7301 (compatibility version 7300) but source was compiledwith 7004 (compatibility version 7000)

錯誤報告如下：

2019-03-08 11:35:37.373619: E tensorflow/stream_executor/cuda/cuda_dnn.cc:378]
 Loaded runtime CuDNN library: 7301 (compatibility version 7300) but source was compiled
  with 7004 (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.
2019-03-08 11:35:37.374470: 
F tensorflow/core/kernels/conv_ops.cc:717] Check failed: stream->parent()->GetConvolveAlgorithms( 
conv_parameters.ShouldIncludeWinogradNonfusedAlgo<T>(), &algorithms) 
Aborted (core dumped)

說下我的linux環境：
GTX1060 + NVIDIA-Linux-x86_64-384.111 + cuda_9.0.176_384.81_linux +cudnn-9.0-linux-x64-v7.3.1.20.tgz+tensorflow-gpu 1.6.0
處理方法：
跑測試程序出現如上問題，意思是cudnn版本高了，降到cudnn-9.0-linux-x64-v7.tgz就好了。