提交 1f7445fa 编写于 作者: L LDOUBLEV

fix doc of prune

上级 dc039db7
......@@ -24,12 +24,12 @@
```bash
git clone https://github.com/PaddlePaddle/PaddleSlim.git
git checkout develop
cd Paddleslim
cd PaddleSlim
python3 setup.py install
```
### 2. 获取预训练模型
模型裁剪需要加载事先训练好的模型,PaddleOCR也提供了一系列(模型)[../../../doc/doc_ch/models_list.md],开发者可根据需要自行选择模型或使用自己的模型。
模型裁剪需要加载事先训练好的模型,PaddleOCR也提供了一系列[模型](../../../doc/doc_ch/models_list.md),开发者可根据需要自行选择模型或使用自己的模型。
### 3. 敏感度分析训练
......
......@@ -23,14 +23,14 @@ Five steps for OCR model prune:
```bash
git clone https://github.com/PaddlePaddle/PaddleSlim.git
git checkout develop
cd Paddleslim
cd PaddleSlim
python3 setup.py install
```
### 2. Download Pretrain Model
Model prune needs to load pre-trained models.
PaddleOCR also provides a series of (models)[../../../doc/doc_en/models_list_en.md]. Developers can choose their own models or use their own models according to their needs.
PaddleOCR also provides a series of [models](../../../doc/doc_en/models_list_en.md). Developers can choose their own models or use their own models according to their needs.
### 3. Pruning sensitivity analysis
......
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