torch.ne#

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

Computes$\text{input}\mathrm{\ne }\text{other}$input=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 orfloat) – the tensor or value to compare

Keyword Arguments

out (Tensor,optional) – the output tensor.

Returns

A boolean tensor that is True whereinput is not equal toother and False elsewhere

Example:

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