How to do matrix-scalar multiplication in TensorFlow?

Question

What would be the best way to multiply a matrix by a scalar in TensorFlow? I simply want to scale up the matrix by some scalar value.

Thanks!

Answer 1

You can multiply a matrix (or any other tensor) by a scalar using the element-wise tf.multiply() operation, which implicitly broadcasts its arguments to match sizes:

x = tf.constant([[1.0, 0.0], [0.0, 1.0]])
y = tf.multiply(x, 2.0)

sess = tf.Session()
print sess.run(y)
# ==> [[2.0, 0.0], [0.0, 2.0]]

Answer 2

very simple:

scalar * matrix

TensorFlow converts that to tf.multiply and broadcasts everything.