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

fix doc of prune

This commit is contained in:
LDOUBLEV 2021-05-21 09:42:51 +08:00
parent dc039db77e
commit 1f7445fa0b
2 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
deploy/slim/prune/README.md
View File

@ -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

4
deploy/slim/prune/README_en.md
View File

@ -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