chainer.initializers.LeCunUniform

class chainer.initializers.LeCunUniform(scale=1.0, dtype=None)

Initializes array with a scaled uniform distribution.

Each element of the array is initialized by the value drawn independently from uniform distribution \([-s, s]\) where \(s = scale \times \sqrt{\frac{3}{fan_{in}}}\). Here \(fan_{in}\) is the number of input units.

Reference: LeCun 98, Efficient Backprop http://yann.lecun.com/exdb/publis/pdf/lecun-98b.pdf

Variables

• scale (float) – A constant that determines the scale of the uniform distribution.

• dtype – Data type specifier.

Methods

__call__(array)

Initializes given array.

This method destructively changes the value of array. The derived class is required to implement this method. The algorithms used to make the new values depend on the concrete derived classes.

Parameters

array (numpy.ndarray or cupy.ndarray) – An array to be initialized by this initializer.