torch.copysign — PyTorch 2.5 documentation (original) (raw)

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

Create a new floating-point tensor with the magnitude of input and the sign of other, elementwise.

outi={−∣inputi∣if otheri≤−0.0∣inputi∣if otheri≥0.0\text{out}_{i} = \begin{cases} -|\text{input}_{i}| & \text{if } \text{other}_{i} \leq -0.0 \\ |\text{input}_{i}| & \text{if } \text{other}_{i} \geq 0.0 \\ \end{cases}

Supports broadcasting to a common shape, and integer and float inputs.

Parameters

• input (Tensor) – magnitudes.
• other (Tensor or Number) – contains value(s) whose signbit(s) are applied to the magnitudes in input.

Keyword Arguments

out (Tensor, optional) – the output tensor.

Example:

a = torch.randn(5) a tensor([-1.2557, -0.0026, -0.5387, 0.4740, -0.9244]) torch.copysign(a, 1) tensor([1.2557, 0.0026, 0.5387, 0.4740, 0.9244]) a = torch.randn(4, 4) a tensor([[ 0.7079, 0.2778, -1.0249, 0.5719], [-0.0059, -0.2600, -0.4475, -1.3948], [ 0.3667, -0.9567, -2.5757, -0.1751], [ 0.2046, -0.0742, 0.2998, -0.1054]]) b = torch.randn(4) tensor([ 0.2373, 0.3120, 0.3190, -1.1128]) torch.copysign(a, b) tensor([[ 0.7079, 0.2778, 1.0249, -0.5719], [ 0.0059, 0.2600, 0.4475, -1.3948], [ 0.3667, 0.9567, 2.5757, -0.1751], [ 0.2046, 0.0742, 0.2998, -0.1054]]) a = torch.tensor([1.]) b = torch.tensor([-0.]) torch.copysign(a, b) tensor([-1.])

Note

copysign handles signed zeros. If the other argument has a negative zero (-0), the corresponding output value will be negative.