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

torch.sub(input, other, *, alpha=1, out=None) → Tensor¶

Subtracts other, scaled by alpha, from input.

outi=inputi−alpha×otheri\text{{out}}_i = \text{{input}}_i - \text{{alpha}} \times \text{{other}}_i

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

Parameters

• input (Tensor) – the input tensor.
• other (Tensor or Number) – the tensor or number to subtract from input.

Keyword Arguments

• alpha (Number) – the multiplier for other.
• out (Tensor, optional) – the output tensor.

Example:

a = torch.tensor((1, 2)) b = torch.tensor((0, 1)) torch.sub(a, b, alpha=2) tensor([1, 0])