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

  • 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'.