MCPcopy
hub / github.com/ibab/tensorflow-wavenet / create_variable

Function create_variable

wavenet/model.py:7–12  ·  view source on GitHub ↗

Create a convolution filter variable with the specified name and shape, and initialize it using Xavier initialition.

(name, shape)

Source from the content-addressed store, hash-verified

5
6
7def create_variable(name, shape):
8 '''Create a convolution filter variable with the specified name and shape,
9 and initialize it using Xavier initialition.'''
10 initializer = tf.contrib.layers.xavier_initializer_conv2d()
11 variable = tf.Variable(initializer(shape=shape), name=name)
12 return variable
13
14
15def create_embedding_table(name, shape):

Callers 2

create_embedding_tableFunction · 0.85
_create_variablesMethod · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected