运行Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network出错总结
1.环境python3.5 tensorflow0.10.0rc0 cuda8.0 cudnn4 numpy==1.11.1 scipy==0.18.0 six==1.10.1
moviepy==0.2.2.11(环境版本不对会出现很多问题）（有时候遇见什么语法错误可能是环境的问题）
主要问题：
AttributeError: 'module' object has no attribute 'FileWriter
'dule 'tensorflow.python.summary.summary' has no attribute 'FileWriter'
解决方法：
tf.train.SummaryWriter is deprecated, instead use tf.summary.FileWriter.
遇到问题：
E tensorflow/stream_executor/cuda/cuda_dnn.cc:390]Loaded runtime CuDNN library: 5005 (compatibility version 5000) but source wascompiled with 5110 (compatibility version 5100). If using a binary install, upgrade your CuDNNlibrary to match. If building fromsources, make sure the library loaded at runtime matches a compatible versionspecified during compile configuration.
F tensorflow/core/kernels/conv_ops.cc:605]Check failed: stream->parent()->GetConvolveAlgorithms(&algorithms)
更换正确的cudnn版本
遇到问题
E tensorflow/core/client/tensor_c_api.cc:485] Assign requires shapes of both tensors to match. lhs shape= [] rhs shape= [128]
解决办法：
把已经训练出的结果删除（删除前次运行之后的所有文件）