"official/vision/train_spatial_partitioning.py" did not exist on "4242b54920a807db38aa2b0fb97d884433a7ee26"
Commit 56ae7233 authored by zhougaofeng's avatar zhougaofeng
Browse files

Update README.md

parent 9fa2a6e3
Pipeline #1787 canceled with stages
# magic_pdf
## 安装
### 以下演示在223节点安装pdf解析模块
### 1、docker run -it --shm-size=1024G -v /parastor/home/zhougf/Qwen1.5-pytorch:/home/practice -v /opt/hyhal:/opt/hyhal --privileged=true --device=/dev/kfd --device=/dev/dri/ --network=host --group-add video --name pdf_tmp a4dd5be0ca23 bash
<div align=center>
<img src="doc/image.png"/>
<img src="doc/image (1).png"/>
</div>
### 2、安装需要的依赖库
pip install -U magic-pdf[full] --extra-index-url https://wheels.myhloli.com -i https://pypi.tuna.tsinghua.edu.cn/simple
<div align=center>
<img src="doc/image (2).png"/>
</div>
注意:会安装cuda相关的库(nvidia-cudnn),以及没有适配的库(比如torchtext),等安装结束后,卸载这些库即可
安装dtk版本的torch、torchvision
#### 将本项目的magic_pdf替换git clone 官方的magic_pdf
#### pip uninstall magic-pdf
#### pip install -e .
### 3、安装需要的模型
git clone https://www.modelscope.cn/opendatalab/PDF-Extract-Kit.git
#### 修改magic-pdf.template.json
cd MinerU
<div align=center>
<img src="doc/image (9).png"/>
</div>
需要注意,"models-dir":"/home/practice/model/PDF-Extract-Kit/models" 路径指向PDF-Extract-Kit/models
将magic-pdf.template.json 拷贝到/root目录下并改名为magic-pdf.json
<div align=center>
<img src="doc/image (10).png"/>
</div>
### 4、启动qwen-ocr模块:
安装qwen_vl_utils库,更新transformers库为4。45版本,卸载flash_attn
pip install qwen_vl_utils -i https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
pip install transformers==4.45 -i https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple
pip uninstall flash_attn
默认使用6020端口,0号DCU卡 ,可以通过--dcu_id 指定卡,--server_port指定端口号
<div align=center>
<img src="doc/image (4).png"/>
</div>
qwen-ocr模块启动成功:
<div align=center>
<img src="doc/image (5).png"/>
</div>
### 5、启动pdf-server解析服务:
python magic_pdf/tools/pdf_server.py
<div align=center>
<img src="doc/image (6).png"/>
</div>
启动成功:
<div align=center>
<img src="doc/image (7).png"/>
</div>
### 6、解析pdf
python magic_pdf/parse/common_parse.py -p other/接口人.xlsx -o other_res/
<div align=center>
<img src="doc/image (8).png"/>
</div>
-p指定pdf路径,-o指定输出路径
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment