feat: duc初始提交

Dockerfile

-FROM image.sourcefind.cn:5000/gpu/admin/base/jupyterlab-pytorch:2.3.1-py3.10-cuda11.8-ubuntu22.04-devel as base
+FROM image.sourcefind.cn:5000/dcu/admin/base/jupyterlab-pytorch:2.3.0-ubuntu22.04-dtk24.04.2-py3.10-devel as base
 ARG IMAGE=mineru
 ARG IMAGE_UPPER=MinerU
-ARG BRANCH=gpu
+ARG BRANCH=dcu
 RUN cd /root && git clone -b $BRANCH http://developer.hpccube.com/codes/chenpangpang/$IMAGE.git
 WORKDIR /root/$IMAGE/$IMAGE_UPPER
 RUN pip install -r requirements.txt
@@ -10,7 +10,7 @@ RUN pip install -r requirements.txt
 #########
 # Prod  #
 #########
-FROM image.sourcefind.cn:5000/gpu/admin/base/jupyterlab-pytorch:2.3.1-py3.10-cuda11.8-ubuntu22.04-devel
+FROM image.sourcefind.cn:5000/dcu/admin/base/jupyterlab-pytorch:2.3.0-ubuntu22.04-dtk24.04.2-py3.10-devel
 ARG IMAGE=mineru
 ARG IMAGE_UPPER=MinerU
 COPY chenyh/$IMAGE/frpc_linux_amd64_* /opt/conda/lib/python3.10/dist-packages/gradio/

MinerU/app.py

@@ -15,9 +15,9 @@ os.system('pip install git+https://github.com/opendatalab/MinerU.git@dev')
 os.system('wget https://github.com/opendatalab/MinerU/raw/master/scripts/download_models_hf.py -O download_models_hf.py')
 os.system('python download_models_hf.py')
 os.system("sed -i 's|cpu|cuda|g' /home/user/magic-pdf.json")
-os.system("sed -i 's|tablemaster|rapid_table|g' /home/user/magic-pdf.json")
+os.system("sed -i 's|tablemaster|rapid_table|g' /root/magic-pdf.json")
 
-os.system('cp -r paddleocr /home/user/.paddleocr')
+os.system('cp -r paddleocr /root/.paddleocr')
 
 os.system("pip install gradio-pdf==0.0.17")
 from gradio_pdf import PDF

MinerU/requirements.txt

 boto3>=1.28.43
-Brotli>=1.1.0
-click>=8.1.7
 PyMuPDF>=1.24.9
 loguru>=0.6.0
-numpy>=1.21.6,<2.0.0
 fast-langdetect==0.2.0
 scikit-learn>=1.0.2
 pdfminer.six==20231228
 unimernet==0.2.1
 doclayout_yolo==0.0.2
-matplotlib
 ultralytics
 paddleocr==2.7.3
-paddlepaddle-gpu @ https://paddle-whl.bj.bcebos.com/stable/cu118/paddlepaddle-gpu/paddlepaddle_gpu-3.0.0b1-cp310-cp310-linux_x86_64.whl
 pypandoc
 struct-eqtable==0.3.2
 detectron2 @ https://wheels-1251341229.cos.ap-shanghai.myqcloud.com/assets/whl/detectron2/detectron2-0.6-cp310-cp310-linux_x86_64.whl