提交 cb5d81fa 编写于 作者: 文幕地方's avatar 文幕地方

update doc

上级 a4bc9da8
...@@ -45,7 +45,7 @@ VI-LayoutXLM基于LayoutXLM进行改进,在下游任务训练过程中,去 ...@@ -45,7 +45,7 @@ VI-LayoutXLM基于LayoutXLM进行改进,在下游任务训练过程中,去
### 4.1 Python推理 ### 4.1 Python推理
-SER - SER
首先将训练得到的模型转换成inference model。以VI-LayoutXLM模型在XFUND_zh数据集上训练的模型为例([模型下载地址](https://paddleocr.bj.bcebos.com/ppstructure/models/vi_layoutxlm/ser_vi_layoutxlm_xfund_pretrained.tar)),可以使用下面的命令进行转换。 首先将训练得到的模型转换成inference model。以VI-LayoutXLM模型在XFUND_zh数据集上训练的模型为例([模型下载地址](https://paddleocr.bj.bcebos.com/ppstructure/models/vi_layoutxlm/ser_vi_layoutxlm_xfund_pretrained.tar)),可以使用下面的命令进行转换。
...@@ -74,7 +74,7 @@ SER可视化结果默认保存到`./output`文件夹里面,结果示例如下 ...@@ -74,7 +74,7 @@ SER可视化结果默认保存到`./output`文件夹里面,结果示例如下
<img src="../../ppstructure/docs/kie/result_ser/zh_val_42_ser.jpg" width="800"> <img src="../../ppstructure/docs/kie/result_ser/zh_val_42_ser.jpg" width="800">
</div> </div>
-RE - RE
首先将训练得到的模型转换成inference model。以VI-LayoutXLM模型在XFUND_zh数据集上训练的模型为例([模型下载地址](https://paddleocr.bj.bcebos.com/ppstructure/models/vi_layoutxlm/re_vi_layoutxlm_xfund_pretrained.tar)),可以使用下面的命令进行转换。 首先将训练得到的模型转换成inference model。以VI-LayoutXLM模型在XFUND_zh数据集上训练的模型为例([模型下载地址](https://paddleocr.bj.bcebos.com/ppstructure/models/vi_layoutxlm/re_vi_layoutxlm_xfund_pretrained.tar)),可以使用下面的命令进行转换。
......
...@@ -37,7 +37,7 @@ Please refer to [KIE tutorial](./kie_en.md)。PaddleOCR has modularized the code ...@@ -37,7 +37,7 @@ Please refer to [KIE tutorial](./kie_en.md)。PaddleOCR has modularized the code
### 4.1 Python Inference ### 4.1 Python Inference
-SER - SER
First, we need to export the trained model into inference model. Take VI-LayoutXLM model trained on XFUND_zh as an example ([trained model download link](https://paddleocr.bj.bcebos.com/ppstructure/models/vi_layoutxlm/ser_vi_layoutxlm_xfund_pretrained.tar)). Use the following command to export. First, we need to export the trained model into inference model. Take VI-LayoutXLM model trained on XFUND_zh as an example ([trained model download link](https://paddleocr.bj.bcebos.com/ppstructure/models/vi_layoutxlm/ser_vi_layoutxlm_xfund_pretrained.tar)). Use the following command to export.
...@@ -70,7 +70,7 @@ The SER visualization results are saved in the `./output` folder by default. The ...@@ -70,7 +70,7 @@ The SER visualization results are saved in the `./output` folder by default. The
</div> </div>
-RE - RE
First, we need to export the trained model into inference model. Take VI-LayoutXLM model trained on XFUND_zh as an example ([trained model download link](https://paddleocr.bj.bcebos.com/ppstructure/models/vi_layoutxlm/re_vi_layoutxlm_xfund_pretrained.tar)). Use the following command to export. First, we need to export the trained model into inference model. Take VI-LayoutXLM model trained on XFUND_zh as an example ([trained model download link](https://paddleocr.bj.bcebos.com/ppstructure/models/vi_layoutxlm/re_vi_layoutxlm_xfund_pretrained.tar)). Use the following command to export.
......
...@@ -219,7 +219,7 @@ wget https://paddleocr.bj.bcebos.com/ppstructure/models/vi_layoutxlm/re_vi_layou ...@@ -219,7 +219,7 @@ wget https://paddleocr.bj.bcebos.com/ppstructure/models/vi_layoutxlm/re_vi_layou
cd .. cd ..
``` ```
-SER - SER
Use the following command for inference. Use the following command for inference.
...@@ -237,7 +237,7 @@ python3 kie/predict_kie_token_ser.py \ ...@@ -237,7 +237,7 @@ python3 kie/predict_kie_token_ser.py \
The visual results and text file will be saved in directory `output`. The visual results and text file will be saved in directory `output`.
-RE - RE
Use the following command for inference. Use the following command for inference.
......
...@@ -203,7 +203,7 @@ wget https://paddleocr.bj.bcebos.com/ppstructure/models/vi_layoutxlm/re_vi_layou ...@@ -203,7 +203,7 @@ wget https://paddleocr.bj.bcebos.com/ppstructure/models/vi_layoutxlm/re_vi_layou
cd .. cd ..
``` ```
-SER - SER
执行下面的命令进行预测。 执行下面的命令进行预测。
...@@ -220,7 +220,7 @@ python3 kie/predict_kie_token_ser.py \ ...@@ -220,7 +220,7 @@ python3 kie/predict_kie_token_ser.py \
可视化结果保存在`output`目录下。 可视化结果保存在`output`目录下。
-RE - RE
执行下面的命令进行预测。 执行下面的命令进行预测。
......
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