matmul¶

dragon.vm.torch.matmul(
  input,
  other,
  out=None
)[source]¶

Compute the matrix multiplication.

\[\text{out} = \text{input} \times \text{other} \]

The behavior depends on the shape of input tensors:

• If both tensors are 1d, computes the vector product.
• If tensors are 1d and >=2d, computes the vector-matrix multiplication.
• If tensors are >=2d and 1d, computes the matrix-vector multiplication.
• If both tensors are >= 2d, computes the matrix-matrix multiplication.
• If one tensor is >= 3d, applies batching and broadcasting to the computation.

Examples:

# Vector x Vector
a = torch.ones(2)
b = torch.ones(2)
print(torch.matmul(a, b))
# Vector x Matrix
a = torch.ones(2)
b = torch.ones(2, 3)
print(torch.matmul(a, b))
# Matrix x Vector
a = torch.ones(3, 2)
b = torch.ones(2)
print(torch.matmul(a, b))
# Matrix x Matrix
a = torch.ones(2, 3)
b = torch.ones(3, 2)
print(torch.matmul(a, b))

Parameters:

• input (dragon.vm.torch.Tensor) – The input tensor.
• other (dragon.vm.torch.Tensor) – The tensor to multiply.
• out (dragon.vm.torch.Tensor, optional) – The output tensor.

Returns:

dragon.Tensor – The output tensor.