Help protect the Great Barrier Reef with TensorFlow on Kaggle Join Challenge


View source on GitHub

Initializer that generates an orthogonal matrix.

Inherits From: Initializer

Initializers allow you to pre-specify an initialization strategy, encoded in the Initializer object, without knowing the shape and dtype of the variable being initialized.

If the shape of the tensor to initialize is two-dimensional, it is initialized with an orthogonal matrix obtained from the QR decomposition of a matrix of random numbers drawn from a normal distribution. If the matrix has fewer rows than columns then the output will have orthogonal rows. Otherwise, the output will have orthogonal columns.

If the shape of the tensor to initialize is more than two-dimensional, a matrix of shape (shape[0] * ... * shape[n - 2], shape[n - 1]) is initialized, where n is the length of the shape vector. The matrix is subsequently reshaped to give a tensor of the desired shape.


def make_variables(k, initializer):
  return (tf.Variable(initializer(shape=[k, k], dtype=tf.float32)),
          tf.Variable(initializer(shape=[k, k, k], dtype=tf.float32)))
v1, v2 = make_variables(3, tf.initializers.Orthogonal())
<tf.Variable ... shape=(3, 3) ...
<tf.Variable ... shape=(3, 3, 3) ...
make_variables(4, tf.initializers.Orthogonal(gain=0.5))
(<tf.Variable ... shape=(4, 4) dtype=float32...
 <tf.Variable ... shape=(4, 4, 4) dtype=float32...

gain multiplicative factor to apply to the orthogonal matrix
seed A Python integer. Used to create random seeds. See tf.random.set_seed for behavior.


Saxe et al., 2014 (pdf)



View source

Instantiates an initializer from a configuration dictionary.


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

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

An Initializer instance.


View source

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

A JSON-serializable Python dict.


View source

Returns a tensor object initialized as specified by the initializer.

shape Shape of the tensor.
dtype Optional dtype of the tensor. Only floating point types are supported.

ValueError If the dtype is not floating point or the input shape is not valid.