Apply to speak at TensorFlow World. Deadline April 23rd. Propose talk

tf.initializers.uniform_unit_scaling

Class uniform_unit_scaling

Inherits From: Initializer

Aliases:

  • Class tf.initializers.uniform_unit_scaling
  • Class tf.uniform_unit_scaling_initializer

Defined in tensorflow/python/ops/init_ops.py.

Initializer that generates tensors without scaling variance.

When initializing a deep network, it is in principle advantageous to keep the scale of the input variance constant, so it does not explode or diminish by reaching the final layer. If the input is x and the operation x * W, and we want to initialize W uniformly at random, we need to pick W from

[-sqrt(3) / sqrt(dim), sqrt(3) / sqrt(dim)]

to keep the scale intact, where dim = W.shape[0] (the size of the input). A similar calculation for convolutional networks gives an analogous result with dim equal to the product of the first 3 dimensions. When nonlinearities are present, we need to multiply this by a constant factor. See (Sussillo et al., 2014) for deeper motivation, experiments and the calculation of constants. In section 2.3 there, the constants were numerically computed: for a linear layer it's 1.0, relu: ~1.43, tanh: ~1.15.

Args:

  • factor: Float. A multiplicative factor by which the values will be scaled.
  • seed: A Python integer. Used to create random seeds. See tf.set_random_seed for behavior.
  • dtype: Default data type, used if no dtype argument is provided when calling the initializer. Only floating point types are supported.

References: Sussillo et al., 2014 (pdf)

__init__

__init__(
    factor=1.0,
    seed=None,
    dtype=tf.dtypes.float32
)

DEPRECATED FUNCTION

Methods

__call__

__call__(
    shape,
    dtype=None,
    partition_info=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.

from_config

from_config(
    cls,
    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

get_config()

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

Returns:

A JSON-serializable Python dict.