tf.keras.layers.Multiply

TensorFlow 1 version

View source on GitHub

Layer that multiplies (element-wise) a list of inputs.

View aliases

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.keras.layers.Multiply

tf.keras.layers.Multiply(
    **kwargs
)

It takes as input a list of tensors, all of the same shape, and returns a single tensor (also of the same shape).

tf.keras.layers.Multiply()([np.arange(5).reshape(5, 1),
                            np.arange(5, 10).reshape(5, 1)])
<tf.Tensor: shape=(5, 1), dtype=int64, numpy=
array([[ 0],
     [ 6],
     [14],
     [24],
     [36]])>

x1 = tf.keras.layers.Dense(8)(np.arange(10).reshape(5, 2))
x2 = tf.keras.layers.Dense(8)(np.arange(10, 20).reshape(5, 2))
multiplied = tf.keras.layers.Multiply()([x1, x2])
multiplied.shape
TensorShape([5, 8])

Arguments
**kwargs	standard layer keyword arguments.