diff --git a/PPOCRLabel/PPOCRLabel.py b/PPOCRLabel/PPOCRLabel.py
index 4d9c52740a5ca5bcdd891bb55ff769f23e7a2499..efe00a33b7917c8f8dd0965fb69f019c37b55e84 100644
--- a/PPOCRLabel/PPOCRLabel.py
+++ b/PPOCRLabel/PPOCRLabel.py
@@ -1031,7 +1031,7 @@ class MainWindow(QMainWindow, WindowMixin):
for box in self.result_dic:
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
shapes.append(trans_dic)
@@ -1764,7 +1764,7 @@ class MainWindow(QMainWindow, WindowMixin):
QMessageBox.information(self, "Information", msg)
return
result = self.ocr.ocr(img_crop, cls=True, det=False)
- if result[0][0] is not '':
+ if result[0][0] != '':
result.insert(0, box)
print('result in reRec is ', result)
self.result_dic.append(result)
@@ -1795,7 +1795,7 @@ class MainWindow(QMainWindow, WindowMixin):
QMessageBox.information(self, "Information", msg)
return
result = self.ocr.ocr(img_crop, cls=True, det=False)
- if result[0][0] is not '':
+ if result[0][0] != '':
result.insert(0, box)
print('result in reRec is ', result)
if result[1][0] == shape.label:
@@ -1991,7 +1991,7 @@ if __name__ == '__main__':
resource_file = './libs/resources.py'
if not os.path.exists(resource_file):
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 "
import libs.resources
sys.exit(main())
diff --git a/README.md b/README.md
index 5b6e4bd0b594d71edd3ab4f8da350475c3ac83b8..67d65e98e8d7b978e25d9582cf21d2b222858e69 100644
--- a/README.md
+++ b/README.md
@@ -5,10 +5,11 @@ PaddleOCR aims to create multilingual, awesome, leading, and practical OCR tools
## Notice
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
**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.
- 2020.11.25 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
diff --git a/README_ch.md b/README_ch.md
index e2e96a6bc5a126f8193e069ae37f403e37824891..d627ec450f8260d1b88593ea14d9172d03016b5f 100755
--- a/README_ch.md
+++ b/README_ch.md
@@ -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。
## 注意
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
**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。
+- 2021.1.21 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。
- 2020.11.25 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
diff --git a/StyleText/README.md b/StyleText/README.md
index df4fbf3cfed44b26d690f70e2ab0d4b5c0aa1ff0..65a72ac808f5f875e1f42369e7d588027e9508a2 100644
--- a/StyleText/README.md
+++ b/StyleText/README.md
@@ -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
```
-* 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.
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.
@@ -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.
* `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`.
- * `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.
diff --git a/StyleText/README_ch.md b/StyleText/README_ch.md
index fd259ca018efcdcf6bdd1040ee1642424c120ae7..ccd1efaf1afae2c21c746f989e9b86bfed19e74b 100644
--- a/StyleText/README_ch.md
+++ b/StyleText/README_ch.md
@@ -63,10 +63,10 @@ fusion_generator:
```python
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。
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":
@@ -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。
* `CorpusGenerator`：
* `method`：语料生成方法，目前有`FileCorpus`和`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`和`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。
语料文件格式示例：
diff --git a/configs/rec/multi_language/rec_en_number_lite_train.yml b/configs/rec/multi_language/rec_en_number_lite_train.yml
index cee0512114fe9d488004a71cf6f0a0409822a4b5..13eda8481cad8ca308cd0629214b52146c3ebf13 100644
--- a/configs/rec/multi_language/rec_en_number_lite_train.yml
+++ b/configs/rec/multi_language/rec_en_number_lite_train.yml
@@ -16,7 +16,7 @@ Global:
infer_img:
# for data or label process
character_dict_path: ppocr/utils/dict/en_dict.txt
- character_type: ch
+ character_type: EN
max_text_length: 25
infer_mode: False
use_space_char: False
diff --git a/deploy/slim/quantization/README.md b/deploy/slim/quantization/README.md
index ccd4d06b4f16165f968402751b63a8fe58773e0b..4ac3f7c3016c9ef53724ad6f7745507cef3580a8 100644
--- a/deploy/slim/quantization/README.md
+++ b/deploy/slim/quantization/README.md
@@ -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
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
-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。
diff --git a/deploy/slim/quantization/README_en.md b/deploy/slim/quantization/README_en.md
index 7da0b3e7e7d5f72e45dc17864630b9725f6fc8ba..36407a2bb58ee3a36afc211ca7a8f0d786d1714f 100644
--- a/deploy/slim/quantization/README_en.md
+++ b/deploy/slim/quantization/README_en.md
@@ -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:
```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
diff --git a/doc/doc_ch/FAQ.md b/doc/doc_ch/FAQ.md
index bb61689bfae403062ba77ca6bb39719ef7d93725..11a9f35d9e8a92c9bef0da68e085739c1b1e821c 100755
--- a/doc/doc_ch/FAQ.md
+++ b/doc/doc_ch/FAQ.md
@@ -31,7 +31,7 @@
#### 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？
@@ -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。
#### 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)
-**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:
`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`。
@@ -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。
- 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。
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
#### 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？
@@ -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？
-**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？
@@ -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’。
-**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。
### 数据集
@@ -877,4 +877,4 @@ img = cv.imdecode(img_array, -1)
**A**：我们目前已经通过Paddle2ONNX来支持各模型套件的转换，PaddleOCR基于PaddlePaddle 2.0的版本（dygraph分支）已经支持导出为ONNX，欢迎关注Paddle2ONNX，了解更多项目的进展：
Paddle2ONNX项目：https://github.com/PaddlePaddle/Paddle2ONNX
-Paddle2ONNX支持转换的[模型列表](https://github.com/PaddlePaddle/Paddle2ONNX/blob/develop/docs/zh/model_zoo.md#%E5%9B%BE%E5%83%8Focr)
\ No newline at end of file
+Paddle2ONNX支持转换的[模型列表](https://github.com/PaddlePaddle/Paddle2ONNX/blob/develop/docs/zh/model_zoo.md#%E5%9B%BE%E5%83%8Focr)
diff --git a/doc/doc_ch/angle_class.md b/doc/doc_ch/angle_class.md
index 4d7ff0d7aa839591df6e359d4f7295ab2f0cc445..6e68134a4d1b8d9b8927d67c9724ba88563383a4 100644
--- a/doc/doc_ch/angle_class.md
+++ b/doc/doc_ch/angle_class.md
@@ -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*
```
-# 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
python3 -m paddle.distributed.launch --gpus '0,1,2,3,4,5,6,7' tools/train.py -c configs/cls/cls_mv3.yml
```
diff --git a/doc/doc_ch/detection.md b/doc/doc_ch/detection.md
index 8f0f69796a38ac16643e1168c3ecf73b92daa19a..a8dee65a220e3c66d8502181dd2a542cb01a29b5 100644
--- a/doc/doc_ch/detection.md
+++ b/doc/doc_ch/detection.md
@@ -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
python3 tools/train.py -c configs/det/det_mv3_db.yml \
-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 \
-o Global.pretrain_weights=./pretrain_models/MobileNetV3_large_x0_5_pretrained/
```
diff --git a/doc/doc_ch/inference.md b/doc/doc_ch/inference.md
index ab5487037e69d40e38dde96fc8006022054f31df..c4601e1526d29e0a8c62030a4b47d2b2cc193d5d 100755
--- a/doc/doc_ch/inference.md
+++ b/doc/doc_ch/inference.md
@@ -306,10 +306,10 @@ python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png
### 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，
-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"
```
diff --git a/doc/doc_ch/installation.md b/doc/doc_ch/installation.md
index 36565cd4197a9b8b8404f57b378aa49637cdc58b..fce151eb9fee567477c09eee211633f7377dddb3 100644
--- a/doc/doc_ch/installation.md
+++ b/doc/doc_ch/installation.md
@@ -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
PaddleOCR 工作环境
-- PaddlePaddle 1.8+ ，推荐使用 PaddlePaddle 2.0rc1
+- PaddlePaddle 2.0.0
- python3.7
- glibc 2.23
- cuDNN 7.6+ (GPU)
@@ -35,11 +35,11 @@ sudo docker container exec -it ppocr /bin/bash
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
-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
-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。
```
diff --git a/doc/doc_ch/recognition.md b/doc/doc_ch/recognition.md
index b473f3ac0a5007dee6ac5773e2b989454d4b8983..c5f459bdb88558b1cdea93b9b85eed0e4bb8433b 100644
--- a/doc/doc_ch/recognition.md
+++ b/doc/doc_ch/recognition.md
@@ -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_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_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 |
@@ -272,16 +270,109 @@ Eval:
- 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 |
-| :--------: | :-------: | :-------: | :-------: | :-----: | :-----: | :-----: |
-| 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 |
+您有两种方式创建所需的配置文件：
+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。
diff --git a/doc/doc_en/angle_class_en.md b/doc/doc_en/angle_class_en.md
index 8d9328700f3e638eb4576d132aa32fb93b3ad0c0..d1cc712f312bf8e70c0b399422519217df323129 100644
--- a/doc/doc_en/angle_class_en.md
+++ b/doc/doc_en/angle_class_en.md
@@ -66,7 +66,7 @@ Start training:
```
# Set PYTHONPATH path
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
python3 -m paddle.distributed.launch --gpus '0,1,2,3,4,5,6,7' tools/train.py -c configs/cls/cls_mv3.yml
```
diff --git a/doc/doc_en/detection_en.md b/doc/doc_en/detection_en.md
index 5c4a63e23ed4fe8f6d398bc68dec830bef6c09c9..3ee9092cc6a6f50b19f20df646c9cb1949d5d80f 100644
--- a/doc/doc_en/detection_en.md
+++ b/doc/doc_en/detection_en.md
@@ -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
# 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
diff --git a/doc/doc_en/inference_en.md b/doc/doc_en/inference_en.md
index 98e3ef6378480022baaf6e82843294dab3fbcaf4..ccbb71847d5946e854b88817a162957af0e6ed00 100755
--- a/doc/doc_en/inference_en.md
+++ b/doc/doc_en/inference_en.md
@@ -315,10 +315,10 @@ python3 tools/infer/predict_rec.py --image_dir="./doc/imgs_words_en/word_336.png
### 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,
-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"
```
diff --git a/doc/doc_en/installation_en.md b/doc/doc_en/installation_en.md
index 7f1f0e83c94e4d4a18b99d620b4b192c47ffde7c..35c1881d12087e6509a68b504729d9ef20240e9c 100644
--- a/doc/doc_en/installation_en.md
+++ b/doc/doc_en/installation_en.md
@@ -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.
PaddleOCR working environment:
-- PaddlePaddle 1.8+, Recommend PaddlePaddle 2.0rc1
+- PaddlePaddle 2.0.0
- python3.7
- glibc 2.23
@@ -38,10 +38,10 @@ sudo docker container exec -it ppocr /bin/bash
pip3 install --upgrade pip
# 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
-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.
diff --git a/doc/doc_en/models_list_en.md b/doc/doc_en/models_list_en.md
index 3eb0cd237801aa62d1c741c177be7b73d9c08808..33033f8348fa4fb08d6e8998ff53cd62349c214e 100644
--- a/doc/doc_en/models_list_en.md
+++ b/doc/doc_en/models_list_en.md
@@ -93,7 +93,7 @@ python3 generate_multi_language_configs.py -l it \
|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) |
-| 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) |
| 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) |
diff --git a/doc/doc_en/recognition_en.md b/doc/doc_en/recognition_en.md
index 7723d20b9f982bc2c121965f4cd7996c81aa42d5..22f89cdef080afe0b119d08d1e88f02ede5932c1 100644
--- a/doc/doc_en/recognition_en.md
+++ b/doc/doc_en/recognition_en.md
@@ -266,15 +266,116 @@ Eval:
- 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:
-
-| Configuration file | Algorithm name | backbone | trans | seq | pred | language ｜
-| :--------: | :-------: | :-------: | :-------: | :-----: | :-----: | :-----: |
-| 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 ｜
-| 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 ｜
-| rec_korean_lite_train.yml | CRNN | Mobilenet_v3 small 0.5 | None | BiLSTM | ctc | Korean ｜
+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)。
+
+There are two ways to create the required configuration file:：
+
+1. Automatically generated by script
+
+[generate_multi_language_configs.py](../../configs/rec/multi_language/generate_multi_language_configs.py) Can help you generate configuration files for multi-language models
+
+- 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.
diff --git a/doc/fonts/arabic.ttf b/doc/fonts/arabic.ttf
new file mode 100644
index 0000000000000000000000000000000000000000..064b6041ee32814d852e084f639dae75d044d357
Binary files /dev/null and b/doc/fonts/arabic.ttf differ
diff --git a/doc/fonts/chinese_cht.ttf b/doc/fonts/chinese_cht.ttf
new file mode 100644
index 0000000000000000000000000000000000000000..3416754fd35aecd6eb0d9acfc730ae10a408bffd
Binary files /dev/null and b/doc/fonts/chinese_cht.ttf differ
diff --git a/doc/fonts/cyrillic.ttf b/doc/fonts/cyrillic.ttf
new file mode 100644
index 0000000000000000000000000000000000000000..be4bf6605808d15ab25c9cbbe1fda2a1d190ac8b
Binary files /dev/null and b/doc/fonts/cyrillic.ttf differ
diff --git a/doc/french.ttf b/doc/fonts/french.ttf
similarity index 100%
rename from doc/french.ttf
rename to doc/fonts/french.ttf
diff --git a/doc/german.ttf b/doc/fonts/german.ttf
similarity index 100%
rename from doc/german.ttf
rename to doc/fonts/german.ttf
diff --git a/doc/fonts/hindi.ttf b/doc/fonts/hindi.ttf
new file mode 100644
index 0000000000000000000000000000000000000000..8b0c36f5868b935464f30883094b9556c3e41009
Binary files /dev/null and b/doc/fonts/hindi.ttf differ
diff --git a/doc/japan.ttc b/doc/fonts/japan.ttc
similarity index 100%
rename from doc/japan.ttc
rename to doc/fonts/japan.ttc
diff --git a/doc/fonts/kannada.ttf b/doc/fonts/kannada.ttf
new file mode 100644
index 0000000000000000000000000000000000000000..43b60d423ad5ea5f5528c9c9e5d6f013f87fa1d7
Binary files /dev/null and b/doc/fonts/kannada.ttf differ
diff --git a/doc/korean.ttf b/doc/fonts/korean.ttf
similarity index 100%
rename from doc/korean.ttf
rename to doc/fonts/korean.ttf
diff --git a/doc/fonts/latin.ttf b/doc/fonts/latin.ttf
new file mode 100644
index 0000000000000000000000000000000000000000..e392413ac2f82905b3c07073669c3e2058d20235
Binary files /dev/null and b/doc/fonts/latin.ttf differ
diff --git a/doc/fonts/marathi.ttf b/doc/fonts/marathi.ttf
new file mode 100644
index 0000000000000000000000000000000000000000..a796d3edc6a4cc140a9360d0fc502a9d99352db0
Binary files /dev/null and b/doc/fonts/marathi.ttf differ
diff --git a/doc/fonts/nepali.ttf b/doc/fonts/nepali.ttf
new file mode 100644
index 0000000000000000000000000000000000000000..8b0c36f5868b935464f30883094b9556c3e41009
Binary files /dev/null and b/doc/fonts/nepali.ttf differ
diff --git a/doc/fonts/persian.ttf b/doc/fonts/persian.ttf
new file mode 100644
index 0000000000000000000000000000000000000000..bdb1c8d7402148127b7633c6b4cd1586e23745ab
Binary files /dev/null and b/doc/fonts/persian.ttf differ
diff --git a/doc/simfang.ttf b/doc/fonts/simfang.ttf
similarity index 100%
rename from doc/simfang.ttf
rename to doc/fonts/simfang.ttf
diff --git a/doc/fonts/spanish.ttf b/doc/fonts/spanish.ttf
new file mode 100644
index 0000000000000000000000000000000000000000..532353d2778cd2bb37a5baf06f5daeea32729168
Binary files /dev/null and b/doc/fonts/spanish.ttf differ
diff --git a/doc/fonts/tamil.ttf b/doc/fonts/tamil.ttf
new file mode 100644
index 0000000000000000000000000000000000000000..2e9998e8d8218f1e868f06ba0db3e13b4620eed1
Binary files /dev/null and b/doc/fonts/tamil.ttf differ
diff --git a/doc/fonts/telugu.ttf b/doc/fonts/telugu.ttf
new file mode 100644
index 0000000000000000000000000000000000000000..12c91e41973a4704f52984e2089fdb2eaf1ed4a5
Binary files /dev/null and b/doc/fonts/telugu.ttf differ
diff --git a/doc/fonts/urdu.ttf b/doc/fonts/urdu.ttf
new file mode 100644
index 0000000000000000000000000000000000000000..625feee2e9616809c13e17eeb7da1aec58988b65
Binary files /dev/null and b/doc/fonts/urdu.ttf differ
diff --git a/doc/fonts/uyghur.ttf b/doc/fonts/uyghur.ttf
new file mode 100644
index 0000000000000000000000000000000000000000..625feee2e9616809c13e17eeb7da1aec58988b65
Binary files /dev/null and b/doc/fonts/uyghur.ttf differ
diff --git a/doc/joinus.PNG b/doc/joinus.PNG
index ee505a0c78b8625b0faadc9a6bc28980440158e5..22258be049c275567953018f26f6d3949297e72e 100644
Binary files a/doc/joinus.PNG and b/doc/joinus.PNG differ
diff --git a/ppocr/data/__init__.py b/ppocr/data/__init__.py
index 231cee196fbcfb9e960b34587ec6044ead51a005..7cb50d7a62aa3f24811e517768e0635ac7b7321a 100644
--- a/ppocr/data/__init__.py
+++ b/ppocr/data/__init__.py
@@ -65,6 +65,7 @@ def build_dataloader(config, mode, device, logger, seed=None):
loader_config = config[mode]['loader']
batch_size = loader_config['batch_size_per_card']
drop_last = loader_config['drop_last']
+ shuffle = loader_config['shuffle']
num_workers = loader_config['num_workers']
if 'use_shared_memory' in loader_config.keys():
use_shared_memory = loader_config['use_shared_memory']
@@ -75,14 +76,14 @@ def build_dataloader(config, mode, device, logger, seed=None):
batch_sampler = DistributedBatchSampler(
dataset=dataset,
batch_size=batch_size,
- shuffle=False,
+ shuffle=shuffle,
drop_last=drop_last)
else:
#Distribute data to single card
batch_sampler = BatchSampler(
dataset=dataset,
batch_size=batch_size,
- shuffle=False,
+ shuffle=shuffle,
drop_last=drop_last)
data_loader = DataLoader(
diff --git a/ppocr/data/imaug/label_ops.py b/ppocr/data/imaug/label_ops.py
index 986cec3dba2a30bf9698cbd22b6a46c5279432ae..61c0c196b3a48911707dc5210a410145ec93a76d 100644
--- a/ppocr/data/imaug/label_ops.py
+++ b/ppocr/data/imaug/label_ops.py
@@ -18,6 +18,7 @@ from __future__ import print_function
from __future__ import unicode_literals
import numpy as np
+import string
class ClsLabelEncode(object):
@@ -92,7 +93,10 @@ class BaseRecLabelEncode(object):
character_type='ch',
use_space_char=False):
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(
support_character_type, character_type)
@@ -103,9 +107,14 @@ class BaseRecLabelEncode(object):
if character_type == "en":
self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
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 = ""
- 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:
lines = fin.readlines()
for line in lines:
@@ -114,11 +123,6 @@ class BaseRecLabelEncode(object):
if use_space_char:
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
dict_character = self.add_special_char(dict_character)
self.dict = {}
diff --git a/ppocr/modeling/backbones/det_mobilenet_v3.py b/ppocr/modeling/backbones/det_mobilenet_v3.py
index f97bcfca472310cfd681025595b7bce57d1ccf85..bb451bbec9327e2624ab0d501a7adf4355dc3407 100755
--- a/ppocr/modeling/backbones/det_mobilenet_v3.py
+++ b/ppocr/modeling/backbones/det_mobilenet_v3.py
@@ -58,15 +58,15 @@ class MobileNetV3(nn.Layer):
[5, 72, 40, True, 'relu', 2],
[5, 120, 40, True, 'relu', 1],
[5, 120, 40, True, 'relu', 1],
- [3, 240, 80, False, 'hard_swish', 2],
- [3, 200, 80, False, 'hard_swish', 1],
- [3, 184, 80, False, 'hard_swish', 1],
- [3, 184, 80, False, 'hard_swish', 1],
- [3, 480, 112, True, 'hard_swish', 1],
- [3, 672, 112, True, 'hard_swish', 1],
- [5, 672, 160, True, 'hard_swish', 2],
- [5, 960, 160, True, 'hard_swish', 1],
- [5, 960, 160, True, 'hard_swish', 1],
+ [3, 240, 80, False, 'hardswish', 2],
+ [3, 200, 80, False, 'hardswish', 1],
+ [3, 184, 80, False, 'hardswish', 1],
+ [3, 184, 80, False, 'hardswish', 1],
+ [3, 480, 112, True, 'hardswish', 1],
+ [3, 672, 112, True, 'hardswish', 1],
+ [5, 672, 160, True, 'hardswish', 2],
+ [5, 960, 160, True, 'hardswish', 1],
+ [5, 960, 160, True, 'hardswish', 1],
]
cls_ch_squeeze = 960
elif model_name == "small":
@@ -75,14 +75,14 @@ class MobileNetV3(nn.Layer):
[3, 16, 16, True, 'relu', 2],
[3, 72, 24, False, 'relu', 2],
[3, 88, 24, False, 'relu', 1],
- [5, 96, 40, True, 'hard_swish', 2],
- [5, 240, 40, True, 'hard_swish', 1],
- [5, 240, 40, True, 'hard_swish', 1],
- [5, 120, 48, True, 'hard_swish', 1],
- [5, 144, 48, True, 'hard_swish', 1],
- [5, 288, 96, True, 'hard_swish', 2],
- [5, 576, 96, True, 'hard_swish', 1],
- [5, 576, 96, True, 'hard_swish', 1],
+ [5, 96, 40, True, 'hardswish', 2],
+ [5, 240, 40, True, 'hardswish', 1],
+ [5, 240, 40, True, 'hardswish', 1],
+ [5, 120, 48, True, 'hardswish', 1],
+ [5, 144, 48, True, 'hardswish', 1],
+ [5, 288, 96, True, 'hardswish', 2],
+ [5, 576, 96, True, 'hardswish', 1],
+ [5, 576, 96, True, 'hardswish', 1],
]
cls_ch_squeeze = 576
else:
@@ -102,7 +102,7 @@ class MobileNetV3(nn.Layer):
padding=1,
groups=1,
if_act=True,
- act='hard_swish',
+ act='hardswish',
name='conv1')
self.stages = []
@@ -112,7 +112,8 @@ class MobileNetV3(nn.Layer):
inplanes = make_divisible(inplanes * scale)
for (k, exp, c, se, nl, s) in cfg:
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.stages.append(nn.Sequential(*block_list))
block_list = []
@@ -137,7 +138,7 @@ class MobileNetV3(nn.Layer):
padding=0,
groups=1,
if_act=True,
- act='hard_swish',
+ act='hardswish',
name='conv_last'))
self.stages.append(nn.Sequential(*block_list))
self.out_channels.append(make_divisible(scale * cls_ch_squeeze))
@@ -191,10 +192,11 @@ class ConvBNLayer(nn.Layer):
if self.if_act:
if self.act == "relu":
x = F.relu(x)
- elif self.act == "hard_swish":
- x = F.activation.hard_swish(x)
+ elif self.act == "hardswish":
+ x = F.hardswish(x)
else:
- print("The activation function is selected incorrectly.")
+ print("The activation function({}) is selected incorrectly.".
+ format(self.act))
exit()
return x
@@ -281,5 +283,5 @@ class SEModule(nn.Layer):
outputs = self.conv1(outputs)
outputs = F.relu(outputs)
outputs = self.conv2(outputs)
- outputs = F.activation.hard_sigmoid(outputs)
+ outputs = F.hardsigmoid(outputs, slope=0.2, offset=0.5)
return inputs * outputs
diff --git a/ppocr/modeling/backbones/rec_mobilenet_v3.py b/ppocr/modeling/backbones/rec_mobilenet_v3.py
index bdf4a616d2cf03275ba311cff625a78d0140e442..1ff17159680372b00e6943e180e5fb638b39ec58 100644
--- a/ppocr/modeling/backbones/rec_mobilenet_v3.py
+++ b/ppocr/modeling/backbones/rec_mobilenet_v3.py
@@ -51,15 +51,15 @@ class MobileNetV3(nn.Layer):
[5, 72, 40, True, 'relu', (large_stride[2], 1)],
[5, 120, 40, True, 'relu', 1],
[5, 120, 40, True, 'relu', 1],
- [3, 240, 80, False, 'hard_swish', 1],
- [3, 200, 80, False, 'hard_swish', 1],
- [3, 184, 80, False, 'hard_swish', 1],
- [3, 184, 80, False, 'hard_swish', 1],
- [3, 480, 112, True, 'hard_swish', 1],
- [3, 672, 112, True, 'hard_swish', 1],
- [5, 672, 160, True, 'hard_swish', (large_stride[3], 1)],
- [5, 960, 160, True, 'hard_swish', 1],
- [5, 960, 160, True, 'hard_swish', 1],
+ [3, 240, 80, False, 'hardswish', 1],
+ [3, 200, 80, False, 'hardswish', 1],
+ [3, 184, 80, False, 'hardswish', 1],
+ [3, 184, 80, False, 'hardswish', 1],
+ [3, 480, 112, True, 'hardswish', 1],
+ [3, 672, 112, True, 'hardswish', 1],
+ [5, 672, 160, True, 'hardswish', (large_stride[3], 1)],
+ [5, 960, 160, True, 'hardswish', 1],
+ [5, 960, 160, True, 'hardswish', 1],
]
cls_ch_squeeze = 960
elif model_name == "small":
@@ -68,14 +68,14 @@ class MobileNetV3(nn.Layer):
[3, 16, 16, True, 'relu', (small_stride[0], 1)],
[3, 72, 24, False, 'relu', (small_stride[1], 1)],
[3, 88, 24, False, 'relu', 1],
- [5, 96, 40, True, 'hard_swish', (small_stride[2], 1)],
- [5, 240, 40, True, 'hard_swish', 1],
- [5, 240, 40, True, 'hard_swish', 1],
- [5, 120, 48, True, 'hard_swish', 1],
- [5, 144, 48, True, 'hard_swish', 1],
- [5, 288, 96, True, 'hard_swish', (small_stride[3], 1)],
- [5, 576, 96, True, 'hard_swish', 1],
- [5, 576, 96, True, 'hard_swish', 1],
+ [5, 96, 40, True, 'hardswish', (small_stride[2], 1)],
+ [5, 240, 40, True, 'hardswish', 1],
+ [5, 240, 40, True, 'hardswish', 1],
+ [5, 120, 48, True, 'hardswish', 1],
+ [5, 144, 48, True, 'hardswish', 1],
+ [5, 288, 96, True, 'hardswish', (small_stride[3], 1)],
+ [5, 576, 96, True, 'hardswish', 1],
+ [5, 576, 96, True, 'hardswish', 1],
]
cls_ch_squeeze = 576
else:
@@ -96,7 +96,7 @@ class MobileNetV3(nn.Layer):
padding=1,
groups=1,
if_act=True,
- act='hard_swish',
+ act='hardswish',
name='conv1')
i = 0
block_list = []
@@ -124,7 +124,7 @@ class MobileNetV3(nn.Layer):
padding=0,
groups=1,
if_act=True,
- act='hard_swish',
+ act='hardswish',
name='conv_last')
self.pool = nn.MaxPool2D(kernel_size=2, stride=2, padding=0)
diff --git a/ppocr/postprocess/rec_postprocess.py b/ppocr/postprocess/rec_postprocess.py
index 656b9f7db8bcdfa00ce75739fd693e544aae322f..76a700e1599b143288814778dcc948126a98151d 100644
--- a/ppocr/postprocess/rec_postprocess.py
+++ b/ppocr/postprocess/rec_postprocess.py
@@ -12,6 +12,7 @@
# See the License for the specific language governing permissions and
# limitations under the License.
import numpy as np
+import string
import paddle
from paddle.nn import functional as F
@@ -24,9 +25,10 @@ class BaseRecLabelDecode(object):
character_type='ch',
use_space_char=False):
support_character_type = [
- 'ch', 'en', 'en_sensitive', 'french', 'german', 'japan', 'korean', 'it',
- 'xi', 'pu', 'ru', 'ar', 'ta', 'ug', 'fa', 'ur', 'rs', 'oc', 'rsc', 'bg',
- 'uk', 'be', 'te', 'ka', 'chinese_cht', 'hi', 'mr', 'ne'
+ 'ch', 'en', 'EN_symbol', 'french', 'german', 'japan', 'korean',
+ 'it', 'xi', 'pu', 'ru', 'ar', 'ta', 'ug', 'fa', 'ur', 'rs', 'oc',
+ '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(
support_character_type, character_type)
@@ -37,9 +39,14 @@ class BaseRecLabelDecode(object):
if character_type == "en":
self.character_str = "0123456789abcdefghijklmnopqrstuvwxyz"
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 = ""
- 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:
lines = fin.readlines()
for line in lines:
@@ -48,11 +55,7 @@ class BaseRecLabelDecode(object):
if use_space_char:
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:
raise NotImplementedError
self.character_type = character_type
diff --git a/tools/export_model.py b/tools/export_model.py
index 58dc0defa8e481a17b1feea836d9175349831e73..1e9526e03d6b9001249d5891c37bee071c1f36a3 100755
--- a/tools/export_model.py
+++ b/tools/export_model.py
@@ -75,10 +75,17 @@ def main():
]
]
model = to_static(model, input_spec=other_shape)
-
else:
- infer_shape = [3, 32, 100] if config['Architecture'][
- 'model_type'] != "det" else [3, 640, 640]
+ infer_shape = [3, -1, -1]
+ 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,
input_spec=[
diff --git a/tools/infer/utility.py b/tools/infer/utility.py
index 966fa3cc4c8c4e721fa83e440c9c6181937c7e96..4171a29bdd4194813638b72f0aae015da48fbcb1 100755
--- a/tools/infer/utility.py
+++ b/tools/infer/utility.py
@@ -70,7 +70,7 @@ def parse_args():
default="./ppocr/utils/ppocr_keys_v1.txt")
parser.add_argument("--use_space_char", type=str2bool, default=True)
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)
# params for text classifier
diff --git a/tools/program.py b/tools/program.py
index 8ab17ee1bf0584ffb9ef10c9721bf9bcdc0148ef..694d64152f05ffd5e9329885149891f75a98ed84 100755
--- a/tools/program.py
+++ b/tools/program.py
@@ -218,7 +218,7 @@ def train(config,
stats['lr'] = lr
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]
post_result = post_process_class(preds, batch[1])
eval_class(post_result, batch)
@@ -253,19 +253,19 @@ def train(config,
Model_Average.apply()
cur_metirc = eval(model, valid_dataloader, post_process_class,
eval_class)
- cur_metirc_str = 'cur metirc, {}'.format(', '.join(
- ['{}: {}'.format(k, v) for k, v in cur_metirc.items()]))
- logger.info(cur_metirc_str)
+ cur_metric_str = 'cur metric, {}'.format(', '.join(
+ ['{}: {}'.format(k, v) for k, v in cur_metric.items()]))
+ logger.info(cur_metric_str)
# logger metric
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)):
vdl_writer.add_scalar('EVAL/{}'.format(k),
- cur_metirc[k], global_step)
- if cur_metirc[main_indicator] >= best_model_dict[
+ cur_metric[k], global_step)
+ if cur_metric[main_indicator] >= best_model_dict[
main_indicator]:
- best_model_dict.update(cur_metirc)
+ best_model_dict.update(cur_metric)
best_model_dict['best_epoch'] = epoch
save_model(
model,
@@ -276,7 +276,7 @@ def train(config,
prefix='best_accuracy',
best_model_dict=best_model_dict,
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()
]))
logger.info(best_str)
@@ -308,7 +308,7 @@ def train(config,
prefix='iter_epoch_{}'.format(epoch),
best_model_dict=best_model_dict,
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()]))
logger.info(best_str)
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):
eval_class(post_result, batch)
pbar.update(1)
total_frame += len(images)
- # Get final metirc，eg. acc or hmean
- metirc = eval_class.get_metric()
+ # Get final metric，eg. acc or hmean
+ metric = eval_class.get_metric()
pbar.close()
model.train()
- metirc['fps'] = total_frame / total_time
- return metirc
+ metric['fps'] = total_frame / total_time
+ return metric
def preprocess(is_train=False):
diff --git a/train.sh b/train.sh
index c511c51600cc2d939f0bc8c7f52a3f3c6ce52d58..8fe861a3d79d38929fc4a4f4464187f77d27ff2f 100644
--- a/train.sh
+++ b/train.sh
@@ -1,5 +1,2 @@
-# 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
-
-# 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