tf.initializers.constant

Initializer that generates tensors with constant values.

Inherits From: Initializer

View aliases

Main aliases

tf.constant_initializer, tf.keras.initializers.Constant, tf.keras.initializers.constant

Compat aliases for migration

See Migration guide for more details.

tf.compat.v1.constant_initializer, tf.compat.v1.initializers.constant, tf.compat.v1.keras.initializers.Constant, tf.compat.v1.keras.initializers.constant

tf.initializers.constant(
    value=0, dtype=tf.dtypes.float32, verify_shape=False
)

The resulting tensor is populated with values of type dtype, as specified by arguments value following the desired shape of the new tensor (see examples below).

The argument value can be a constant value, or a list of values of type dtype. If value is a list, then the length of the list must be less than or equal to the number of elements implied by the desired shape of the tensor. In the case where the total number of elements in value is less than the number of elements required by the tensor shape, the last element in value will be used to fill the remaining entries. If the total number of elements in value is greater than the number of elements required by the tensor shape, the initializer will raise a ValueError.

Args
value	A Python scalar, list or tuple of values, or a N-dimensional numpy array. All elements of the initialized variable will be set to the corresponding value in the value argument.
dtype	Default data type, used if no dtype argument is provided when calling the initializer.
verify_shape	Boolean that enables verification of the shape of value. If True, the initializer will throw an error if the shape of value is not compatible with the shape of the initialized tensor.

Raises
TypeError	If the input value is not one of the expected types.

Examples:

The following example can be rewritten using a numpy.ndarray instead of the value list, even reshaped, as shown in the two commented lines below the value list initialization.

import numpy as np
import tensorflow as tf

  

value = [0, 1, 2, 3, 4, 5, 6, 7]

value = np.array(value)

value = value.reshape([2, 4])

init = tf.compat.v1.constant_initializer(value)

<pre class="devsite-click-to-copy prettyprint lang-py">
  <code class="devsite-terminal" data-terminal-prefix="&gt;&gt;&gt;">print(&#x27;fitting shape:&#x27;)</code>
  <code class="devsite-terminal" data-terminal-prefix="&gt;&gt;&gt;">with tf.compat.v1.Session():</code>
  <code class="devsite-terminal" data-terminal-prefix="&gt;&gt;&gt;">  x = tf.compat.v1.get_variable(&#x27;x&#x27;, shape=[2, 4], initializer=init)</code>
  <code class="devsite-terminal" data-terminal-prefix="&gt;&gt;&gt;">  x.initializer.run()</code>
  <code class="devsite-terminal" data-terminal-prefix="&gt;&gt;&gt;">  print(x.eval())</code>
  <code class="no-select nocode">  </code>
</pre>


  fitting shape:
  [[ 0.  1.  2.  3.]
   [ 4.  5.  6.  7.]]

<pre class="devsite-click-to-copy prettyprint lang-py">
  <code class="devsite-terminal" data-terminal-prefix="&gt;&gt;&gt;">print(&#x27;larger shape:&#x27;)</code>
  <code class="devsite-terminal" data-terminal-prefix="&gt;&gt;&gt;">with tf.compat.v1.Session():</code>
  <code class="devsite-terminal" data-terminal-prefix="&gt;&gt;&gt;">  x = tf.compat.v1.get_variable(&#x27;x&#x27;, shape=[3, 4], initializer=init)</code>
  <code class="devsite-terminal" data-terminal-prefix="&gt;&gt;&gt;">  x.initializer.run()</code>
  <code class="devsite-terminal" data-terminal-prefix="&gt;&gt;&gt;">  print(x.eval())</code>
  <code class="no-select nocode">  </code>
</pre>


  larger shape:
  [[ 0.  1.  2.  3.]
   [ 4.  5.  6.  7.]
   [ 7.  7.  7.  7.]]

<pre class="devsite-click-to-copy prettyprint lang-py">
  <code class="devsite-terminal" data-terminal-prefix="&gt;&gt;&gt;">print(&#x27;smaller shape:&#x27;)</code>
  <code class="devsite-terminal" data-terminal-prefix="&gt;&gt;&gt;">with tf.compat.v1.Session():</code>
  <code class="devsite-terminal" data-terminal-prefix="&gt;&gt;&gt;">  x = tf.compat.v1.get_variable(&#x27;x&#x27;, shape=[2, 3], initializer=init)</code>
  <code class="no-select nocode">  </code>
</pre>


  ValueError: Too many elements provided. Needed at most 6, but received 8

<pre class="devsite-click-to-copy prettyprint lang-py">
  <code class="devsite-terminal" data-terminal-prefix="&gt;&gt;&gt;">print(&#x27;shape verification:&#x27;)</code>
  <code class="devsite-terminal" data-terminal-prefix="&gt;&gt;&gt;">init_verify = tf.compat.v1.constant_initializer(value,</code>
  <code class="no-select nocode">  verify_shape=True)</code>
  <code class="devsite-terminal" data-terminal-prefix="&gt;&gt;&gt;">with tf.compat.v1.Session():</code>
  <code class="devsite-terminal" data-terminal-prefix="&gt;&gt;&gt;">  x = tf.compat.v1.get_variable(&#x27;x&#x27;, shape=[3, 4],</code>
  <code class="no-select nocode">  initializer=init_verify)</code>
  <code class="no-select nocode">  </code>
</pre>


  TypeError: Expected Tensor's shape: (3, 4), got (8,).

Methods

from_config

View source

@classmethod
from_config(
    config
)

Instantiates an initializer from a configuration dictionary.

Example:

initializer = RandomUniform(-1, 1)
config = initializer.get_config()
initializer = RandomUniform.from_config(config)

Args
config	A Python dictionary. It will typically be the output of get_config.

Returns
An Initializer instance.

get_config

View source

get_config()

Returns the configuration of the initializer as a JSON-serializable dict.

Returns
A JSON-serializable Python dict.

__call__

View source

__call__(
    shape, dtype=None, partition_info=None, verify_shape=None
)

Returns a tensor object initialized as specified by the initializer.

Args
shape	Shape of the tensor.
dtype	Optional dtype of the tensor. If not provided use the initializer dtype.
partition_info	Optional information about the possible partitioning of a tensor.