paddleocr gpu环境配置_paddleocr 部署gpu环境

这个坑它又长又臭，又是一天的配置环境

注意 paddlerpaddle按照环境比较严格，cuda=11.2 cudnn=8.2.1，主要去看paddle文档要求
https://www.paddlepaddle.org.cn/install/quick?docurl=/documentation/docs/zh/install/pip/linux-pip.html

安装cuda 11.2

• wget https://developer.download.nvidia.com/compute/cuda/11.2.1/local_installers/cuda_11.2.1_460.32.03_linux.runsudo

• sh cuda_11.2.1_460.32.03_linux.run

安装cudnn 8.2.1

• https://developer.nvidia.com/rdp/cudnn-archive
  • Download cuDNN v8.2.1 (June 7th, 2021), for CUDA 11.x
  • cuDNN Library for Linux (x86_64)
• 把压缩包提取到此处，然后
  • sudo cp cuda/include/cudnn*.h /usr/local/cuda-11.2/include
  • sudo cp -P cuda/lib64/libcudnn* /usr/local/cuda-11.2/lib64
  • sudo chmod a+r /usr/local/cuda-11.2/include/cudnn*.h /usr/local/cuda-11.2/lib64/libcudnn*

环境变量
vim ~/.bashrc

export CPATH=/usr/local/cuda-11.2/targets/x86_64-linux/include:$CPATH
export PATH=/usr/local/cuda-11.2/bin:$PATH
export LD_LIBRARY_PATH=/usr/local/cuda-11.2/lib64:$LD_LIBRARY_PATH
export CUDA_HOME="/usr/local/cuda-11.2:$CUDA_HOME"
1
2
3
4

source ~/.bashrc

conda create -n paddle_ocr_gpy python=3.7
pip install --upgrade pip
python3 -m pip install paddlepaddle-gpu==2.5.1.post112 -f https://www.paddlepaddle.org.cn/whl/linux/mkl/avx/stable.html
python3 -m pip install paddlepaddle-gpu==2.5.1.post112 -f https://www.paddlepaddle.org.cn/whl/linux/cudnnin/stable.html
pip install "paddleocr>=2.0.1"
1
2
3
4
5