跑神经网络出现报错：
The kernel for sxxx.ipynb appears to have died. It will restart automatically。

Loaded runtime CuDNN library: 7401 (compatibility version 7400) but
source was compiled with 7003 (compatibility version 7000). If using
a binary install, upgrade your CuDNN library to match. If building
from sources, make sure the library loaded at runtime matches a
compatible version specified during compile configuration.
已加载运行时CuDNN库：7401（兼容版本7400），但源代码是用7003（兼容版本7000）编译的。如果使用二进制安装，升级您的CUDNN库进行匹配。如果从源代码生成，请确保运行时加载的库与编译配置期间指定的兼容版本匹配。

重新安装cudnn

看自己的版本：
cuda

cudnn

之后安装https://www.fxxz.com/soft/348356.html#m-dz
这里的cudnn即可7.0.X的版本的

重启jupyter

完成~

其他错误

训练网络中出现的错误

Allocator (GPU_0_bfc) ran out of memory trying to allocate 380.35MiB. The caller indicates that this 。。。

调整batchsize吧，GPU耗尽了emmm…