init.py 文件源码

def kaiming_normal(tensor, a=0, mode='fan_in'):
    """Fills the input Tensor or Variable with values according to the method described in "Delving deep into
    rectifiers: Surpassing human-level performance on ImageNet classification" - He, K. et al. (2015), using a normal
    distribution. The resulting tensor will have values sampled from :math:`N(0, std)` where
    :math:`std = \sqrt{2 / ((1 + a^2) \\times fan\_in)}`. Also known as He initialisation.

    Args:
        tensor: an n-dimensional torch.Tensor or autograd.Variable
        a: the negative slope of the rectifier used after this layer (0 for ReLU by default)
        mode: either 'fan_in' (default) or 'fan_out'. Choosing `fan_in` preserves the magnitude of the variance of the
              weights in the forward pass. Choosing `fan_out` preserves the magnitudes in the backwards pass.

    Examples:
        >>> w = torch.Tensor(3, 5)
        >>> nn.init.kaiming_normal(w, mode='fan_out')
    """
    if isinstance(tensor, Variable):
        kaiming_normal(tensor.data, a=a, mode=mode)
        return tensor

    fan = _calculate_correct_fan(tensor, mode)
    gain = calculate_gain('leaky_relu', a)
    std = gain / math.sqrt(fan)
    return tensor.normal_(0, std)