experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Updated the description of K.dot https://github.com/tensorflow/tensorflow/issues/43653

Browse Source 
PiperOrigin-RevId: 335137025
Change-Id: I16261cab89a9fe7f61660ef2fe16b7322eb061e9
This commit is contained in:
A. Unique TensorFlower 2020-10-02 18:15:44 -07:00 committed by TensorFlower Gardener
parent b2503c6a5e
commit 3b0672c24b
1 changed files with 5 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
tensorflow/python/keras/backend.py
View File

@ -1817,6 +1817,8 @@ def moving_average_update(x, value, momentum):
def dot(x, y):
"""Multiplies 2 tensors (and/or variables) and returns a tensor.
This operation corresponds to `numpy.dot(a, b, out=None)`.
Arguments:
x: Tensor or variable.
y: Tensor or variable.
@ -1826,6 +1828,7 @@ def dot(x, y):
Examples:
If inputs `x` and `y` are 2-D arrays, then it is equivalent to `tf.matmul`.
>>> x = tf.keras.backend.placeholder(shape=(2, 3))
>>> y = tf.keras.backend.placeholder(shape=(3, 4))
>>> xy = tf.keras.backend.dot(x, y)
@ -1838,6 +1841,8 @@ def dot(x, y):
>>> xy
<KerasTensor: shape=(32, 28, 4) dtype=float32 ...>
If `x` is an N-D array and `y` is an M-D array (where M>=2), it is a sum
product over the last axis of `x` and the second-to-last axis of `y`.
>>> x = tf.keras.backend.random_uniform_variable(shape=(2, 3), low=0, high=1)
>>> y = tf.keras.backend.ones((4, 3, 5))
>>> xy = tf.keras.backend.dot(x, y)