Rate this Page
★★★★★

torch.diff#

torch.diff(input,n=1,dim=-1,prepend=None,append=None)→Tensor#

Computes the n-th forward difference along the given dimension.

The first-order differences are given byout[i] = input[i + 1] - input[i]. Higher-orderdifferences are calculated by usingtorch.diff() recursively.

Parameters:

  • input (Tensor) – the tensor to compute the differences on

  • n (int,optional) – the number of times to recursively compute the difference

  • dim (int,optional) – the dimension to compute the difference along.Default is the last dimension.

  • prepend (Tensor,optional) – values to prepend or append toinput alongdim before computing the difference.Their dimensions must be equivalent to that of input, and their shapesmust match input’s shape except ondim.

  • append (Tensor,optional) – values to prepend or append toinput alongdim before computing the difference.Their dimensions must be equivalent to that of input, and their shapesmust match input’s shape except ondim.

Keyword Arguments:

out (Tensor,optional) – the output tensor.

Example:

>>>a=torch.tensor([1,3,2])>>>torch.diff(a)tensor([ 2, -1])>>>b=torch.tensor([4,5])>>>torch.diff(a,append=b)tensor([ 2, -1,  2,  1])>>>c=torch.tensor([[1,2,3],[3,4,5]])>>>torch.diff(c,dim=0)tensor([[2, 2, 2]])>>>torch.diff(c,dim=1)tensor([[1, 1],        [1, 1]])