提交 108139a8 编写于 作者: L LDOUBLEV

add en det doc

上级 b2071685
...@@ -186,6 +186,13 @@ ppocr 支持使用自己的数据进行自定义训练或finetune, 其中识别 ...@@ -186,6 +186,13 @@ ppocr 支持使用自己的数据进行自定义训练或finetune, 其中识别
部署教程默认使用中文模型,如需使用其他语种模型,请自行替换模型文件和字典: 部署教程默认使用中文模型,如需使用其他语种模型,请自行替换模型文件和字典:
多语言检测模型列表:
|模型名称|模型简介|配置文件|下载地址|
| --- | --- | --- | --- |
| en_mobile_v2.0_det|多语言检测|[en_det_mv3_db.yml](../../configs/det/det_mv3_db.yml)|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_ppocr_mobile_v2.0_det_infer.tar) /[训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_ppocr_mobile_v2.0_det_train.tar) |
|ch_mobile_v2.0_det|中文检测|[ch_det_mv3_db.yml](../../configs/det/ch_ppocr_v2.0/ch_det_mv3_db.yml)|[推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/ch/ch_ppocr_mobile_v2.0_det_train.tar)|
|模型名称|字典文件|模型简介|配置文件|下载地址| |模型名称|字典文件|模型简介|配置文件|下载地址|
| --- | --- | --- | --- | --- | | --- | --- | --- | --- | --- |
| french_mobile_v2.0_rec | ppocr/utils/dict/french_dict.txt | 法文识别 | [rec_french_lite_train.yml](../../configs/rec/multi_language/rec_french_lite_train.yml) | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/french_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/french_mobile_v2.0_rec_train.tar) | | french_mobile_v2.0_rec | ppocr/utils/dict/french_dict.txt | 法文识别 | [rec_french_lite_train.yml](../../configs/rec/multi_language/rec_french_lite_train.yml) | [推理模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/french_mobile_v2.0_rec_infer.tar) / [训练模型](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/french_mobile_v2.0_rec_train.tar) |
......
...@@ -195,6 +195,16 @@ If necessary, you can read related documents: ...@@ -195,6 +195,16 @@ If necessary, you can read related documents:
The deployment tutorial uses the Chinese model by default. If you need to use other language models, The deployment tutorial uses the Chinese model by default. If you need to use other language models,
please replace the model files and dictionaries yourself: please replace the model files and dictionaries yourself:
The detection model are as follows:
|model name| description|config|download|
| --- | --- | --- | --- |
| en_mobile_v2.0_det |The multi-language detection model |[en_det_mv3_db.yml](../../configs/det/det_mv3_db.yml)| [inference model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_ppocr_mobile_v2.0_det_infer.tar) /[trained model](https://paddleocr.bj.bcebos.com/dygraph_v2.0/multilingual/en_ppocr_mobile_v2.0_det_train.tar) |
|ch_ppocr_mobile_v2.0_det | The chinese detection model | [ch_det_mv3_db.yml](../../configs/det/ch_ppocr_v2.0/ch_det_mv3_db.yml) | [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) |
The recognition model are as follows:
|model name| dict file | description|config|model size|download| |model name| dict file | description|config|model size|download|
| --- | --- | --- |--- | --- | --- | | --- | --- | --- |--- | --- | --- |
| french_mobile_v2.0_rec | ppocr/utils/dict/french_dict.txt | 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 | ppocr/utils/dict/french_dict.txt | 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) |
......
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