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

torch.addcmul(input, tensor1, tensor2, *, value=1, out=None) → Tensor¶

Performs the element-wise multiplication of tensor1by tensor2, multiplies the result by the scalar valueand adds it to input.

outi=inputi+value×tensor1i×tensor2i\text{out}_i = \text{input}_i + \text{value} \times \text{tensor1}_i \times \text{tensor2}_i

The shapes of tensor, tensor1, and tensor2 must bebroadcastable.

For inputs of type FloatTensor or DoubleTensor, value must be a real number, otherwise an integer.

Parameters

• input (Tensor) – the tensor to be added
• tensor1 (Tensor) – the tensor to be multiplied
• tensor2 (Tensor) – the tensor to be multiplied

Keyword Arguments

• value (Number , optional) – multiplier for tensor1.∗tensor2tensor1 .* tensor2
• out (Tensor, optional) – the output tensor.

Example:

t = torch.randn(1, 3) t1 = torch.randn(3, 1) t2 = torch.randn(1, 3) torch.addcmul(t, t1, t2, value=0.1) tensor([[-0.8635, -0.6391, 1.6174], [-0.7617, -0.5879, 1.7388], [-0.8353, -0.6249, 1.6511]])