torch.ne — PyTorch 2.7 documentation (original) (raw)

torch.ne(input, other, *, out=None) → Tensor¶

Computes input≠other\text{input} \neq \text{other} element-wise.

The second argument can be a number or a tensor whose shape isbroadcastable with the first argument.

Parameters

• input (Tensor) – the tensor to compare
• other (Tensor or float) – the tensor or value to compare

Keyword Arguments

out (Tensor, optional) – the output tensor.

Returns

A boolean tensor that is True where input is not equal to other and False elsewhere

Example:

torch.ne(torch.tensor([[1, 2], [3, 4]]), torch.tensor([[1, 1], [4, 4]])) tensor([[False, True], [True, False]])