Function he_uniform

python/singa/initializer.py:165–180

Initialize the values of the input tensor following a uniform distribution with specific bounds. It draws samples from a uniform distribution within [-limit, limit] where `limit` is `sqrt(6 / fan_in)` where `fan_in` is the number of input units in the weight tensor. # Arguments

(t)

def he_uniform(t):
    '''Initialize the values of the input tensor following a uniform
    distribution with specific bounds.

    It draws samples from a uniform distribution within [-limit, limit]
    where `limit` is `sqrt(6 / fan_in)`
    where `fan_in` is the number of input units in the weight tensor.

    # Arguments
        t(Tensor): the tensor to be filled in.

    # References
        - [Delving Deep into Rectifiers: Surpassing Human-Level Performance on
           ImageNet Classification](http://arxiv.org/abs/1502.01852)
    '''
    _random_fill(t, scale=2., mode='fan_in', distribution='uniform')


@deprecated(reason="Use he_normal or glorot_normal")