpu`(true或者false)参数来决定是否使用GPU进行预测。
例如,输入如下图片和语料"PaddleOCR": 例如,输入如下图片和语料"PaddleOCR":
...@@ -105,7 +105,7 @@ python3 tools/synth_image.py -c configs/config.yml --style_image examples/style_ ...@@ -105,7 +105,7 @@ python3 tools/synth_image.py -c configs/config.yml --style_image examples/style_
* `with_label`:标志`label_file`是否为label文件。 * `with_label`:标志`label_file`是否为label文件。
* `CorpusGenerator` * `CorpusGenerator`
* `method`:语料生成方法,目前有`FileCorpus``EnNumCorpus`可选。如果使用`EnNumCorpus`,则不需要填写其他配置,否则需要修改`corpus_file``language` * `method`:语料生成方法,目前有`FileCorpus``EnNumCorpus`可选。如果使用`EnNumCorpus`,则不需要填写其他配置,否则需要修改`corpus_file``language`
* `language`:语料的语种; * `language`:语料的语种,目前支持英文(en)、简体中文(ch)和韩语(ko)
* `corpus_file`: 语料文件路径。语料文件应使用文本文件。语料生成器首先会将语料按行切分,之后每次随机选取一行。 * `corpus_file`: 语料文件路径。语料文件应使用文本文件。语料生成器首先会将语料按行切分,之后每次随机选取一行。
语料文件格式示例: 语料文件格式示例:
......
...@@ -16,7 +16,7 @@ Global: ...@@ -16,7 +16,7 @@ Global:
infer_img: infer_img:
# for data or label process # for data or label process
character_dict_path: ppocr/utils/dict/en_dict.txt character_dict_path: ppocr/utils/dict/en_dict.txt
character_type: ch character_type: EN
max_text_length: 25 max_text_length: 25
infer_mode: False infer_mode: False
use_space_char: False use_space_char: False
......
...@@ -42,7 +42,7 @@ python deploy/slim/quantization/quant.py -c configs/det/det_mv3_db.yml -o Global ...@@ -42,7 +42,7 @@ python deploy/slim/quantization/quant.py -c configs/det/det_mv3_db.yml -o Global
# 比如下载提供的训练模型 # 比如下载提供的训练模型
wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar wget https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar
tar -xf ch_ppocr_mobile_v2.0_det_train.tar tar -xf ch_ppocr_mobile_v2.0_det_train.tar
python deploy/slim/quantization/quant.py -c configs/det/det_mv3_db.yml -o Global.pretrain_weights=./ch_ppocr_mobile_v2.0_det_train/best_accuracy Global.save_model_dir=./output/quant_model python deploy/slim/quantization/quant.py -c configs/det/det_mv3_db.yml -o Global.pretrain_weights=./ch_ppocr_mobile_v2.0_det_train/best_accuracy Global.save_inference_dir=./output/quant_inference_model
``` ```
如果要训练识别模型的量化,修改配置文件和加载的模型参数即可。 如果要训练识别模型的量化,修改配置文件和加载的模型参数即可。
......
...@@ -58,7 +58,7 @@ python deploy/slim/quantization/quant.py -c configs/det/det_mv3_db.yml -o Global ...@@ -58,7 +58,7 @@ python deploy/slim/quantization/quant.py -c configs/det/det_mv3_db.yml -o Global
After getting the model after pruning and finetuning we, can export it as inference_model for predictive deployment: After getting the model after pruning and finetuning we, can export it as inference_model for predictive deployment:
```bash ```bash
python deploy/slim/quantization/export_model.py -c configs/det/det_mv3_db.yml -o Global.checkpoints=output/quant_model/best_accuracy Global.save_model_dir=./output/quant_inference_model python deploy/slim/quantization/export_model.py -c configs/det/det_mv3_db.yml -o Global.checkpoints=output/quant_model/best_accuracy Global.save_inference_dir=./output/quant_inference_model
``` ```
### 5. Deploy ### 5. Deploy
......
...@@ -31,7 +31,7 @@ ...@@ -31,7 +31,7 @@
#### Q3.1.38: module 'paddle.distributed' has no attribute ‘get_rank’。 #### Q3.1.38: module 'paddle.distributed' has no attribute ‘get_rank’。
**A**:Paddle版本问题,请安装2.0版本Paddle:pip install paddlepaddle==2.0.0rc1 **A**:Paddle版本问题,请安装2.0版本Paddle:pip install paddlepaddle==2.0.0。
#### Q3.4.30: PaddleOCR是否支持在华为鲲鹏920CPU上部署? #### Q3.4.30: PaddleOCR是否支持在华为鲲鹏920CPU上部署?
...@@ -397,13 +397,13 @@ Paddle2ONNX支持转换的[模型列表](https://github.com/PaddlePaddle/Paddle2 ...@@ -397,13 +397,13 @@ Paddle2ONNX支持转换的[模型列表](https://github.com/PaddlePaddle/Paddle2
**A**:动态图版本正在紧锣密鼓开发中,将于2020年12月16日发布,敬请关注。 **A**:动态图版本正在紧锣密鼓开发中,将于2020年12月16日发布,敬请关注。
#### Q3.1.22:ModuleNotFoundError: No module named 'paddle.nn', #### Q3.1.22:ModuleNotFoundError: No module named 'paddle.nn',
**A**:paddle.nn是Paddle2.0版本特有的功能,请安装大于等于Paddle 2.0.0rc1的版本,安装方式为 **A**:paddle.nn是Paddle2.0版本特有的功能,请安装大于等于Paddle 2.0.0的版本,安装方式为
``` ```
python3 -m pip install paddlepaddle-gpu==2.0.0rc1 -i https://mirror.baidu.com/pypi/simple python3 -m pip install paddlepaddle-gpu==2.0.0 -i https://mirror.baidu.com/pypi/simple
``` ```
#### Q3.1.23: ImportError: /usr/lib/x86_64_linux-gnu/libstdc++.so.6:version `CXXABI_1.3.11` not found (required by /usr/lib/python3.6/site-package/paddle/fluid/core+avx.so) #### Q3.1.23: ImportError: /usr/lib/x86_64_linux-gnu/libstdc++.so.6:version `CXXABI_1.3.11` not found (required by /usr/lib/python3.6/site-package/paddle/fluid/core+avx.so)
**A**:这个问题是glibc版本不足导致的,Paddle2.0rc1版本对gcc版本和glib版本有更高的要求,推荐gcc版本为8.2,glibc版本2.12以上。 **A**:这个问题是glibc版本不足导致的,Paddle2.0.0版本对gcc版本和glib版本有更高的要求,推荐gcc版本为8.2,glibc版本2.12以上。
如果您的环境不满足这个要求,或者使用的docker镜像为: 如果您的环境不满足这个要求,或者使用的docker镜像为:
`hub.baidubce.com/paddlepaddle/paddle:latest-gpu-cuda9.0-cudnn7-dev` `hub.baidubce.com/paddlepaddle/paddle:latest-gpu-cuda9.0-cudnn7-dev`
`hub.baidubce.com/paddlepaddle/paddle:latest-gpu-cuda9.0-cudnn7-dev`,安装Paddle2.0rc版本可能会出现上述错误,2.0版本推荐使用新的docker镜像 `paddlepaddle/paddle:latest-dev-cuda10.1-cudnn7-gcc82` `hub.baidubce.com/paddlepaddle/paddle:latest-gpu-cuda9.0-cudnn7-dev`,安装Paddle2.0rc版本可能会出现上述错误,2.0版本推荐使用新的docker镜像 `paddlepaddle/paddle:latest-dev-cuda10.1-cudnn7-gcc82`
...@@ -415,7 +415,7 @@ python3 -m pip install paddlepaddle-gpu==2.0.0rc1 -i https://mirror.baidu.com/py ...@@ -415,7 +415,7 @@ python3 -m pip install paddlepaddle-gpu==2.0.0rc1 -i https://mirror.baidu.com/py
- develop:基于Paddle静态图开发的分支,推荐使用paddle1.8 或者2.0版本,该分支具备完善的模型训练、预测、推理部署、量化裁剪等功能,领先于release/1.1分支。 - develop:基于Paddle静态图开发的分支,推荐使用paddle1.8 或者2.0版本,该分支具备完善的模型训练、预测、推理部署、量化裁剪等功能,领先于release/1.1分支。
- release/1.1:PaddleOCR 发布的第一个稳定版本,基于静态图开发,具备完善的训练、预测、推理部署、量化裁剪等功能。 - release/1.1:PaddleOCR 发布的第一个稳定版本,基于静态图开发,具备完善的训练、预测、推理部署、量化裁剪等功能。
- dygraph:基于Paddle动态图开发的分支,目前仍在开发中,未来将作为主要开发分支,运行要求使用Paddle2.0rc1版本,目前仍在开发中 - dygraph:基于Paddle动态图开发的分支,目前仍在开发中,未来将作为主要开发分支,运行要求使用Paddle2.0.0版本
- release/2.0-rc1-0:PaddleOCR发布的第二个稳定版本,基于动态图和paddle2.0版本开发,动态图开发的工程更易于调试,目前支,支持模型训练、预测,暂不支持移动端部署。 - release/2.0-rc1-0:PaddleOCR发布的第二个稳定版本,基于动态图和paddle2.0版本开发,动态图开发的工程更易于调试,目前支,支持模型训练、预测,暂不支持移动端部署。
如果您已经上手过PaddleOCR,并且希望在各种环境上部署PaddleOCR,目前建议使用静态图分支,develop或者release/1.1分支。如果您是初学者,想快速训练,调试PaddleOCR中的算法,建议尝鲜PaddleOCR dygraph分支。 如果您已经上手过PaddleOCR,并且希望在各种环境上部署PaddleOCR,目前建议使用静态图分支,develop或者release/1.1分支。如果您是初学者,想快速训练,调试PaddleOCR中的算法,建议尝鲜PaddleOCR dygraph分支。
...@@ -432,7 +432,7 @@ python3 -m pip install paddlepaddle-gpu==2.0.0rc1 -i https://mirror.baidu.com/py ...@@ -432,7 +432,7 @@ python3 -m pip install paddlepaddle-gpu==2.0.0rc1 -i https://mirror.baidu.com/py
#### Q3.1.27: 如何可视化acc,loss曲线图,模型网络结构图等? #### Q3.1.27: 如何可视化acc,loss曲线图,模型网络结构图等?
**A**:在配置文件里有`use_visualdl`的参数,设置为True即可,更多的使用命令可以参考:[VisualDL使用指南](https://www.paddlepaddle.org.cn/documentation/docs/zh/2.0-rc1/guides/03_VisualDL/visualdl.html) **A**:在配置文件里有`use_visualdl`的参数,设置为True即可,更多的使用命令可以参考:[VisualDL使用指南](https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/guides/03_VisualDL/visualdl.html)
#### Q3.1.28: 在使用StyleText数据合成工具的时候,报错`ModuleNotFoundError: No module named 'utils.config'`,这是为什么呢? #### Q3.1.28: 在使用StyleText数据合成工具的时候,报错`ModuleNotFoundError: No module named 'utils.config'`,这是为什么呢?
...@@ -451,7 +451,7 @@ https://github.com/PaddlePaddle/PaddleOCR/blob/de3e2e7cd3b8b65ee02d7a41e570fa5b5 ...@@ -451,7 +451,7 @@ https://github.com/PaddlePaddle/PaddleOCR/blob/de3e2e7cd3b8b65ee02d7a41e570fa5b5
#### Q3.1.31: 怎么输出网络结构以及每层的参数信息? #### Q3.1.31: 怎么输出网络结构以及每层的参数信息?
**A**:可以使用 `paddle.summary`, 具体参考:https://www.paddlepaddle.org.cn/documentation/docs/zh/2.0-rc1/api/paddle/hapi/model_summary/summary_cn.html#summary **A**:可以使用 `paddle.summary`, 具体参考:https://www.paddlepaddle.org.cn/documentation/docs/zh/develop/api/paddle/hapi/model_summary/summary_cn.html
#### Q3.1.32 能否修改StyleText配置文件中的分辨率? #### Q3.1.32 能否修改StyleText配置文件中的分辨率?
...@@ -485,7 +485,7 @@ StyleText的用途主要是:提取style_image中的字体、背景等style信 ...@@ -485,7 +485,7 @@ StyleText的用途主要是:提取style_image中的字体、背景等style信
#### Q3.1.38: module 'paddle.distributed' has no attribute ‘get_rank’。 #### Q3.1.38: module 'paddle.distributed' has no attribute ‘get_rank’。
**A**:Paddle版本问题,请安装2.0版本Paddle:pip install paddlepaddle==2.0.0rc1 **A**:Paddle版本问题,请安装2.0版本Paddle:pip install paddlepaddle==2.0.0。
<a name="数据集3"></a> <a name="数据集3"></a>
### 数据集 ### 数据集
......
...@@ -63,7 +63,7 @@ PaddleOCR提供了训练脚本、评估脚本和预测脚本。 ...@@ -63,7 +63,7 @@ PaddleOCR提供了训练脚本、评估脚本和预测脚本。
*如果您安装的是cpu版本,请将配置文件中的 `use_gpu` 字段修改为false* *如果您安装的是cpu版本,请将配置文件中的 `use_gpu` 字段修改为false*
``` ```
# GPU训练 支持单卡,多卡训练,通过 '--gpus' 指定卡号,如果使用的paddle版本小于2.0rc1,请使用'--select_gpus'参数选择要使用的GPU # GPU训练 支持单卡,多卡训练,通过 '--gpus' 指定卡号
# 启动训练,下面的命令已经写入train.sh文件中,只需修改文件里的配置文件路径即可 # 启动训练,下面的命令已经写入train.sh文件中,只需修改文件里的配置文件路径即可
python3 -m paddle.distributed.launch --gpus '0,1,2,3,4,5,6,7' tools/train.py -c configs/cls/cls_mv3.yml python3 -m paddle.distributed.launch --gpus '0,1,2,3,4,5,6,7' tools/train.py -c configs/cls/cls_mv3.yml
``` ```
......
...@@ -76,7 +76,7 @@ tar -xf ./pretrain_models/MobileNetV3_large_x0_5_pretrained.tar ./pretrain_model ...@@ -76,7 +76,7 @@ tar -xf ./pretrain_models/MobileNetV3_large_x0_5_pretrained.tar ./pretrain_model
# 单机单卡训练 mv3_db 模型 # 单机单卡训练 mv3_db 模型
python3 tools/train.py -c configs/det/det_mv3_db.yml \ python3 tools/train.py -c configs/det/det_mv3_db.yml \
-o Global.pretrain_weights=./pretrain_models/MobileNetV3_large_x0_5_pretrained/ -o Global.pretrain_weights=./pretrain_models/MobileNetV3_large_x0_5_pretrained/
# 单机多卡训练,通过 --gpus 参数设置使用的GPU ID;如果使用的paddle版本小于2.0rc1,请使用'--select_gpus'参数选择要使用的GPU # 单机多卡训练,通过 --gpus 参数设置使用的GPU ID
python3 -m paddle.distributed.launch --gpus '0,1,2,3' tools/train.py -c configs/det/det_mv3_db.yml \ python3 -m paddle.distributed.launch --gpus '0,1,2,3' tools/train.py -c configs/det/det_mv3_db.yml \
-o Global.pretrain_weights=./pretrain_models/MobileNetV3_large_x0_5_pretrained/ -o Global.pretrain_weights=./pretrain_models/MobileNetV3_large_x0_5_pretrained/
``` ```
......
...@@ -306,10 +306,10 @@ python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png ...@@ -306,10 +306,10 @@ python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png
<a name="多语言模型的推理"></a> <a name="多语言模型的推理"></a>
### 4. 多语言模型的推理 ### 4. 多语言模型的推理
如果您需要预测的是其他语言模型,在使用inference模型预测时,需要通过`--rec_char_dict_path`指定使用的字典路径, 同时为了得到正确的可视化结果, 如果您需要预测的是其他语言模型,在使用inference模型预测时,需要通过`--rec_char_dict_path`指定使用的字典路径, 同时为了得到正确的可视化结果,
需要通过 `--vis_font_path` 指定可视化的字体路径,`doc/` 路径下有默认提供的小语种字体,例如韩文识别: 需要通过 `--vis_font_path` 指定可视化的字体路径,`doc/fonts/` 路径下有默认提供的小语种字体,例如韩文识别:
``` ```
python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/korean/1.jpg" --rec_model_dir="./your inference model" --rec_char_type="korean" --rec_char_dict_path="ppocr/utils/dict/korean_dict.txt" --vis_font_path="doc/korean.ttf" python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/korean/1.jpg" --rec_model_dir="./your inference model" --rec_char_type="korean" --rec_char_dict_path="ppocr/utils/dict/korean_dict.txt" --vis_font_path="doc/fonts/korean.ttf"
``` ```
![](../imgs_words/korean/1.jpg) ![](../imgs_words/korean/1.jpg)
......
...@@ -2,7 +2,7 @@ ...@@ -2,7 +2,7 @@
经测试PaddleOCR可在glibc 2.23上运行,您也可以测试其他glibc版本或安装glic 2.23 经测试PaddleOCR可在glibc 2.23上运行,您也可以测试其他glibc版本或安装glic 2.23
PaddleOCR 工作环境 PaddleOCR 工作环境
- PaddlePaddle 1.8+ ,推荐使用 PaddlePaddle 2.0rc1 - PaddlePaddle 2.0.0
- python3.7 - python3.7
- glibc 2.23 - glibc 2.23
- cuDNN 7.6+ (GPU) - cuDNN 7.6+ (GPU)
...@@ -35,11 +35,11 @@ sudo docker container exec -it ppocr /bin/bash ...@@ -35,11 +35,11 @@ sudo docker container exec -it ppocr /bin/bash
pip3 install --upgrade pip pip3 install --upgrade pip
如果您的机器安装的是CUDA9或CUDA10,请运行以下命令安装 如果您的机器安装的是CUDA9或CUDA10,请运行以下命令安装
python3 -m pip install paddlepaddle-gpu==2.0.0rc1 -i https://mirror.baidu.com/pypi/simple python3 -m pip install paddlepaddle-gpu==2.0.0 -i https://mirror.baidu.com/pypi/simple
如果您的机器是CPU,请运行以下命令安装 如果您的机器是CPU,请运行以下命令安装
python3 -m pip install paddlepaddle==2.0.0rc1 -i https://mirror.baidu.com/pypi/simple python3 -m pip install paddlepaddle==2.0.0 -i https://mirror.baidu.com/pypi/simple
更多的版本需求,请参照[安装文档](https://www.paddlepaddle.org.cn/install/quick)中的说明进行操作。 更多的版本需求,请参照[安装文档](https://www.paddlepaddle.org.cn/install/quick)中的说明进行操作。
``` ```
......
...@@ -195,8 +195,6 @@ PaddleOCR支持训练和评估交替进行, 可以在 `configs/rec/rec_icdar15_t ...@@ -195,8 +195,6 @@ PaddleOCR支持训练和评估交替进行, 可以在 `configs/rec/rec_icdar15_t
| :--------: | :-------: | :-------: | :-------: | :-----: | :-----: | | :--------: | :-------: | :-------: | :-------: | :-----: | :-----: |
| [rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml) | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | | [rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml) | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc |
| [rec_chinese_common_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml) | CRNN | ResNet34_vd | None | BiLSTM | ctc | | [rec_chinese_common_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml) | CRNN | ResNet34_vd | None | BiLSTM | ctc |
| rec_chinese_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc |
| rec_chinese_common_train.yml | CRNN | ResNet34_vd | None | BiLSTM | ctc |
| rec_icdar15_train.yml | CRNN | Mobilenet_v3 large 0.5 | None | BiLSTM | ctc | | rec_icdar15_train.yml | CRNN | Mobilenet_v3 large 0.5 | None | BiLSTM | ctc |
| rec_mv3_none_bilstm_ctc.yml | CRNN | Mobilenet_v3 large 0.5 | None | BiLSTM | ctc | | rec_mv3_none_bilstm_ctc.yml | CRNN | Mobilenet_v3 large 0.5 | None | BiLSTM | ctc |
| rec_mv3_none_none_ctc.yml | Rosetta | Mobilenet_v3 large 0.5 | None | None | ctc | | rec_mv3_none_none_ctc.yml | Rosetta | Mobilenet_v3 large 0.5 | None | None | ctc |
...@@ -272,16 +270,109 @@ Eval: ...@@ -272,16 +270,109 @@ Eval:
<a name="小语种"></a> <a name="小语种"></a>
- 小语种 - 小语种
PaddleOCR也提供了多语言的, `configs/rec/multi_languages` 路径下的提供了多语言的配置文件,目前PaddleOCR支持的多语言算法有: PaddleOCR目前已支持26种(除中文外)语种识别,`configs/rec/multi_languages` 路径下提供了一个多语言的配置文件模版: [rec_multi_language_lite_train.yml](../../configs/rec/multi_language/rec_multi_language_lite_train.yml)
| 配置文件 | 算法名称 | backbone | trans | seq | pred | language | 您有两种方式创建所需的配置文件:
| :--------: | :-------: | :-------: | :-------: | :-----: | :-----: | :-----: |
| rec_en_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 英语 |
| rec_french_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 法语 |
| rec_ger_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 德语 |
| rec_japan_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 日语 |
| rec_korean_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 韩语 |
1. 通过脚本自动生成
[generate_multi_language_configs.py](../../configs/rec/multi_language/generate_multi_language_configs.py) 可以帮助您生成多语言模型的配置文件
- 以意大利语为例,如果您的数据是按如下格式准备的:
```
|-train_data
|- it_train.txt # 训练集标签
|- it_val.txt # 验证集标签
|- data
|- word_001.jpg
|- word_002.jpg
|- word_003.jpg
| ...
```
可以使用默认参数,生成配置文件:
```bash
# 该代码需要在指定目录运行
cd PaddleOCR/configs/rec/multi_language/
# 通过-l或者--language参数设置需要生成的语种的配置文件,该命令会将默认参数写入配置文件
python3 generate_multi_language_configs.py -l it
```
- 如果您的数据放置在其他位置,或希望使用自己的字典,可以通过指定相关参数来生成配置文件:
```bash
# -l或者--language字段是必须的
# --train修改训练集,--val修改验证集,--data_dir修改数据集目录,--dict修改字典路径, -o修改对应默认参数
cd PaddleOCR/configs/rec/multi_language/
python3 generate_multi_language_configs.py -l it \ # 语种
--train {path/of/train_label.txt} \ # 训练标签文件的路径
--val {path/of/val_label.txt} \ # 验证集标签文件的路径
--data_dir {train_data/path} \ # 训练数据的根目录
--dict {path/of/dict} \ # 字典文件路径
-o Global.use_gpu=False # 是否使用gpu
...
```
2. 手动修改配置文件
您也可以手动修改模版中的以下几个字段:
```
Global:
use_gpu: True
epoch_num: 500
...
character_type: it # 需要识别的语种
character_dict_path: {path/of/dict} # 字典文件所在路径
Train:
dataset:
name: SimpleDataSet
data_dir: train_data/ # 数据存放根目录
label_file_list: ["./train_data/train_list.txt"] # 训练集label路径
...
Eval:
dataset:
name: SimpleDataSet
data_dir: train_data/ # 数据存放根目录
label_file_list: ["./train_data/val_list.txt"] # 验证集label路径
...
```
目前PaddleOCR支持的多语言算法有:
| 配置文件 | 算法名称 | backbone | trans | seq | pred | language | character_type |
| :--------: | :-------: | :-------: | :-------: | :-----: | :-----: | :-----: | :-----: |
| rec_chinese_cht_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 中文繁体 | chinese_cht|
| rec_en_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 英语(区分大小写) | EN |
| rec_french_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 法语 | french |
| rec_ger_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 德语 | german |
| rec_japan_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 日语 | japan |
| rec_korean_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 韩语 | korean |
| rec_it_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 意大利语 | it |
| rec_xi_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 西班牙语 | xi |
| rec_pu_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 葡萄牙语 | pu |
| rec_ru_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 俄罗斯语 | ru |
| rec_ar_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 阿拉伯语 | ar |
| rec_hi_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 印地语 | hi |
| rec_ug_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 维吾尔语 | ug |
| rec_fa_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 波斯语 | fa |
| rec_ur_ite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 乌尔都语 | ur |
| rec_rs_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 塞尔维亚(latin)语 | rs |
| rec_oc_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 欧西坦语 | oc |
| rec_mr_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 马拉地语 | mr |
| rec_ne_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 尼泊尔语 | ne |
| rec_rsc_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 塞尔维亚(cyrillic)语 | rsc |
| rec_bg_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 保加利亚语 | bg |
| rec_uk_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 乌克兰语 | uk |
| rec_be_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 白俄罗斯语 | be |
| rec_te_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 泰卢固语 | te |
| rec_ka_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 卡纳达语 | ka |
| rec_ta_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | 泰米尔语 | ta |
多语言模型训练方式与中文模型一致,训练数据集均为100w的合成数据,少量的字体可以在 [百度网盘](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA) 上下载,提取码:frgi。 多语言模型训练方式与中文模型一致,训练数据集均为100w的合成数据,少量的字体可以在 [百度网盘](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA) 上下载,提取码:frgi。
......
...@@ -66,7 +66,7 @@ Start training: ...@@ -66,7 +66,7 @@ Start training:
``` ```
# Set PYTHONPATH path # Set PYTHONPATH path
export PYTHONPATH=$PYTHONPATH:. export PYTHONPATH=$PYTHONPATH:.
# GPU training Support single card and multi-card training, specify the card number through --gpus. If your paddle version is less than 2.0rc1, please use '--selected_gpus' # GPU training Support single card and multi-card training, specify the card number through --gpus.
# Start training, the following command has been written into the train.sh file, just modify the configuration file path in the file # Start training, the following command has been written into the train.sh file, just modify the configuration file path in the file
python3 -m paddle.distributed.launch --gpus '0,1,2,3,4,5,6,7' tools/train.py -c configs/cls/cls_mv3.yml python3 -m paddle.distributed.launch --gpus '0,1,2,3,4,5,6,7' tools/train.py -c configs/cls/cls_mv3.yml
``` ```
......
...@@ -76,7 +76,7 @@ You can also use `-o` to change the training parameters without modifying the ym ...@@ -76,7 +76,7 @@ You can also use `-o` to change the training parameters without modifying the ym
python3 tools/train.py -c configs/det/det_mv3_db.yml -o Optimizer.base_lr=0.0001 python3 tools/train.py -c configs/det/det_mv3_db.yml -o Optimizer.base_lr=0.0001
# multi-GPU training # multi-GPU training
# Set the GPU ID used by the '--gpus' parameter; If your paddle version is less than 2.0rc1, please use '--selected_gpus' # Set the GPU ID used by the '--gpus' parameter.
python3 -m paddle.distributed.launch --gpus '0,1,2,3' tools/train.py -c configs/det/det_mv3_db.yml -o Optimizer.base_lr=0.0001 python3 -m paddle.distributed.launch --gpus '0,1,2,3' tools/train.py -c configs/det/det_mv3_db.yml -o Optimizer.base_lr=0.0001
......
...@@ -315,10 +315,10 @@ python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png ...@@ -315,10 +315,10 @@ python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png
<a name="MULTILINGUAL_MODEL_INFERENCE"></a> <a name="MULTILINGUAL_MODEL_INFERENCE"></a>
### 4. MULTILINGAUL MODEL INFERENCE ### 4. MULTILINGAUL MODEL INFERENCE
If you need to predict other language models, when using inference model prediction, you need to specify the dictionary path used by `--rec_char_dict_path`. At the same time, in order to get the correct visualization results, If you need to predict other language models, when using inference model prediction, you need to specify the dictionary path used by `--rec_char_dict_path`. At the same time, in order to get the correct visualization results,
You need to specify the visual font path through `--vis_font_path`. There are small language fonts provided by default under the `doc/` path, such as Korean recognition: You need to specify the visual font path through `--vis_font_path`. There are small language fonts provided by default under the `doc/fonts` path, such as Korean recognition:
``` ```
python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/korean/1.jpg" --rec_model_dir="./your inference model" --rec_char_type="korean" --rec_char_dict_path="ppocr/utils/dict/korean_dict.txt" --vis_font_path="doc/korean.ttf" python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words/korean/1.jpg" --rec_model_dir="./your inference model" --rec_char_type="korean" --rec_char_dict_path="ppocr/utils/dict/korean_dict.txt" --vis_font_path="doc/fonts/korean.ttf"
``` ```
![](../imgs_words/korean/1.jpg) ![](../imgs_words/korean/1.jpg)
......
...@@ -3,7 +3,7 @@ ...@@ -3,7 +3,7 @@
After testing, paddleocr can run on glibc 2.23. You can also test other glibc versions or install glic 2.23 for the best compatibility. After testing, paddleocr can run on glibc 2.23. You can also test other glibc versions or install glic 2.23 for the best compatibility.
PaddleOCR working environment: PaddleOCR working environment:
- PaddlePaddle 1.8+, Recommend PaddlePaddle 2.0rc1 - PaddlePaddle 2.0.0
- python3.7 - python3.7
- glibc 2.23 - glibc 2.23
...@@ -38,10 +38,10 @@ sudo docker container exec -it ppocr /bin/bash ...@@ -38,10 +38,10 @@ sudo docker container exec -it ppocr /bin/bash
pip3 install --upgrade pip pip3 install --upgrade pip
# If you have cuda9 or cuda10 installed on your machine, please run the following command to install # If you have cuda9 or cuda10 installed on your machine, please run the following command to install
python3 -m pip install paddlepaddle-gpu==2.0rc1 -i https://mirror.baidu.com/pypi/simple python3 -m pip install paddlepaddle-gpu==2.0.0 -i https://mirror.baidu.com/pypi/simple
# If you only have cpu on your machine, please run the following command to install # If you only have cpu on your machine, please run the following command to install
python3 -m pip install paddlepaddle==2.0rc1 -i https://mirror.baidu.com/pypi/simple python3 -m pip install paddlepaddle==2.0.0 -i https://mirror.baidu.com/pypi/simple
``` ```
For more software version requirements, please refer to the instructions in [Installation Document](https://www.paddlepaddle.org.cn/install/quick) for operation. For more software version requirements, please refer to the instructions in [Installation Document](https://www.paddlepaddle.org.cn/install/quick) for operation.
......
...@@ -93,7 +93,7 @@ python3 generate_multi_language_configs.py -l it \ ...@@ -93,7 +93,7 @@ python3 generate_multi_language_configs.py -l it \
|model name|description|config|model size|download| |model name|description|config|model size|download|
| --- | --- | --- | --- | --- | | --- | --- | --- | --- | --- |
| french_mobile_v2.0_rec |Lightweight model for French recognition|[rec_french_lite_train.yml](../../configs/rec/multi_language/rec_french_lite_train.yml)|2.65M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/french_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/french_mobile_v2.0_rec_train.tar) | | french_mobile_v2.0_rec |Lightweight model for French recognition|[rec_french_lite_train.yml](../../configs/rec/multi_language/rec_french_lite_train.yml)|2.65M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/french_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/french_mobile_v2.0_rec_train.tar) |
| german_mobile_v2.0_rec |Lightweight model for French recognition|[rec_german_lite_train.yml](../../configs/rec/multi_language/rec_german_lite_train.yml)|2.65M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/german_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/german_mobile_v2.0_rec_train.tar) | | german_mobile_v2.0_rec |Lightweight model for German recognition|[rec_german_lite_train.yml](../../configs/rec/multi_language/rec_german_lite_train.yml)|2.65M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/german_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/german_mobile_v2.0_rec_train.tar) |
| korean_mobile_v2.0_rec |Lightweight model for Korean recognition|[rec_korean_lite_train.yml](../../configs/rec/multi_language/rec_korean_lite_train.yml)|3.9M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/korean_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/korean_mobile_v2.0_rec_train.tar) | | korean_mobile_v2.0_rec |Lightweight model for Korean recognition|[rec_korean_lite_train.yml](../../configs/rec/multi_language/rec_korean_lite_train.yml)|3.9M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/korean_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/korean_mobile_v2.0_rec_train.tar) |
| japan_mobile_v2.0_rec |Lightweight model for Japanese recognition|[rec_japan_lite_train.yml](../../configs/rec/multi_language/rec_japan_lite_train.yml)|4.23M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/japan_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/japan_mobile_v2.0_rec_train.tar) | | japan_mobile_v2.0_rec |Lightweight model for Japanese recognition|[rec_japan_lite_train.yml](../../configs/rec/multi_language/rec_japan_lite_train.yml)|4.23M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/japan_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/japan_mobile_v2.0_rec_train.tar) |
| it_mobile_v2.0_rec |Lightweight model for Italian recognition|rec_it_lite_train.yml|2.53M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/it_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/it_mobile_v2.0_rec_train.tar) | | it_mobile_v2.0_rec |Lightweight model for Italian recognition|rec_it_lite_train.yml|2.53M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/it_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/it_mobile_v2.0_rec_train.tar) |
......
...@@ -266,15 +266,116 @@ Eval: ...@@ -266,15 +266,116 @@ Eval:
<a name="Multi_language"></a> <a name="Multi_language"></a>
- Multi-language - Multi-language
PaddleOCR also provides multi-language. The configuration file in `configs/rec/multi_languages` provides multi-language configuration files. Currently, the multi-language algorithms supported by PaddleOCR are: PaddleOCR currently supports 26 (except Chinese) language recognition. A multi-language configuration file template is
provided under the path `configs/rec/multi_languages`: [rec_multi_language_lite_train.yml](../../configs/rec/multi_language/rec_multi_language_lite_train.yml)
| Configuration file | Algorithm name | backbone | trans | seq | pred | language |
| :--------: | :-------: | :-------: | :-------: | :-----: | :-----: | :-----: | There are two ways to create the required configuration file::
| rec_en_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | English |
| rec_french_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | French | 1. Automatically generated by script
| rec_ger_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | German |
| rec_japan_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Japanese | [generate_multi_language_configs.py](../../configs/rec/multi_language/generate_multi_language_configs.py) Can help you generate configuration files for multi-language models
| rec_korean_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Korean |
- Take Italian as an example, if your data is prepared in the following format:
```
|-train_data
|- it_train.txt # train_set label
|- it_val.txt # val_set label
|- data
|- word_001.jpg
|- word_002.jpg
|- word_003.jpg
| ...
```
You can use the default parameters to generate a configuration file:
```bash
# The code needs to be run in the specified directory
cd PaddleOCR/configs/rec/multi_language/
# Set the configuration file of the language to be generated through the -l or --language parameter.
# This command will write the default parameters into the configuration file
python3 generate_multi_language_configs.py -l it
```
- If your data is placed in another location, or you want to use your own dictionary, you can generate the configuration file by specifying the relevant parameters:
```bash
# -l or --language field is required
# --train to modify the training set
# --val to modify the validation set
# --data_dir to modify the data set directory
# --dict to modify the dict path
# -o to modify the corresponding default parameters
cd PaddleOCR/configs/rec/multi_language/
python3 generate_multi_language_configs.py -l it \ # language
--train {path/of/train_label.txt} \ # path of train_label
--val {path/of/val_label.txt} \ # path of val_label
--data_dir {train_data/path} \ # root directory of training data
--dict {path/of/dict} \ # path of dict
-o Global.use_gpu=False # whether to use gpu
...
```
2. Manually modify the configuration file
You can also manually modify the following fields in the template:
```
Global:
use_gpu: True
epoch_num: 500
...
character_type: it # language
character_dict_path: {path/of/dict} # path of dict
Train:
dataset:
name: SimpleDataSet
data_dir: train_data/ # root directory of training data
label_file_list: ["./train_data/train_list.txt"] # train label path
...
Eval:
dataset:
name: SimpleDataSet
data_dir: train_data/ # root directory of val data
label_file_list: ["./train_data/val_list.txt"] # val label path
...
```
Currently, the multi-language algorithms supported by PaddleOCR are:
| Configuration file | Algorithm name | backbone | trans | seq | pred | language | character_type |
| :--------: | :-------: | :-------: | :-------: | :-----: | :-----: | :-----: | :-----: |
| rec_chinese_cht_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | chinese traditional | chinese_cht|
| rec_en_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | English(Case sensitive) | EN |
| rec_french_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | French | french |
| rec_ger_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | German | german |
| rec_japan_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Japanese | japan |
| rec_korean_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Korean | korean |
| rec_it_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Italian | it |
| rec_xi_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Spanish | xi |
| rec_pu_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Portuguese | pu |
| rec_ru_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Russia | ru |
| rec_ar_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Arabic | ar |
| rec_hi_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Hindi | hi |
| rec_ug_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Uyghur | ug |
| rec_fa_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Persian(Farsi) | fa |
| rec_ur_ite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Urdu | ur |
| rec_rs_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Serbian(latin) | rs |
| rec_oc_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Occitan | oc |
| rec_mr_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Marathi | mr |
| rec_ne_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Nepali | ne |
| rec_rsc_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Serbian(cyrillic) | rsc |
| rec_bg_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Bulgarian | bg |
| rec_uk_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Ukranian | uk |
| rec_be_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Belarusian | be |
| rec_te_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Telugu | te |
| rec_ka_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Kannada | ka |
| rec_ta_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Tamil | ta |
The multi-language model training method is the same as the Chinese model. The training data set is 100w synthetic data. A small amount of fonts and test data can be downloaded on [Baidu Netdisk](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA),Extraction code:frgi. The multi-language model training method is the same as the Chinese model. The training data set is 100w synthetic data. A small amount of fonts and test data can be downloaded on [Baidu Netdisk](https://pan.baidu.com/s/1bS_u207Rm7YbY33wOECKDA),Extraction code:frgi.
......
文件已添加
文件已添加
文件已添加
文件已添加
文件已添加
文件已添加
文件已添加
文件已添加
doc/joinus.PNG

107.3 KB | W: | H:

doc/joinus.PNG

104.5 KB | W: | H:

doc/joinus.PNG
doc/joinus.PNG
doc/joinus.PNG
doc/joinus.PNG
  • 2-up
  • Swipe
  • Onion skin
...@@ -65,6 +65,7 @@ def build_dataloader(config, mode, device, logger, seed=None): ...@@ -65,6 +65,7 @@ def build_dataloader(config, mode, device, logger, seed=None):
loader_config = config[mode]['loader'] loader_config = config[mode]['loader']
batch_size = loader_config['batch_size_per_card'] batch_size = loader_config['batch_size_per_card']
drop_last = loader_config['drop_last'] drop_last = loader_config['drop_last']
shuffle = loader_config['shuffle']
num_workers = loader_config['num_workers'] num_workers = loader_config['num_workers']
if 'use_shared_memory' in loader_config.keys(): if 'use_shared_memory' in loader_config.keys():
use_shared_memory = loader_config['use_shared_memory'] use_shared_memory = loader_config['use_shared_memory']
...@@ -75,14 +76,14 @@ def build_dataloader(config, mode, device, logger, seed=None): ...@@ -75,14 +76,14 @@ def build_dataloader(config, mode, device, logger, seed=None):
batch_sampler = DistributedBatchSampler( batch_sampler = DistributedBatchSampler(
dataset=dataset, dataset=dataset,
batch_size=batch_size, batch_size=batch_size,
shuffle=False, shuffle=shuffle,
drop_last=drop_last) drop_last=drop_last)
else: else:
#Distribute data to single card #Distribute data to single card
batch_sampler = BatchSampler( batch_sampler = BatchSampler(
dataset=dataset, dataset=dataset,
batch_size=batch_size, batch_size=batch_size,
shuffle=False, shuffle=shuffle,
drop_last=drop_last) drop_last=drop_last)
data_loader = DataLoader( data_loader = DataLoader(
......
...@@ -18,6 +18,7 @@ from __future__ import print_function ...@@ -18,6 +18,7 @@ from __future__ import print_function
from __future__ import unicode_literals from __future__ import unicode_literals
import numpy as np import numpy as np
import string
class ClsLabelEncode(object): class ClsLabelEncode(object):
...@@ -92,7 +93,10 @@ class BaseRecLabelEncode(object): ...@@ -92,7 +93,10 @@ class BaseRecLabelEncode(object):
character_type='ch', character_type='ch',
use_space_char=False): use_space_char=False):
support_character_type = [ support_character_type = [
'ch', 'en', 'en_sensitive', 'french', 'german', 'japan', 'korean' 'ch', 'en', 'EN_symbol', 'french', 'german', 'japan', 'korean',
'EN', 'it', 'xi', 'pu', 'ru', 'ar', 'ta', 'ug', 'fa', 'ur', 'rs',
'oc', 'rsc', 'bg', 'uk', 'be', 'te', 'ka', 'chinese_cht', 'hi',
'mr', 'ne'
] ]
assert character_type in support_character_type, "Only {} are supported now but get {}".format( assert character_type in support_character_type, "Only {} are supported now but get {}".format(
support_character_type, character_type) support_character_type, character_type)
...@@ -103,9 +107,14 @@ class BaseRecLabelEncode(object): ...@@ -103,9 +107,14 @@ class BaseRecLabelEncode(object):
if character_type == "en": if character_type == "en":
self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz" self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
dict_character = list(self.character_str) dict_character = list(self.character_str)
elif character_type in ["ch", "french", "german", "japan", "korean"]: elif character_type == "EN_symbol":
# same with ASTER setting (use 94 char).
self.character_str = string.printable[:-6]
dict_character = list(self.character_str)
elif character_type in support_character_type:
self.character_str = "" self.character_str = ""
assert character_dict_path is not None, "character_dict_path should not be None when character_type is ch" assert character_dict_path is not None, "character_dict_path should not be None when character_type is {}".format(
character_type)
with open(character_dict_path, "rb") as fin: with open(character_dict_path, "rb") as fin:
lines = fin.readlines() lines = fin.readlines()
for line in lines: for line in lines:
...@@ -114,11 +123,6 @@ class BaseRecLabelEncode(object): ...@@ -114,11 +123,6 @@ class BaseRecLabelEncode(object):
if use_space_char: if use_space_char:
self.character_str += " " self.character_str += " "
dict_character = list(self.character_str) dict_character = list(self.character_str)
elif character_type == "en_sensitive":
# same with ASTER setting (use 94 char).
import string
self.character_str = string.printable[:-6]
dict_character = list(self.character_str)
self.character_type = character_type self.character_type = character_type
dict_character = self.add_special_char(dict_character) dict_character = self.add_special_char(dict_character)
self.dict = {} self.dict = {}
......
...@@ -58,15 +58,15 @@ class MobileNetV3(nn.Layer): ...@@ -58,15 +58,15 @@ class MobileNetV3(nn.Layer):
[5, 72, 40, True, 'relu', 2], [5, 72, 40, True, 'relu', 2],
[5, 120, 40, True, 'relu', 1], [5, 120, 40, True, 'relu', 1],
[5, 120, 40, True, 'relu', 1], [5, 120, 40, True, 'relu', 1],
[3, 240, 80, False, 'hard_swish', 2], [3, 240, 80, False, 'hardswish', 2],
[3, 200, 80, False, 'hard_swish', 1], [3, 200, 80, False, 'hardswish', 1],
[3, 184, 80, False, 'hard_swish', 1], [3, 184, 80, False, 'hardswish', 1],
[3, 184, 80, False, 'hard_swish', 1], [3, 184, 80, False, 'hardswish', 1],
[3, 480, 112, True, 'hard_swish', 1], [3, 480, 112, True, 'hardswish', 1],
[3, 672, 112, True, 'hard_swish', 1], [3, 672, 112, True, 'hardswish', 1],
[5, 672, 160, True, 'hard_swish', 2], [5, 672, 160, True, 'hardswish', 2],
[5, 960, 160, True, 'hard_swish', 1], [5, 960, 160, True, 'hardswish', 1],
[5, 960, 160, True, 'hard_swish', 1], [5, 960, 160, True, 'hardswish', 1],
] ]
cls_ch_squeeze = 960 cls_ch_squeeze = 960
elif model_name == "small": elif model_name == "small":
...@@ -75,14 +75,14 @@ class MobileNetV3(nn.Layer): ...@@ -75,14 +75,14 @@ class MobileNetV3(nn.Layer):
[3, 16, 16, True, 'relu', 2], [3, 16, 16, True, 'relu', 2],
[3, 72, 24, False, 'relu', 2], [3, 72, 24, False, 'relu', 2],
[3, 88, 24, False, 'relu', 1], [3, 88, 24, False, 'relu', 1],
[5, 96, 40, True, 'hard_swish', 2], [5, 96, 40, True, 'hardswish', 2],
[5, 240, 40, True, 'hard_swish', 1], [5, 240, 40, True, 'hardswish', 1],
[5, 240, 40, True, 'hard_swish', 1], [5, 240, 40, True, 'hardswish', 1],
[5, 120, 48, True, 'hard_swish', 1], [5, 120, 48, True, 'hardswish', 1],
[5, 144, 48, True, 'hard_swish', 1], [5, 144, 48, True, 'hardswish', 1],
[5, 288, 96, True, 'hard_swish', 2], [5, 288, 96, True, 'hardswish', 2],
[5, 576, 96, True, 'hard_swish', 1], [5, 576, 96, True, 'hardswish', 1],
[5, 576, 96, True, 'hard_swish', 1], [5, 576, 96, True, 'hardswish', 1],
] ]
cls_ch_squeeze = 576 cls_ch_squeeze = 576
else: else:
...@@ -102,7 +102,7 @@ class MobileNetV3(nn.Layer): ...@@ -102,7 +102,7 @@ class MobileNetV3(nn.Layer):
padding=1, padding=1,
groups=1, groups=1,
if_act=True, if_act=True,
act='hard_swish', act='hardswish',
name='conv1') name='conv1')
self.stages = [] self.stages = []
...@@ -112,7 +112,8 @@ class MobileNetV3(nn.Layer): ...@@ -112,7 +112,8 @@ class MobileNetV3(nn.Layer):
inplanes = make_divisible(inplanes * scale) inplanes = make_divisible(inplanes * scale)
for (k, exp, c, se, nl, s) in cfg: for (k, exp, c, se, nl, s) in cfg:
se = se and not self.disable_se se = se and not self.disable_se
if s == 2 and i > 2: start_idx = 2 if model_name == 'large' else 0
if s == 2 and i > start_idx:
self.out_channels.append(inplanes) self.out_channels.append(inplanes)
self.stages.append(nn.Sequential(*block_list)) self.stages.append(nn.Sequential(*block_list))
block_list = [] block_list = []
...@@ -137,7 +138,7 @@ class MobileNetV3(nn.Layer): ...@@ -137,7 +138,7 @@ class MobileNetV3(nn.Layer):
padding=0, padding=0,
groups=1, groups=1,
if_act=True, if_act=True,
act='hard_swish', act='hardswish',
name='conv_last')) name='conv_last'))
self.stages.append(nn.Sequential(*block_list)) self.stages.append(nn.Sequential(*block_list))
self.out_channels.append(make_divisible(scale * cls_ch_squeeze)) self.out_channels.append(make_divisible(scale * cls_ch_squeeze))
...@@ -191,10 +192,11 @@ class ConvBNLayer(nn.Layer): ...@@ -191,10 +192,11 @@ class ConvBNLayer(nn.Layer):
if self.if_act: if self.if_act:
if self.act == "relu": if self.act == "relu":
x = F.relu(x) x = F.relu(x)
elif self.act == "hard_swish": elif self.act == "hardswish":
x = F.activation.hard_swish(x) x = F.hardswish(x)
else: else:
print("The activation function is selected incorrectly.") print("The activation function({}) is selected incorrectly.".
format(self.act))
exit() exit()
return x return x
...@@ -281,5 +283,5 @@ class SEModule(nn.Layer): ...@@ -281,5 +283,5 @@ class SEModule(nn.Layer):
outputs = self.conv1(outputs) outputs = self.conv1(outputs)
outputs = F.relu(outputs) outputs = F.relu(outputs)
outputs = self.conv2(outputs) outputs = self.conv2(outputs)
outputs = F.activation.hard_sigmoid(outputs) outputs = F.hardsigmoid(outputs, slope=0.2, offset=0.5)
return inputs * outputs return inputs * outputs
...@@ -51,15 +51,15 @@ class MobileNetV3(nn.Layer): ...@@ -51,15 +51,15 @@ class MobileNetV3(nn.Layer):
[5, 72, 40, True, 'relu', (large_stride[2], 1)], [5, 72, 40, True, 'relu', (large_stride[2], 1)],
[5, 120, 40, True, 'relu', 1], [5, 120, 40, True, 'relu', 1],
[5, 120, 40, True, 'relu', 1], [5, 120, 40, True, 'relu', 1],
[3, 240, 80, False, 'hard_swish', 1], [3, 240, 80, False, 'hardswish', 1],
[3, 200, 80, False, 'hard_swish', 1], [3, 200, 80, False, 'hardswish', 1],
[3, 184, 80, False, 'hard_swish', 1], [3, 184, 80, False, 'hardswish', 1],
[3, 184, 80, False, 'hard_swish', 1], [3, 184, 80, False, 'hardswish', 1],
[3, 480, 112, True, 'hard_swish', 1], [3, 480, 112, True, 'hardswish', 1],
[3, 672, 112, True, 'hard_swish', 1], [3, 672, 112, True, 'hardswish', 1],
[5, 672, 160, True, 'hard_swish', (large_stride[3], 1)], [5, 672, 160, True, 'hardswish', (large_stride[3], 1)],
[5, 960, 160, True, 'hard_swish', 1], [5, 960, 160, True, 'hardswish', 1],
[5, 960, 160, True, 'hard_swish', 1], [5, 960, 160, True, 'hardswish', 1],
] ]
cls_ch_squeeze = 960 cls_ch_squeeze = 960
elif model_name == "small": elif model_name == "small":
...@@ -68,14 +68,14 @@ class MobileNetV3(nn.Layer): ...@@ -68,14 +68,14 @@ class MobileNetV3(nn.Layer):
[3, 16, 16, True, 'relu', (small_stride[0], 1)], [3, 16, 16, True, 'relu', (small_stride[0], 1)],
[3, 72, 24, False, 'relu', (small_stride[1], 1)], [3, 72, 24, False, 'relu', (small_stride[1], 1)],
[3, 88, 24, False, 'relu', 1], [3, 88, 24, False, 'relu', 1],
[5, 96, 40, True, 'hard_swish', (small_stride[2], 1)], [5, 96, 40, True, 'hardswish', (small_stride[2], 1)],
[5, 240, 40, True, 'hard_swish', 1], [5, 240, 40, True, 'hardswish', 1],
[5, 240, 40, True, 'hard_swish', 1], [5, 240, 40, True, 'hardswish', 1],
[5, 120, 48, True, 'hard_swish', 1], [5, 120, 48, True, 'hardswish', 1],
[5, 144, 48, True, 'hard_swish', 1], [5, 144, 48, True, 'hardswish', 1],
[5, 288, 96, True, 'hard_swish', (small_stride[3], 1)], [5, 288, 96, True, 'hardswish', (small_stride[3], 1)],
[5, 576, 96, True, 'hard_swish', 1], [5, 576, 96, True, 'hardswish', 1],
[5, 576, 96, True, 'hard_swish', 1], [5, 576, 96, True, 'hardswish', 1],
] ]
cls_ch_squeeze = 576 cls_ch_squeeze = 576
else: else:
...@@ -96,7 +96,7 @@ class MobileNetV3(nn.Layer): ...@@ -96,7 +96,7 @@ class MobileNetV3(nn.Layer):
padding=1, padding=1,
groups=1, groups=1,
if_act=True, if_act=True,
act='hard_swish', act='hardswish',
name='conv1') name='conv1')
i = 0 i = 0
block_list = [] block_list = []
...@@ -124,7 +124,7 @@ class MobileNetV3(nn.Layer): ...@@ -124,7 +124,7 @@ class MobileNetV3(nn.Layer):
padding=0, padding=0,
groups=1, groups=1,
if_act=True, if_act=True,
act='hard_swish', act='hardswish',
name='conv_last') name='conv_last')
self.pool = nn.MaxPool2D(kernel_size=2, stride=2, padding=0) self.pool = nn.MaxPool2D(kernel_size=2, stride=2, padding=0)
......
...@@ -12,6 +12,7 @@ ...@@ -12,6 +12,7 @@
# See the License for the specific language governing permissions and # See the License for the specific language governing permissions and
# limitations under the License. # limitations under the License.
import numpy as np import numpy as np
import string
import paddle import paddle
from paddle.nn import functional as F from paddle.nn import functional as F
...@@ -24,9 +25,10 @@ class BaseRecLabelDecode(object): ...@@ -24,9 +25,10 @@ class BaseRecLabelDecode(object):
character_type='ch', character_type='ch',
use_space_char=False): use_space_char=False):
support_character_type = [ support_character_type = [
'ch', 'en', 'en_sensitive', 'french', 'german', 'japan', 'korean', 'it', 'ch', 'en', 'EN_symbol', 'french', 'german', 'japan', 'korean',
'xi', 'pu', 'ru', 'ar', 'ta', 'ug', 'fa', 'ur', 'rs', 'oc', 'rsc', 'bg', 'it', 'xi', 'pu', 'ru', 'ar', 'ta', 'ug', 'fa', 'ur', 'rs', 'oc',
'uk', 'be', 'te', 'ka', 'chinese_cht', 'hi', 'mr', 'ne' 'rsc', 'bg', 'uk', 'be', 'te', 'ka', 'chinese_cht', 'hi', 'mr',
'ne', 'EN'
] ]
assert character_type in support_character_type, "Only {} are supported now but get {}".format( assert character_type in support_character_type, "Only {} are supported now but get {}".format(
support_character_type, character_type) support_character_type, character_type)
...@@ -37,9 +39,14 @@ class BaseRecLabelDecode(object): ...@@ -37,9 +39,14 @@ class BaseRecLabelDecode(object):
if character_type == "en": if character_type == "en":
self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz" self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
dict_character = list(self.character_str) dict_character = list(self.character_str)
elif character_type in ["ch", "french", "german", "japan", "korean"]: elif character_type == "EN_symbol":
# same with ASTER setting (use 94 char).
self.character_str = string.printable[:-6]
dict_character = list(self.character_str)
elif character_type in support_character_type:
self.character_str = "" self.character_str = ""
assert character_dict_path is not None, "character_dict_path should not be None when character_type is ch" assert character_dict_path is not None, "character_dict_path should not be None when character_type is {}".format(
character_type)
with open(character_dict_path, "rb") as fin: with open(character_dict_path, "rb") as fin:
lines = fin.readlines() lines = fin.readlines()
for line in lines: for line in lines:
...@@ -48,11 +55,7 @@ class BaseRecLabelDecode(object): ...@@ -48,11 +55,7 @@ class BaseRecLabelDecode(object):
if use_space_char: if use_space_char:
self.character_str += " " self.character_str += " "
dict_character = list(self.character_str) dict_character = list(self.character_str)
elif character_type == "en_sensitive":
# same with ASTER setting (use 94 char).
import string
self.character_str = string.printable[:-6]
dict_character = list(self.character_str)
else: else:
raise NotImplementedError raise NotImplementedError
self.character_type = character_type self.character_type = character_type
......
...@@ -75,10 +75,17 @@ def main(): ...@@ -75,10 +75,17 @@ def main():
] ]
] ]
model = to_static(model, input_spec=other_shape) model = to_static(model, input_spec=other_shape)
else: else:
infer_shape = [3, 32, 100] if config['Architecture'][ infer_shape = [3, -1, -1]
'model_type'] != "det" else [3, 640, 640] if config['Architecture']['model_type'] == "rec":
infer_shape = [3, 32, -1] # for rec model, H must be 32
if 'Transform' in config['Architecture'] and config['Architecture'][
'Transform'] is not None and config['Architecture'][
'Transform']['name'] == 'TPS':
logger.info(
'When there is tps in the network, variable length input is not supported, and the input size needs to be the same as during training'
)
infer_shape[-1] = 100
model = to_static( model = to_static(
model, model,
input_spec=[ input_spec=[
......
...@@ -70,7 +70,7 @@ def parse_args(): ...@@ -70,7 +70,7 @@ def parse_args():
default="./ppocr/utils/ppocr_keys_v1.txt") default="./ppocr/utils/ppocr_keys_v1.txt")
parser.add_argument("--use_space_char", type=str2bool, default=True) parser.add_argument("--use_space_char", type=str2bool, default=True)
parser.add_argument( parser.add_argument(
"--vis_font_path", type=str, default="./doc/simfang.ttf") "--vis_font_path", type=str, default="./doc/fonts/simfang.ttf")
parser.add_argument("--drop_score", type=float, default=0.5) parser.add_argument("--drop_score", type=float, default=0.5)
# params for text classifier # params for text classifier
......
...@@ -218,7 +218,7 @@ def train(config, ...@@ -218,7 +218,7 @@ def train(config,
stats['lr'] = lr stats['lr'] = lr
train_stats.update(stats) train_stats.update(stats)
if cal_metric_during_train: # onlt rec and cls need if cal_metric_during_train: # only rec and cls need
batch = [item.numpy() for item in batch] batch = [item.numpy() for item in batch]
post_result = post_process_class(preds, batch[1]) post_result = post_process_class(preds, batch[1])
eval_class(post_result, batch) eval_class(post_result, batch)
...@@ -253,19 +253,19 @@ def train(config, ...@@ -253,19 +253,19 @@ def train(config,
Model_Average.apply() Model_Average.apply()
cur_metirc = eval(model, valid_dataloader, post_process_class, cur_metirc = eval(model, valid_dataloader, post_process_class,
eval_class) eval_class)
cur_metirc_str = 'cur metirc, {}'.format(', '.join( cur_metric_str = 'cur metric, {}'.format(', '.join(
['{}: {}'.format(k, v) for k, v in cur_metirc.items()])) ['{}: {}'.format(k, v) for k, v in cur_metric.items()]))
logger.info(cur_metirc_str) logger.info(cur_metric_str)
# logger metric # logger metric
if vdl_writer is not None: if vdl_writer is not None:
for k, v in cur_metirc.items(): for k, v in cur_metric.items():
if isinstance(v, (float, int)): if isinstance(v, (float, int)):
vdl_writer.add_scalar('EVAL/{}'.format(k), vdl_writer.add_scalar('EVAL/{}'.format(k),
cur_metirc[k], global_step) cur_metric[k], global_step)
if cur_metirc[main_indicator] >= best_model_dict[ if cur_metric[main_indicator] >= best_model_dict[
main_indicator]: main_indicator]:
best_model_dict.update(cur_metirc) best_model_dict.update(cur_metric)
best_model_dict['best_epoch'] = epoch best_model_dict['best_epoch'] = epoch
save_model( save_model(
model, model,
...@@ -276,7 +276,7 @@ def train(config, ...@@ -276,7 +276,7 @@ def train(config,
prefix='best_accuracy', prefix='best_accuracy',
best_model_dict=best_model_dict, best_model_dict=best_model_dict,
epoch=epoch) epoch=epoch)
best_str = 'best metirc, {}'.format(', '.join([ best_str = 'best metric, {}'.format(', '.join([
'{}: {}'.format(k, v) for k, v in best_model_dict.items() '{}: {}'.format(k, v) for k, v in best_model_dict.items()
])) ]))
logger.info(best_str) logger.info(best_str)
...@@ -308,7 +308,7 @@ def train(config, ...@@ -308,7 +308,7 @@ def train(config,
prefix='iter_epoch_{}'.format(epoch), prefix='iter_epoch_{}'.format(epoch),
best_model_dict=best_model_dict, best_model_dict=best_model_dict,
epoch=epoch) epoch=epoch)
best_str = 'best metirc, {}'.format(', '.join( best_str = 'best metric, {}'.format(', '.join(
['{}: {}'.format(k, v) for k, v in best_model_dict.items()])) ['{}: {}'.format(k, v) for k, v in best_model_dict.items()]))
logger.info(best_str) logger.info(best_str)
if dist.get_rank() == 0 and vdl_writer is not None: if dist.get_rank() == 0 and vdl_writer is not None:
...@@ -338,13 +338,13 @@ def eval(model, valid_dataloader, post_process_class, eval_class): ...@@ -338,13 +338,13 @@ def eval(model, valid_dataloader, post_process_class, eval_class):
eval_class(post_result, batch) eval_class(post_result, batch)
pbar.update(1) pbar.update(1)
total_frame += len(images) total_frame += len(images)
# Get final metirc,eg. acc or hmean # Get final metric,eg. acc or hmean
metirc = eval_class.get_metric() metric = eval_class.get_metric()
pbar.close() pbar.close()
model.train() model.train()
metirc['fps'] = total_frame / total_time metric['fps'] = total_frame / total_time
return metirc return metric
def preprocess(is_train=False): def preprocess(is_train=False):
......
# for paddle.__version__ >= 2.0rc1 # recommended paddle.__version__ == 2.0.0
python3 -m paddle.distributed.launch --gpus '0,1,2,3,4,5,6,7' tools/train.py -c configs/rec/rec_mv3_none_bilstm_ctc.yml python3 -m paddle.distributed.launch --gpus '0,1,2,3,4,5,6,7' tools/train.py -c configs/rec/rec_mv3_none_bilstm_ctc.yml
# for paddle.__version__ < 2.0rc1
# python3 -m paddle.distributed.launch --selected_gpus '0,1,2,3,4,5,6,7' tools/train.py -c configs/rec/rec_mv3_none_bilstm_ctc.yml
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册