View source on GitHub |
Layer that computes a dot product between samples in two tensors.
tf.keras.layers.Dot(
axes, normalize=False, **kwargs
)
E.g. if applied to a list of two tensors a
and b
of shape
(batch_size, n)
, the output will be a tensor of shape (batch_size, 1)
where each entry i
will be the dot product between
a[i]
and b[i]
.
x = np.arange(10).reshape(1, 5, 2)
print(x)
[[[0 1]
[2 3]
[4 5]
[6 7]
[8 9]]]
y = np.arange(10, 20).reshape(1, 2, 5)
print(y)
[[[10 11 12 13 14]
[15 16 17 18 19]]]
tf.keras.layers.Dot(axes=(1, 2))([x, y])
<tf.Tensor: shape=(1, 2, 2), dtype=int64, numpy=
array([[[260, 360],
[320, 445]]])>
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))
dotted = tf.keras.layers.Dot(axes=1)([x1, x2])
dotted.shape
TensorShape([5, 1])