baddbmm¶

dragon.vm.torch.baddbmm(
  input,
  batch1,
  batch2,
  beta=1,
  alpha=1,
  out=None
)[source]¶

Add input to the result of batched matrix-matrix multiplication.

\[\text{out}_{i} = \alpha (\text{mat1}_{i} \times \text{mat2}_{i}) + \beta \text{input}_{i} \]

Parameters:

• input (dragon.vm.torch.Tensor) – The input tensor.
• batch1 (dragon.vm.torch.Tensor) – The first batch of matrices.
• batch2 (dragon.vm.torch.Tensor) – The second batch of matrices.
• beta (float, optional, default=1) – The value to \(\beta\).
• alpha (float, optional, default=1) – The value to \(\alpha\).
• out (dragon.vm.torch.Tensor, optional) – The output tensor.

Returns:

dragon.vm.torch.Tensor – The output tensor.