Function glorot_uniform

python/singa/initializer.py:115–129

Glorot uniform initializer, also called Xavier uniform initializer. It draws samples from a uniform distribution within [-limit, limit] where `limit` is `sqrt(6 / (fan_in + fan_out))` where `fan_in` is the number of input units in the weight tensor and `fan_out` is the number of out

(t)

def glorot_uniform(t):
    """Glorot uniform initializer, also called Xavier uniform initializer.

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

    # Arguments
        t(Tensor):the tensor to be filled in.
    # References
        - [Understanding the difficulty of training deep feedforward neural
           networks](http://jmlr.org/proceedings/papers/v9/glorot10a/glorot10a.pdf)
    """
    _random_fill(t, scale=1., mode='fan_avg', distribution='uniform')


def he_normal(t):