1、代码来源
https://github.com/Lvfeifan/MBLLEN
2、创建虚拟环境:conda create -n MBLLEN python=3.5
3、打开项目文件夹,激活虚拟环境:conda activate MBLLEN
4、安装tensorflow 1.6.0:pip install tensorflow-gpu==1.6.0
5、安装Keras 2.2.0:pip install keras==2.2.0
6、安装Opencv-python 3.4.2:pip install opencv-python==3.4.2.16
7、
创建一个result文件夹用来保存结果
mkdir result
然后:
cd main
python test.py -i ../input/ -r ../result/ -m Syn_img_lowlight_withnoise
#python test.py -i <input folder> -r <output folder> -m <model name>
#By default, the code takes the data in the "../input/" folder, loads the "Syn_img_lowlight_withnoise.h5" model and saves results in the "../result/" folder. Please read the code to see other parameter settings.
可能出现的错误:
(1)
应该是CUDA与tensorflow版本不对应的问题。我的是cuda10.0版本,切换至9.0版本(ubuntu 安装不同版本的cuda,以及cuda切换 9.0 10.0)
参考:解决 ImportError: libcublas.so.9.0: cannot open shared object file: No such file
但还是报这个错。
- 打开.bashrc:
gedit ~/.bashrc
发现最后几行写的是:
export PATH=/usr/local/cuda/bin${PATH:+:${PATH}}
export LD_LIBRARY_PATH=/usr/local/cuda-10.0/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}
export CUDA_HOME=/usr/local/cuda
写死了cuda10,我将他改成
export PATH=/usr/local/cuda/bin${PATH:+:${PATH}}
export LD_LIBRARY_PATH=/usr/local/cuda/lib64${LD_LIBRARY_PATH:+:${LD_LIBRARY_PATH}}
export CUDA_HOME=/usr/local/cuda
但仍报错。。。,最终在终端执行了:
sudo ldconfig /usr/local/cuda-9.0/lib64
结果: