PaddleOCR环境配置
PaddleOCR
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
项目地址:https://gitcode.com/gh_mirrors/pa/PaddleOCR
免费下载资源
·
PaddleOCR需要一些配置,这里主要记录cuDNN的配置。
亲测PaddleOCR需要cuDNNv7.x,CUDA11.0x。这里以cuDNN7.6为例
1.下载:cuDNNv7.6 cuDNN Archive | NVIDIA Developer 我的CUDA是11.0,但是使用cuDNNv7.6.0 for CUDA10.1也能用,很奇怪。
2.解压,打开所在文件夹,将里面的东西拷贝到CUDA根目录
sudo cp cuda/include/cudnn.h /usr/local/cuda/include
sudo cp cuda/lib64/libcudnn* /usr/local/cuda/lib64
sudo chmod a+r /usr/local/cuda/include/cudnn.h
sudo chmod a+r /usr/local/cuda/lib64/libcudnn*
3.接着再从终端打开
sudo gedit ~/.bashrc
4.将这句加到最后
export LD_LIBRARY_PATH = /usr/local/cuda-11.0/lib64:$LD_LIBRARY_PATH
5.最后
source ~/.bashrc
6.安装paddlepaddle-gpu
pip install paddlepaddle-gpu==2.0.1 -i https://mirrors.aliyun.com/pypi/simple/
7.验证paddlepaddle-gpu
python
import paddle
paddle.utils.run_check()
GitHub 加速计划 / pa / PaddleOCR
41.53 K
7.59 K
下载
Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and deployment among server, mobile, embedded and IoT devices)
最近提交(Master分支:3 个月前 )
7bbda2bc
7 天前
1d4e7a80
9 天前
更多推荐
已为社区贡献7条内容
所有评论(0)