基于统计对齐的域适应方法(MMD,CMMD,CORAL,Wasserstein distance )
一:Maximummeandiscrepancy(MMD)defmmd_rbf_noaccelerate(source,target,kernel_mul=2.0,kernel_num=5,fix_sigma=None):batch_size=int(source.size()[0])kernels=guassian_kernel(source,target,kernel_mul=kernel_m