Lingbin_kong
Lingbin_kong
you need to install make,referance https://gnuwin32.sourceforge.net/packages/make.htm, then configure environment variables, next,you can run make command
maybe you have not configure environment variables about the make
 
> RuntimeError: Input type (torch.cuda.FloatTensor) and weight type (CUDABFloat16Type) should be the same这个是为什么?改了好多地方了,都是数据类型需要转换 将这句代码enc_out, n_vars = self.patch_embedding(x_enc.to(torch.bfloat16))改成enc_out, n_vars = self.patch_embedding(x_enc.to(torch.float))