neupy.init.XavierUniform

class neupy.init.XavierUniform[source]

Xavier Glorot parameter initialization method based on uniform distribution.

Parameters:
gain : float

Scales variance of the distribution by this factor. Value 2 is a suitable choice for layers that have Relu non-linearity. Defaults to 1.

seed : None or int

Random seed. Integer value will make results reproducible. Defaults to None.

References

[1] Xavier Glorot, Y Bengio. Understanding the difficulty
of training deep feedforward neural networks, 2010.

Methods

sample(shape, return_array=False) Returns tensorflow’s tensor or numpy array with specified shape. Type of the object depends on the return_array value. Numpy array will be returned when return_array=True and tensor otherwise.
sample(shape, return_array=False)[source]

Returns tensorflow’s tensor with specified shape.

Parameters:
shape : tuple

Parameter shape.

return_array : bool

Returns numpy’s array when equal to True and tensorflow’s tensor when equal to False. Defaults to False.

Returns:
array-like or Tensor