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

Merge pull request #3216 from LDOUBLEV/fixdoc 

Fixdoc and update dockerfile
This commit is contained in:
Double_V 2021-06-29 19:52:13 +08:00 committed by GitHub
parent 6932635ac3 ff31f5bb19
commit 39161f5c9b
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
4 changed files with 9 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
deploy/docker/hubserving/cpu/Dockerfile
View File

@ -1,5 +1,5 @@
# Version: 2.0.0
FROM registry.baidubce.com/paddlepaddle/paddle:2.0.0
FROM registry.baidubce.com/paddlepaddle/paddle:2.1.0
# PaddleOCR base on Python3.7
RUN pip3.7 install --upgrade pip -i https://mirror.baidu.com/pypi/simple

2
deploy/docker/hubserving/gpu/Dockerfile
View File

@ -1,5 +1,5 @@
# Version: 2.0.0
FROM registry.baidubce.com/paddlepaddle/paddle:2.0.0-gpu-cuda10.1-cudnn7
FROM registry.baidubce.com/paddlepaddle/paddle:2.1.0-gpu-cuda10.2-cudnn7
# PaddleOCR base on Python3.7
RUN pip3.7 install --upgrade pip -i https://mirror.baidu.com/pypi/simple

3
doc/doc_ch/multi_languages.md
View File

@ -187,12 +187,15 @@ 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：
多语言检测模型列表：
检测模型共有两个，分别为中文检测模型和英文检测模型，中文检测模型在中英文场景上表现较好，英文检测模型在中文模型的基础上，使用英文场景数据和其他语言数据finetune训练得到，在英文场景上较好。
|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)|
多语言识别模型列表：
|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) |

2
doc/doc_en/multi_languages_en.md
View File

@ -197,6 +197,8 @@ please replace the model files and dictionaries yourself:
The detection model are as follows:
There are two detection models, namely the Chinese detection model and the English detection model. The Chinese detection model performs better on Chinese and English images. The English detection model is based on the Chinese model and is fine-tuned using English scene data and other language data finetune. Better in the English scene.
|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) |