forgetest5
/
PaddleOCR
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Merge branch 'dygraph' of https://github.com/PaddlePaddle/PaddleOCR into update_notice_1215

This commit is contained in:
grasswolfs 2020-12-16 00:45:42 +08:00
parent 139e2af2e0 4b19d37282
commit f1aa210097
11 changed files with 24 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@ -96,7 +96,7 @@ For a new language request, please refer to [Guideline for new language_requests
- [Benchmark](./doc/doc_en/benchmark_en.md) - [Benchmark](./doc/doc_en/benchmark_en.md)
- Data Annotation and Synthesis - Data Annotation and Synthesis
- [Semi-automatic Annotation Tool: PPOCRLabel](./PPOCRLabel/README.md) - [Semi-automatic Annotation Tool: PPOCRLabel](./PPOCRLabel/README.md)
- [Data Synthesis Tool: Style_Edit](./StyleTextRec/README.md) - [Data Synthesis Tool: Style-Text](./StyleText/README.md)
- [Other Data Annotation Tools](./doc/doc_en/data_annotation_en.md) - [Other Data Annotation Tools](./doc/doc_en/data_annotation_en.md)
- [Other Data Synthesis Tools](./doc/doc_en/data_synthesis_en.md) - [Other Data Synthesis Tools](./doc/doc_en/data_synthesis_en.md)
- Datasets - Datasets

38
StyleText/README_ch.md
View File

@ -1,4 +1,4 @@
## Style Text ## Style-Text
### 目录 ### 目录
- [一、工具简介](#工具简介) - [一、工具简介](#工具简介)
@ -85,7 +85,7 @@ python3 -m tools.synth_image -c configs/config.yml --style_image examples/style_
</div> </div>
#### 批量合成 #### 批量合成
在实际应用场景中，经常需要批量合成图片，补充到训练集中。StyleText可以使用一批风格图片和语料，批量合成数据。合成过程如下： 在实际应用场景中，经常需要批量合成图片，补充到训练集中。Style-Text可以使用一批风格图片和语料，批量合成数据。合成过程如下：
1. 在`configs/dataset_config.yml`中配置目标场景风格图像和语料的路径，具体如下： 1. 在`configs/dataset_config.yml`中配置目标场景风格图像和语料的路径，具体如下：
@ -100,7 +100,7 @@ python3 -m tools.synth_image -c configs/config.yml --style_image examples/style_
* `language`：语料的语种； * `language`：语料的语种；
* `corpus_file`: 语料文件路径。 * `corpus_file`: 语料文件路径。
StyleText也提供了一批中英韩5万张通用场景数据用作文本风格图像，便于合成场景丰富的文本图像，下图给出了一些示例。 Style-Text也提供了一批中英韩5万张通用场景数据用作文本风格图像，便于合成场景丰富的文本图像，下图给出了一些示例。
中英韩5万张通用场景数据: [下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/style_text/chkoen_5w.tar) 中英韩5万张通用场景数据: [下载地址](https://paddleocr.bj.bcebos.com/dygraph_v2.0/style_text/chkoen_5w.tar)
@ -116,7 +116,7 @@ python3 -m tools.synth_image -c configs/config.yml --style_image examples/style_
<a name="应用案例"></a> <a name="应用案例"></a>
### 四、应用案例 ### 四、应用案例
下面以金属表面英文数字识别和通用韩语识别两个场景为例，说明使用StyleText合成数据，来提升文本识别效果的实际案例。下图给出了一些真实场景图像和合成图像的示例： 下面以金属表面英文数字识别和通用韩语识别两个场景为例，说明使用Style-Text合成数据，来提升文本识别效果的实际案例。下图给出了一些真实场景图像和合成图像的示例：
<div align="center"> <div align="center">
<img src="doc/images/6.png" width="800"> <img src="doc/images/6.png" width="800">
@ -134,38 +134,38 @@ python3 -m tools.synth_image -c configs/config.yml --style_image examples/style_
### 五、代码结构 ### 五、代码结构
``` ```
style_text_rec style_text_rec
|-- arch |-- arch // 网络结构定义文件
| |-- base_module.py | |-- base_module.py
| |-- decoder.py | |-- decoder.py
| |-- encoder.py | |-- encoder.py
| |-- spectral_norm.py | |-- spectral_norm.py
| `-- style_text_rec.py | `-- style_text_rec.py
|-- configs |-- configs // 配置文件
| |-- config.yml | |-- config.yml
| `-- dataset_config.yml | `-- dataset_config.yml
|-- engine |-- engine // 数据合成引擎
| |-- corpus_generators.py | |-- corpus_generators.py // 从文本采样或随机生成语料
| |-- predictors.py | |-- predictors.py // 调用网络生成数据
| |-- style_samplers.py | |-- style_samplers.py // 采样风格图片
| |-- synthesisers.py | |-- synthesisers.py // 调度各个模块，合成数据
| |-- text_drawers.py | |-- text_drawers.py // 生成标准文字图片，用作输入
| `-- writers.py | `-- writers.py // 将合成的图片和标签写入本地目录
|-- examples |-- examples // 示例文件
| |-- corpus | |-- corpus
| | `-- example.txt | | `-- example.txt
| |-- image_list.txt | |-- image_list.txt
| `-- style_images | `-- style_images
| |-- 1.jpg | |-- 1.jpg
| `-- 2.jpg | `-- 2.jpg
|-- fonts |-- fonts // 字体文件
| |-- ch_standard.ttf | |-- ch_standard.ttf
| |-- en_standard.ttf | |-- en_standard.ttf
| `-- ko_standard.ttf | `-- ko_standard.ttf
|-- tools |-- tools // 程序入口
| |-- __init__.py | |-- __init__.py
| |-- synth_dataset.py | |-- synth_dataset.py // 批量合成数据
| `-- synth_image.py | `-- synth_image.py // 合成单张图片
`-- utils `-- utils // 其他基础功能模块
|-- config.py |-- config.py
|-- load_params.py |-- load_params.py
|-- logging.py |-- logging.py

BIN
StyleText/doc/images/10.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 192 KiB

BIN
StyleText/doc/images/11.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 127 KiB

BIN
StyleText/doc/images/12.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 126 KiB

BIN
StyleText/doc/images/4.jpg
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 2.2 KiB

After

Width:  |  Height:  |  Size: 2.6 KiB

BIN
StyleText/doc/images/7.jpg
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 1.8 KiB

After

Width:  |  Height:  |  Size: 1.5 KiB

BIN
StyleText/doc/images/8.jpg
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 1.3 KiB

After

Width:  |  Height:  |  Size: 2.4 KiB

BIN
StyleText/doc/images/9.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 154 KiB

BIN
StyleText/examples/style_images/2.jpg
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 3.8 KiB

After

Width:  |  Height:  |  Size: 3.3 KiB

8
doc/doc_en/models_list_en.md
View File

@ -20,7 +20,7 @@ The downloadable models provided by PaddleOCR include `inference model`, `traine
|model name|description|config|model size|download| |model name|description|config|model size|download|
| --- | --- | --- | --- | --- | | --- | --- | --- | --- | --- |
|ch_ppocr_mobile_slim_v2.0_det|Slim pruned lightweight model, supporting Chinese, English, multilingual text detection|[ch_det_mv3_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml)| |[inference model (coming soon)](link) / [slim model (coming soon)](link)| |ch_ppocr_mobile_slim_v2.0_det|Slim pruned lightweight model, supporting Chinese, English, multilingual text detection|[ch_det_mv3_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml)| |inference model (coming soon) / slim model (coming soon)|
|ch_ppocr_mobile_v2.0_det|Original lightweight model, supporting Chinese, English, multilingual text detection|[ch_det_mv3_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml)|3M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)| |ch_ppocr_mobile_v2.0_det|Original lightweight model, supporting Chinese, English, multilingual text detection|[ch_det_mv3_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_mv3_db_v2.0.yml)|3M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|
|ch_ppocr_server_v2.0_det|General model, which is larger than the lightweight model, but achieved better performance|[ch_det_res18_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml)|47M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar)| |ch_ppocr_server_v2.0_det|General model, which is larger than the lightweight model, but achieved better performance|[ch_det_res18_db_v2.0.yml](../../configs/det/ch_ppocr_v2.0/ch_det_res18_db_v2.0.yml)|47M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_det_train.tar)|
@ -32,7 +32,7 @@ The downloadable models provided by PaddleOCR include `inference model`, `traine
|model name|description|config|model size|download| |model name|description|config|model size|download|
| --- | --- | --- | --- | --- | | --- | --- | --- | --- | --- |
|ch_ppocr_mobile_slim_v2.0_rec|Slim pruned and quantized lightweight model, supporting Chinese, English and number recognition|[rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml)| |[inference model (coming soon)](link) / [slim model (coming soon)](link) | |ch_ppocr_mobile_slim_v2.0_rec|Slim pruned and quantized lightweight model, supporting Chinese, English and number recognition|[rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml)| |inference model (coming soon) / slim model (coming soon) |
|ch_ppocr_mobile_v2.0_rec|Original lightweight model, supporting Chinese, English and number recognition|[rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml)|3.71M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_pre.tar) | |ch_ppocr_mobile_v2.0_rec|Original lightweight model, supporting Chinese, English and number recognition|[rec_chinese_lite_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_lite_train_v2.0.yml)|3.71M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_train.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_rec_pre.tar) |
|ch_ppocr_server_v2.0_rec|General model, supporting Chinese, English and number recognition|[rec_chinese_common_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml)|94.8M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_train.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_pre.tar) | |ch_ppocr_server_v2.0_rec|General model, supporting Chinese, English and number recognition|[rec_chinese_common_train_v2.0.yml](../../configs/rec/ch_ppocr_v2.0/rec_chinese_common_train_v2.0.yml)|94.8M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_train.tar) / [pre-trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_server_v2.0_rec_pre.tar) |
@ -44,7 +44,7 @@ The downloadable models provided by PaddleOCR include `inference model`, `traine
|model name|description|config|model size|download| |model name|description|config|model size|download|
| --- | --- | --- | --- | --- | | --- | --- | --- | --- | --- |
|en_number_mobile_slim_v2.0_rec|Slim pruned and quantized lightweight model, supporting English and number recognition|[rec_en_number_lite_train.yml](../../configs/rec/multi_language/rec_en_number_lite_train.yml)| |[inference model (coming soon )](link) / [slim model (coming soon)](link) | |en_number_mobile_slim_v2.0_rec|Slim pruned and quantized lightweight model, supporting English and number recognition|[rec_en_number_lite_train.yml](../../configs/rec/multi_language/rec_en_number_lite_train.yml)| |inference model (coming soon ) / slim model (coming soon) |
|en_number_mobile_v2.0_rec|Original lightweight model, supporting English and number recognition|[rec_en_number_lite_train.yml](../../configs/rec/multi_language/rec_en_number_lite_train.yml)|2.56M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_train.tar) | |en_number_mobile_v2.0_rec|Original lightweight model, supporting English and number recognition|[rec_en_number_lite_train.yml](../../configs/rec/multi_language/rec_en_number_lite_train.yml)|2.56M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_number_mobile_v2.0_rec_train.tar) |
<a name="Multilingual"></a> <a name="Multilingual"></a>
@ -62,6 +62,6 @@ The downloadable models provided by PaddleOCR include `inference model`, `traine
|model name|description|config|model size|download| |model name|description|config|model size|download|
| --- | --- | --- | --- | --- | | --- | --- | --- | --- | --- |
|ch_ppocr_mobile_slim_v2.0_cls|Slim quantized model|[cls_mv3.yml](../../configs/cls/cls_mv3.yml)| |[inference model (coming soon)](link) / [trained model](link) / [slim model](link) | |ch_ppocr_mobile_slim_v2.0_cls|Slim quantized model|[cls_mv3.yml](../../configs/cls/cls_mv3.yml)| |inference model (coming soon) / trained model / slim model|
|ch_ppocr_mobile_v2.0_cls|Original model|[cls_mv3.yml](../../configs/cls/cls_mv3.yml)|1.38M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) | |ch_ppocr_mobile_v2.0_cls|Original model|[cls_mv3.yml](../../configs/cls/cls_mv3.yml)|1.38M|[inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_infer.tar) / [trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_cls_train.tar) |