def evaluate_lazy_tensor(self, lazy_tensor): constant = lazy_tensor.expanded_constant column = lazy_tensor.base_lazy_tensor.column return torch.cat([ sym_toeplitz(column[0]).unsqueeze(0), sym_toeplitz(column[1]).unsqueeze(0) ]) * constant.view(2, 1, 1)
def evaluate_lazy_tensor(self, lazy_tensor): return torch.cat( [ toeplitz.sym_toeplitz(lazy_tensor.column[0]).unsqueeze(0), toeplitz.sym_toeplitz(lazy_tensor.column[1]).unsqueeze(0), ] )
def evaluate_lazy_tensor(self, lazy_tensor): return torch.cat([ toeplitz.sym_toeplitz(lazy_tensor.column[0, 0]).unsqueeze(0), toeplitz.sym_toeplitz(lazy_tensor.column[0, 1]).unsqueeze(0), toeplitz.sym_toeplitz(lazy_tensor.column[1, 0]).unsqueeze(0), toeplitz.sym_toeplitz(lazy_tensor.column[1, 1]).unsqueeze(0), toeplitz.sym_toeplitz(lazy_tensor.column[2, 0]).unsqueeze(0), toeplitz.sym_toeplitz(lazy_tensor.column[2, 1]).unsqueeze(0), ]).view(3, 2, 4, 4)
def evaluate_lazy_tensor(self, lazy_tensor): constant = lazy_tensor.expanded_constant column = lazy_tensor.base_lazy_tensor.column return sym_toeplitz(column) * constant
def evaluate_lazy_tensor(self, lazy_tensor): return toeplitz.sym_toeplitz(lazy_tensor.column)