# chainer.initializers.HeNormal¶

class chainer.initializers.HeNormal(scale=1.0, dtype=None, fan_option='fan_in', **kwargs)[source]

Initializes array with scaled Gaussian distribution.

Each element of the array is initialized by the value drawn independently from Gaussian distribution whose mean is 0, and standard deviation is $$scale \times \sqrt{\frac{2}{fan}}$$. If fan_option == 'fan_in', $$fan$$ is the number of input units. If fan_option == 'fan_out', $$fan$$ is the number of output units.

Reference: He et al., https://arxiv.org/abs/1502.01852

Parameters
• scale (float) – A constant that determines the scale of the standard deviation.

• dtype – Data type specifier.

• fan_option ({'fan_in', 'fan_out'}) – Decides how to compute the standard deviation. The default value is 'fan_in'.

• rng (xp.random.RandomState) – Pseudo-random number generator.

Methods

__call__(array)[source]

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 (N-dimensional array) – An array to be initialized by this initializer.

__eq__(value, /)

Return self==value.

__ne__(value, /)

Return self!=value.

__lt__(value, /)

Return self<value.

__le__(value, /)

Return self<=value.

__gt__(value, /)

Return self>value.

__ge__(value, /)

Return self>=value.