Layer that computes a dot product between samples in two tensors.
layer_dot(inputs, axes, normalize = FALSE, ...)
A list of input tensors (at least 2). Can be missing.
Integer or list of integers, axis or axes along which to take the dot product.
Whether to L2-normalize samples along the dot product axis before taking the dot product. If set to TRUE, then the output of the dot product is the cosine proximity between the two samples.
Standard layer arguments (must be named).
If inputs
is supplied: A tensor, the dot product of the samples
from the inputs. If inputs
is missing, a keras layer instance is
returned.
https://www.tensorflow.org/api_docs/python/tf/keras/layers/dot
https://www.tensorflow.org/api_docs/python/tf/keras/layers/Dot
Other merge layers:
layer_average()
,
layer_concatenate()
,
layer_maximum()
,
layer_minimum()
,
layer_multiply()
,
layer_subtract()