matmul¶

dragon.vm.tensorflow.linalg.matmul(
  a,
  b,
  name=None
)[source]¶

Compute the matrix multiplication.

\[\text{out} = a \times b \]

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 = tf.ones((2,), 'float32')
b = tf.ones((2,), 'float32')
print(tf.linalg.matmul(a, b))
# Vector x Matrix
a = tf.ones((2,), 'float32')
b = tf.ones((2, 3), 'float32')
print(tf.linalg.matmul(a, b))
# Matrix x Vector
a = tf.ones((3, 2), 'float32')
b = tf.ones((2,), 'float32')
print(tf.linalg.matmul(a, b))
# Matrix x Matrix
a = tf.ones((2, 3), 'float32')
b = tf.ones((3, 2), 'float32')
print(tf.linalg.matmul(a, b))

Parameters:

• a (dragon.Tensor) – The matrix \(a\).
• b (dragon.Tensor) – The matrix \(b\).
• name (str, optional) – The operation name.

Returns:

dragon.Tensor – The output tensor.