# Module: tf.compat.v1.initializers

<br />

|---|
| [![](https://www.tensorflow.org/images/tf_logo_32px.png) TensorFlow 1 version](https://www.tensorflow.org/versions/r1.15/api_docs/python/tf/compat/v1/initializers) |

Public API for tf.initializers namespace.

## Classes

[`class constant`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/initializers/Constant): Initializer that generates tensors with constant values.

[`class glorot_normal`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/initializers/glorot_normal): The Glorot normal initializer, also called Xavier normal initializer.

[`class glorot_uniform`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/initializers/glorot_uniform): The Glorot uniform initializer, also called Xavier uniform initializer.

[`class identity`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/initializers/Identity): Initializer that generates the identity matrix.

[`class ones`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/initializers/Ones): Initializer that generates tensors initialized to 1.

[`class orthogonal`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/initializers/Orthogonal): Initializer that generates an orthogonal matrix.

[`class random_normal`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/random_normal_initializer): Initializer that generates tensors with a normal distribution.

[`class random_uniform`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/random_uniform_initializer): Initializer that generates tensors with a uniform distribution.

[`class truncated_normal`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/truncated_normal_initializer): Initializer that generates a truncated normal distribution.

[`class uniform_unit_scaling`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/uniform_unit_scaling_initializer): Initializer that generates tensors without scaling variance.

[`class variance_scaling`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/initializers/VarianceScaling): Initializer capable of adapting its scale to the shape of weights tensors.

[`class zeros`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/initializers/Zeros): Initializer that generates tensors initialized to 0.

## Functions

[`global_variables(...)`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/global_variables_initializer): Returns an Op that initializes global variables.

[`he_normal(...)`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/initializers/he_normal): He normal initializer.

[`he_uniform(...)`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/initializers/he_uniform): He uniform variance scaling initializer.

[`lecun_normal(...)`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/initializers/lecun_normal): LeCun normal initializer.

[`lecun_uniform(...)`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/initializers/lecun_uniform): LeCun uniform initializer.

[`local_variables(...)`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/local_variables_initializer): Returns an Op that initializes all local variables.

[`tables_initializer(...)`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/tables_initializer): Returns an Op that initializes all tables of the default graph.

[`variables(...)`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/variables_initializer): Returns an Op that initializes a list of variables.