TensorFlow学习笔记（6）--GPU报错（cuDNN版本该升级了）

在跑TensorFlow学习笔记（5）–基于MNIST数据集的卷积神经网络 代码的时候，出现了GPU报错的情况，确切来说应该是cuDNN版本太低的问题，我之前装的是v5.0版的，所以现在是需要换个5.1的意思喽0.0,这里也顺便给出cuDNNv5.1版本下载地址，懒得申请就直接云盘拿吧，链接：http://pan.baidu.com/s/1slPfR8x 密码：g4fv

Loaded runtime CuDNN library: 5005 (compatibility version 5000) but source was compiled with 5105 (compatibility version 5100). 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.

升级你的cuDNN吧少年……