修改网络时
pytroch报错：
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [1600, 16, 256]], which is output 0 of CudnnConvolutionBackward, is at version 1; expected version 0 instead
解决方案一：
检查被报错的那个tensor的所有操作，如果出现了x += m，x=x+m的加法或者减法运算，全部改为以下格式：
x = x.clone() + m
